Daily AI Implementation Scout Council

Today's ranked top 20

#1

build nowBoth runtimes33 / 35

mattpocock/skills skill

Engineering skills from Matt Pocock's personal .agents directory, published as a public repo. Includes ask-matt (skill router), grill-with-docs (domain model builder updating CONTEXT.md and ADRs inline), triage (issue state machine), improve-codebase-architecture (visual HTML report of deepening opportunities), to-spec (formalises the current conversation into a spec file), to-tickets (decomposes any plan into issue-tracker tickets), and setup-matt-pocock-skills (one-time repo config). MIT license, Shell.

What it does for you: AXION engineering decisions, spec writing, and codebase architecture reviews are currently ad hoc. to-spec captures decisions already in a chat into a formal spec file; to-tickets decomposes that spec into trackable work items; improve-codebase-architecture scans any AXION component and produces a visual report. Matt Pocock uses these skills in his own daily engineering work, making them tested against real codebases rather than generic templates.

In practice: 231,872 GitHub stars, 2,684 new stars today. Fourth consecutive day trending all languages. Star momentum remains among the highest of any repo on trending today. MIT license, Shell.

For: Both runtimes. SKILL.md files with no build step. Compatible with Claude Code, Hermes, and any skill-runner that reads the Agent Skills format.

Security4

Quality5

Auditability5

Useful to you5

Useful to community5

Buildable now5

Hermes4

Verdict: build now. 33 total. Fourth consecutive day as build now, still not adopted in AXION. Tiebreaker over thedotmack/claude-mem: both score 33, neither is new today, mattpocock/skills takes rank 1 on today's star momentum (2,684 vs approximately 100 for claude-mem).

Build #1 mattpocock/skills: use the ai-implementation-build-intake skill to build this safely. Source: https://github.com/mattpocock/skills. Save canonical skill/agent under AXION\Skills and AXION\Agents. Copy

Source · 231,872 GitHub stars, 2,684 new stars today (trending all languages, day 4). MIT license, Shell. Published from the author's personal .agents directory. Last listed 2026-08-22 with verdict build now.

#2

build nowBoth runtimes33 / 35

thedotmack/claude-mem plugin

Persistent context compression system for agent sessions, v13.4.0, Apache 2.0, Node 20+. Captures what an agent does during a Claude Code session, compresses it with AI into a structured memory block, and injects relevant context back into future sessions automatically. Install with one command: `npx claude-mem install`. Also installable via the Claude Code plugin marketplace. Works with Claude Code, Hermes, Codex, Gemini CLI, Copilot, OpenCode, and more. Listed in awesome-claude-code.

What it does for you: AXION sessions lose context between Claude Code runs and Hermes runs, forcing YY to write manual handoff documents. claude-mem automates that handoff: after each session it compresses what happened into a dated memory block, and the next session in any supported CLI reads it before starting. The AI compression step keeps the injected context within token budget even across many sessions. Hermes is explicitly listed as a supported target. Not currently in YY's enabledPlugins.

In practice: Approximately 91,500 GitHub stars. Third consecutive day as a build-now carry. v13.4.0 signals 13 major release cycles. Listed in awesome-claude-code with an official badge.

For: Both runtimes. Installs via npx into Claude Code as a plugin hook, but the compressed memory file it writes is vendor-agnostic markdown that Hermes and Codex read at session start. Works wherever an agent CLI reads a session context file.

Security4

Quality5

Auditability5

Useful to you5

Useful to community5

Buildable now5

Hermes4

Verdict: build now. 33 total. Third consecutive day as build now. thedotmack/claude-mem and mattpocock/skills both score 33; mattpocock takes rank 1 today on star momentum. Directly solves AXION's top operational gap with no infrastructure requirement beyond Node 20. Not yet adopted.

Install: run `npx claude-mem install` to hook into Claude Code automatically, or use `/plugin marketplace add thedotmack/claude-mem` then `/plugin install claude-mem` inside Claude Code. Not currently in YY's enabledPlugins. Review before enabling. Copy

Source · Approximately 91,500 GitHub stars. v13.4.0, Apache 2.0, Node >=20. Listed in awesome-claude-code. Homepage at claude-mem.ai. Last listed 2026-08-22 with verdict build now.

#3

build nowBoth runtimes32 / 35

microsoft/SkillOpt repo

Text-space optimizer from Microsoft Research that trains reusable natural-language skills for frozen LLM agents through trajectory-driven edits and validation-gated updates. Produces deployable best_skill.md artifacts. Ships SkillOpt-Sleep in v0.2.0: a nightly self-evolution engine that harvests real agent session data, mines improvement opportunities, replays and consolidates them behind a held-out validation gate. Claude Code integration shell is in the repo.

What it does for you: AXION updates skills manually. SkillOpt replaces that loop with a research-backed automated pipeline: SkillOpt-Sleep reads real Claude Code session trajectories, identifies skill weaknesses, proposes edits, validates them against held-out tests, and writes an improved best_skill.md. This is the first skill optimizer with a published paper, a PyPI release, and a Claude Code integration shell in one package.

In practice: Approximately 16,100 GitHub stars, 1,500 forks as of 2026-08-22. Microsoft Research blog feature 2026-07-24 with VentureBeat and The Decoder coverage. Fifth consecutive day as a build-now carry: not yet adopted in AXION.

For: Both runtimes. Python package (pip install skillopt). Ships integration shells for Claude Code, Codex, Copilot, and Devin. SKILL.md artifacts are format-agnostic and run in Hermes or any skill-compatible harness.

Security4

Quality5

Auditability5

Useful to you5

Useful to community5

Buildable now4

Hermes4

Verdict: build now. 32 total. Fifth consecutive day as build now, still not adopted in AXION. pip install skillopt plus the Claude Code integration shell in the repo is same-day safe.

Build #3 microsoft/SkillOpt: use the ai-implementation-build-intake skill to build this safely. Source: https://github.com/microsoft/SkillOpt. Save canonical skill/agent under AXION\Skills and AXION\Agents. Copy

Source · Approximately 16,100 GitHub stars, 1,500 forks as of 2026-08-22. v0.2.0 on PyPI released 2026-07-02. Microsoft Research blog post 2026-07-24. MIT license. Last listed 2026-08-22 with verdict build now.

#4

build nowBoth runtimes32 / 35

alirezarezvani/claude-skills skill

Community collection of 345 Claude Code and agent skills across 10 domains: engineering core (52 skills), engineering powerful (84 skills including agent-harness, zero-hallucination-coder, and skillopt-sleep), product, marketing, compliance, C-level advisory, research, business operations, commercial and finance, and daily productivity. Ships 30+ prebuilt agents and 70+ custom commands.

What it does for you: YY can clone this repo and cherry-pick from 345 battle-tested skills rather than writing from scratch. The agent-harness skill adds a goal-plan-execute-verify-close loop over any domain. The engineering/skillopt-sleep module ties this collection to the SkillOpt automated nightly improvement loop at rank 3. Updated 2026-08-18, five days before today.

In practice: Approximately 24,700 GitHub stars, 3,500 forks as of 2026-08-22. Updated 2026-08-18. Fifth consecutive day as a build-now carry: not yet adopted in AXION.

For: Both runtimes. Markdown skill files with no build step; compatible with Claude Code, Codex, Hermes, and any skill-runner that reads SKILL.md or CLAUDE.md format.

Security4

Quality4

Auditability4

Useful to you5

Useful to community5

Buildable now5

Hermes5

Verdict: build now. 32 total. Fifth consecutive day as build now. Clone and copy individual skills today.

Build #4 alirezarezvani/claude-skills: use the ai-implementation-build-intake skill to build this safely. Source: https://github.com/alirezarezvani/claude-skills. Save canonical skill/agent under AXION\Skills and AXION\Agents. Copy

Source · Approximately 24,700 GitHub stars, 3,500 forks as of 2026-08-22. Updated 2026-08-18. 345 skills across 10 domains. Last listed 2026-08-22 with verdict build now.

#5

build nowBoth runtimes32 / 35

affaan-m/ECC repo

Engineering Coding Companion: 68 agents, 286 skills, and 94 custom commands built on a plan->test->implement->review->verify->remember->improve loop. Trending all languages today with 242,143 stars. The AgentShield component is a security scanner for Claude Code installations: it runs as `npx ecc-agentshield scan` with no install step, executes 1,282 tests with 98% coverage, and applies 102 static analysis rules across secrets detection (14 patterns), permission auditing, hook injection analysis, MCP server risk profiling, and agent config review. Scans CLAUDE.md, settings.json, MCP configs, hooks, agent definitions, and skills. MIT license, JavaScript.

What it does for you: AXION has no automated security review of its Claude Code installation. AgentShield runs today with one npx command against the AXION settings.json, CLAUDE.md, hooks, and skill files, and produces a scored security report. The 14-pattern secrets scanner catches credential leaks in hooks and scripts before they reach git. The 286 skills and 68 agents are a separate productivity layer; adopt AgentShield first as a standalone scan, then evaluate the skill library separately.

In practice: 242,143 GitHub stars, 428 new stars today, trending all languages on 2026-08-23. Last listed 2026-08-11 with verdict watch. Upgrade trigger: AgentShield section with npx zero-install path, 1,282 tests, and 102 rules represents a material change from the prior listing. MIT license, JavaScript.

For: Both runtimes. 286 skills are in Agent Skills SKILL.md format, compatible with Claude Code, Hermes, Codex, and Cursor. AgentShield runs as a zero-install npx command on any machine with Node. 68 agents use a vendor-agnostic plan->test->implement->review->verify->remember->improve loop.

Security4

Quality5

Auditability4

Useful to you5

Useful to community5

Buildable now5

Hermes4

Verdict: build now. 32 total. Upgraded from watch (last listed 2026-08-11) to build now via the AgentShield material change: a zero-install security scanner for AXION's own Claude Code setup that runs today with `npx ecc-agentshield scan`. Scores: security 4, review_quality 5, review_auditability 4, useful_yy 5, useful_community 5, buildable_now 5, hermes_usable 4.

Build #5 affaan-m/ECC: use the ai-implementation-build-intake skill to build this safely. Source: https://github.com/affaan-m/ECC. Save canonical skill/agent under AXION\Skills and AXION\Agents. Copy

Source · 242,143 GitHub stars, 428 new stars today (trending all languages, 2026-08-23). 1,282 AgentShield tests, 98% coverage, 102 static analysis rules across 5 categories, 14 secrets detection patterns. 286 skills, 68 agents, 94 commands. MIT license. Last listed 2026-08-11 with verdict watch.

#6

test firstBoth runtimes31 / 35

pydantic/pydantic-ai repo

Python AI agent framework from the Pydantic team. Typed end-to-end across agents, realtime voice, image generation, and embeddings. Every major model provider supported, including Anthropic natively. Dependency injection for tools. Pydantic model validation on all LLM outputs. Supports structured streaming and multi-turn conversations with typed state.

What it does for you: AXION agents today produce untyped output requiring ad hoc JSON parsing and retry logic. Pydantic AI replaces that pattern with full typing from the LLM response through to Python objects, eliminating custom parsing code in every AXION agent. The Anthropic provider ships natively; no adapter or wrapper needed.

In practice: Approximately 19,400 GitHub stars, 2,600 forks as of 2026-08-22. MIT license. Built by the Pydantic team, whose validation library is a Python ecosystem standard. Last listed 2026-08-22 with verdict test first.

For: Both runtimes. Python package; provider-agnostic typed agent framework. Native Anthropic provider ships in the package. Hermes can use it directly for typed response validation from any LLM call.

Security4

Quality5

Auditability5

Useful to you4

Useful to community4

Buildable now4

Hermes5

Verdict: test first. 31 total. The Anthropic provider is native, making this a same-session test. Try it on one AXION agent that currently does manual JSON parsing and compare output quality before committing to wider adoption.

Build #6 pydantic/pydantic-ai: use the ai-implementation-build-intake skill to build this safely. Source: https://github.com/pydantic/pydantic-ai. Save canonical skill/agent under AXION\Skills and AXION\Agents. Copy

Source · Approximately 19,400 GitHub stars, 2,600 forks as of 2026-08-22. MIT license. Anthropic provider documented at ai.pydantic.dev/api/models/anthropic/. pip install pydantic-ai. Last listed 2026-08-22.

#7

test firstBoth runtimes31 / 35

VoltAgent/awesome-agent-skills repo

Curated collection of 1,000+ Agent Skills from official engineering teams at Anthropic, Google, Vercel, Stripe, Cloudflare, and others. Each entry links to a vetted SKILL.md or skills directory. MIT license. The README includes an explicit disclaimer: no security audit has been performed on the listed skills, and users are responsible for reviewing skills before enabling them. Re-listed today after 46 days (last listed 2026-07-08 with verdict build now).

What it does for you: Rather than discovering individual skill repos through search, this list serves as a curated starting directory for filling AXION's skill library from official sources. The Anthropic, Vercel, and Stripe official entries carry institutional-quality review and are directly applicable to AXION workflows. The disclaimer means each skill still needs individual review before enabling; treat this as a discovery index, not a wholesale install.

In practice: 30,900 GitHub stars, 3,300 forks. MIT license. Re-listed after 46 days; last seen 2026-07-08. Verdict changed from build now to test first today due to the explicit security disclaimer in the README driving security to 3.

For: Both runtimes. Curated index of Agent Skills SKILL.md files from official teams. Skills themselves are format-agnostic and load into Claude Code, Hermes, Codex, Cursor, and any Agent Skills compatible runner.

Security3

Quality4

Auditability4

Useful to you5

Useful to community5

Buildable now5

Hermes5

Verdict: test first. 31 total. Security scored 3 because the repository's own README states no security audit has been performed on listed skills. Score of 31 falls below the 32 build-now threshold. Last verdict was build now (2026-07-08); today's downgrade reflects the security disclaimer discovered on re-read. Review each skill individually before adding to AXION. Start with official Anthropic, Vercel, and Stripe entries which have institutional backing.

Build #7 VoltAgent/awesome-agent-skills: use the ai-implementation-build-intake skill to build this safely. Source: https://github.com/VoltAgent/awesome-agent-skills. Save canonical skill/agent under AXION\Skills and AXION\Agents. Copy

Source · 30,900 GitHub stars, 3,300 forks. MIT license. 1,000+ skills from official teams including Anthropic, Google, Vercel, Stripe, and Cloudflare. Security disclaimer present in README. Last listed 2026-07-08 with verdict build now.

#8

test firstBoth runtimes31 / 35

anthropics/skills repo

Official Anthropic public skills repository. Contains SKILL.md files published from Anthropic's own engineering teams. Highlights: docx, pdf, pptx, and xlsx skills that power Claude.ai document creation (source-available, separate licence from Apache 2.0); algorithmic-art and canvas-design skills; frontend-design skill (the same skill already in YY's enabledPlugins via claude-plugins-official); MCP server generation skill; and a web app testing skill. Apache 2.0 for most skills. Re-listed today after 11 days (last listed 2026-08-12 with verdict watch). 171,000 stars, 20,300 forks.

What it does for you: The frontend-design skill in this repo is already active in YY's Claude Code as an enabled plugin, confirming practical quality. The MCP server generation skill lets Claude Code scaffold a complete MCP server from a description in one session, directly useful for the AXION tool build queue. The docx and pdf skills would replace the current headless Chrome workaround for document export in some AXION flows. Upgrade from watch to test first: material additions since last listing are the source-available document skills and the MCP server generation skill.

In practice: 171,000 GitHub stars, 20,300 forks. Apache 2.0 for most skills; document skills (docx, pdf, pptx, xlsx) are source-available under a separate term. Official Anthropic repo. Re-listed after 11 days; upgraded from watch to test first. frontend-design skill already in YY's enabledPlugins, confirming practical value.

For: Both runtimes. Official Anthropic skill files in Agent Skills format. Skills are format-agnostic SKILL.md files that load into Claude Code, Hermes, and any compatible runner. The MCP server generation skill and web app testing skill target Claude Code specifically.

Security5

Quality5

Auditability5

Useful to you3

Useful to community5

Buildable now4

Hermes4

Verdict: test first. 31 total. Upgraded from watch (last listed 2026-08-12). Material change: source-available document skills and the MCP server generation skill were not prominent in the prior listing. useful_yy scored 3 because the document skills require a separate licence review before production use and the MCP generation skill needs testing against AXION's specific server patterns.

Build #8 anthropics/skills: use the ai-implementation-build-intake skill to build this safely. Source: https://github.com/anthropics/skills. Save canonical skill/agent under AXION\Skills and AXION\Agents. Copy

Source · 171,000 GitHub stars, 20,300 forks. Official Anthropic repository. Apache 2.0 for most skills. frontend-design skill already enabled in YY's Claude Code installation. MCP server generation skill and document skills present in repo. Last listed 2026-08-12 with verdict watch.

#9

test firstClaude (Axion)30 / 35

diet103/claude-code-infrastructure-showcase repo

Reference implementation of Claude Code infrastructure patterns: a skill-activation-prompt hook that fires on every user prompt and checks a skill-rules.json file for trigger patterns, suggesting relevant skills automatically. Ships a hooks README, agents README, skills README, and a Claude integration guide written for AI-assisted setup.

What it does for you: AXION already has hooks in settings.json but no systematic trigger-based skill activation. Copying the two essential hooks and one skill-rules.json from this repo introduces declarative, auditable auto-activation. With the large skill libraries at ranks 1, 3, and 4 now on the action queue, a skill-rules.json makes routing to the right skill automatic instead of manual.

In practice: Approximately 10,000 GitHub stars as of 2026-08-22. TypeScript, MIT. Last listed 2026-08-22 with verdict test first.

For: Claude (Axion). Claude Code-specific: the skill-activation-prompt hook and skill-rules.json pattern are designed for Claude Code's hook and skill runtime. Hermes does not run the same hook lifecycle.

Security4

Quality4

Auditability4

Useful to you5

Useful to community4

Buildable now5

Hermes4

Verdict: test first. 30 total. Test on an isolated project first to confirm the hook does not conflict with the build-gate.js hook already in AXION settings.json.

Build #9 diet103/claude-code-infrastructure-showcase: use the ai-implementation-build-intake skill to build this safely. Source: https://github.com/diet103/claude-code-infrastructure-showcase. Save canonical skill/agent under AXION\Skills and AXION\Agents. Copy

Source · Approximately 10,000 GitHub stars as of 2026-08-22. Updated 2026-07-13. TypeScript, MIT license. Ships CLAUDE_INTEGRATION_GUIDE.md plus three README files covering skills, hooks, and agents. Last listed 2026-08-22.

#10

test firstBoth runtimes29 / 35

akitaonrails/ai-memory repo

Rust CLI for long-term memory across agent coding sessions and cross-vendor handoff. Stores structured task context, failed approaches, open questions, and architecture notes in a vendor-agnostic format. When switching from Claude Code to another CLI in the same directory, the next agent reads the memory and continues without re-explaining the project. Ships a web UI for memory inspection and proactive query routing via Agent Skills.

What it does for you: AXION sessions switch between Claude Code and Hermes; context is currently lost unless YY writes handoffs manually. ai-memory automates that handoff via a Rust CLI. Note: thedotmack/claude-mem at rank 2 addresses the same gap via a plugin install. Both are on the test queue; ai-memory uses structured task context while claude-mem uses AI-compressed session summaries. Test both and compare recovery quality before committing to one.

In practice: 2,673 GitHub stars, 231 forks as of 2026-08-22. Rust 1.95+, MIT license. Last listed 2026-08-22 with verdict test first.

For: Both runtimes. Rust CLI binary that writes a vendor-agnostic memory block and Agent Skills files into any project directory. Works with Claude Code, Codex, Gemini CLI, and any agent CLI. Hermes can read the resulting memory files at session startup.

Security4

Quality4

Auditability4

Useful to you5

Useful to community5

Buildable now4

Hermes3

Verdict: test first. 29 total. Two cross-session memory solutions are on the action queue: claude-mem at rank 2 and ai-memory at rank 10. Test both on a non-critical project and compare before adopting either.

Build #10 akitaonrails/ai-memory: use the ai-implementation-build-intake skill to build this safely. Source: https://github.com/akitaonrails/ai-memory. Save canonical skill/agent under AXION\Skills and AXION\Agents. Copy

Source · 2,673 GitHub stars, 231 forks as of 2026-08-22. Rust 1.95+, MIT license. Release badge visible in README. Last listed 2026-08-22.

#11

test firstBoth runtimes29 / 35

mukul975/Anthropic-Cybersecurity-Skills skill

817 structured cybersecurity skills for AI agents, mapped to 6 frameworks: MITRE ATT&CK, NIST CSF 2.0, MITRE ATLAS, D3FEND, NIST AI RMF, and MITRE F3 Fight Fraud. Covers 29 security domains including threat detection, vulnerability management, incident response, and compliance. Apache 2.0. Community project; not affiliated with Anthropic despite the name.

What it does for you: AXION has no dedicated security skills today. This library adds 817 structured audit and defence skills that Claude Code can invoke when reviewing AI-generated code, checking AXION scripts for vulnerabilities, or auditing MCL platform changes. Start with the NIST CSF and D3FEND domains for pure-defence use: those skills cover asset inventory, access control review, and log analysis with no offensive techniques involved.

In practice: Approximately 29,781 GitHub stars, 3,530 forks as of 2026-08-22. Apache 2.0. Security.md and Code of Conduct included. Last listed 2026-08-22 with verdict test first.

For: Both runtimes. agentskills.io standard SKILL.md format. Works with Claude Code, GitHub Copilot, Codex CLI, Cursor, Gemini CLI, and 20+ platforms. Hermes can load SKILL.md files directly.

Security3

Quality4

Auditability4

Useful to you4

Useful to community5

Buildable now5

Hermes4

Verdict: test first. 29 total. The defence and CSF domains are immediately applicable to AXION security reviews. Test on a non-production AXION review first, picking only defence-domain skills. Do not install offensive-technique skills without explicit written authorization for the target system.

Build #11 mukul975/Anthropic-Cybersecurity-Skills: use the ai-implementation-build-intake skill to build this safely. Source: https://github.com/mukul975/Anthropic-Cybersecurity-Skills. Save canonical skill/agent under AXION\Skills and AXION\Agents. Copy

Source · Approximately 29,781 GitHub stars, 3,530 forks as of 2026-08-22. 817 skills across 29 domains. 6 framework mappings documented in README. Apache 2.0. Last listed 2026-08-22.

#12

test firstClaude (Axion)29 / 35

modelcontextprotocol/servers plugin

Anthropic-maintained collection of reference and community MCP server implementations: filesystem, GitHub, Slack, Google Drive, Postgres, fetch, memory, and others. The canonical starting point for adding MCP tools to Claude Code. No new servers confirmed added today.

What it does for you: AXION uses Claude Code with MCP tools daily. The memory server ships a knowledge graph implementation useful for AXION agent memory. The fetch server is directly relevant for the scout newsletter pipeline. Both can be installed with npx commands from this repo without a build step.

In practice: Continuously maintained by Anthropic and the MCP community. No new entries observed in today's plugin scout. Last listed 2026-08-22 with verdict test first.

For: Claude (Axion). Official MCP server reference implementations; each server is installed independently into Claude Code or any MCP client via the mcpServers block in settings.json.

Security4

Quality5

Auditability5

Useful to you3

Useful to community5

Buildable now4

Hermes3

Verdict: test first. 29 total. Re-listed from 2026-08-22. Evaluate the memory and fetch servers specifically rather than the full collection.

Install: enable individual servers by adding them to the mcpServers block in ~/.claude/settings.json following each server's README. Review before enabling. Copy

Source · Official Anthropic repository. MCP org has 24,000+ GitHub followers. Memory server and fetch server documented in the README with npx install commands. No new servers observed in today's plugin scout. Last listed 2026-08-22.

#13

test firstClaude (Axion)28 / 35

yctimlin/mcp_excalidraw plugin

MCP server, Claude Code skill, and CLI for Excalidraw. Provides a programmatic API for creating, editing, and exporting Excalidraw diagrams via AI agents, with real-time canvas sync: when an agent runs a draw command, the live Excalidraw board updates in the browser simultaneously. TypeScript. Installable via npx as an MCP server or by copying the SKILL.md as a Claude Code skill.

What it does for you: AXION planning sessions produce architecture decisions that are currently described in text. mcp_excalidraw lets a Claude Code agent translate those text descriptions into a live Excalidraw diagram in the same session, with the canvas updating in real time. The SKILL.md format means it can be tested without a separate MCP configuration by dropping the file into AXION/Skills. Useful for YY's current AXION architecture documentation and MCL content workflow mapping work.

In practice: 2,300 GitHub stars, 252 forks. TypeScript. Demo video available on YouTube. First listed 2026-08-22; carry from yesterday's new-item find.

For: Claude (Axion). MCP server installed into Claude Code via the mcpServers block in settings.json. Also ships as a Claude Code SKILL.md. Not directly applicable to Hermes without MCP client support.

Security4

Quality4

Auditability4

Useful to you4

Useful to community4

Buildable now5

Hermes3

Verdict: test first. 28 total. Plugin item at the test-first threshold for plugins (28+). Install the SKILL.md first to test diagram generation from a Claude Code session without committing to the full MCP server configuration. Not currently in YY's enabledPlugins or mcpServers.

Install: add to the mcpServers block in ~/.claude/settings.json following the README, or copy the SKILL.md to AXION/Skills to test without MCP setup. Not currently in YY's enabledPlugins. Review before enabling. Copy

Source · 2,300 GitHub stars, 252 forks. TypeScript. Demo video at youtube.com/watch?v=ufW78Amq5qA. First listed 2026-08-22 with verdict test first.

#14

test firstClaude (Axion)28 / 35

context7 (claude-plugins-official external plugin) plugin

MCP server that injects up-to-date library documentation into Claude Code context. When code references a library, context7 fetches current docs for that library version and adds them as context, preventing hallucinated API calls based on outdated training data. Listed in the Anthropic official external plugins directory.

What it does for you: AXION skills and agents frequently call Python library APIs that change between versions. context7 eliminates the class of errors where Claude generates code for an outdated API signature. Not currently in YY's enabledPlugins.

In practice: Listed in the Anthropic-managed external_plugins directory alongside GitHub, GitLab, Discord, Asana, Firebase, and fakechat. No new entries in the official plugins directory observed today. Last listed 2026-08-22 with verdict test first.

For: Claude (Axion). MCP server installed as a Claude Code external plugin via anthropics/claude-plugins-official. Not applicable to Hermes directly.

Security4

Quality4

Auditability4

Useful to you4

Useful to community4

Buildable now5

Hermes3

Verdict: test first. 28 total. Re-listed from 2026-08-22; still not in YY's enabledPlugins. Re-lists at ranks 1 and 2 (VoltAgent, anthropics/skills) push context7 from rank 11 to rank 14.

Install: add context7 to enabledPlugins in ~/.claude/settings.json following the external_plugins/context7 README in anthropics/claude-plugins-official. Not currently in YY's enabledPlugins. Review before enabling. Copy

Source · Listed at github.com/anthropics/claude-plugins-official/tree/main/external_plugins/context7 as of 2026-08-23. Anthropic-reviewed. 7 external plugins in the directory as of today. Last listed 2026-08-22.

#15

test firstClaude (Axion)28 / 35

github (claude-plugins-official external plugin) plugin

Official GitHub MCP server for Claude Code. Provides direct GitHub API access from within a Claude Code session: read repos, files, issues, and PRs; create branches; commit files; open PRs. Listed in the Anthropic official external plugins directory.

What it does for you: AXION runs git operations manually via Bash tools today. The GitHub plugin lets Claude Code read issues, create branches, and open PRs directly, reducing tool-call overhead for the AXION docs repo and future tracked work. Not currently in YY's enabledPlugins.

In practice: Listed in the Anthropic-managed external_plugins directory. No new entries in the official plugins directory observed today. Last listed 2026-08-22 with verdict test first.

For: Claude (Axion). MCP server installed as a Claude Code external plugin via anthropics/claude-plugins-official. Not applicable to Hermes directly.

Security3

Quality4

Auditability4

Useful to you4

Useful to community5

Buildable now5

Hermes3

Verdict: test first. 28 total. Re-listed from 2026-08-22; still not in YY's enabledPlugins. Test on a non-critical repo first to confirm write behaviour before enabling on the main AXION docs repo.

Install: add the github external plugin to enabledPlugins in ~/.claude/settings.json following the external_plugins/github README in anthropics/claude-plugins-official. Not currently in YY's enabledPlugins. Review before enabling. Copy

Source · Listed at github.com/anthropics/claude-plugins-official/tree/main/external_plugins/github as of 2026-08-23. Anthropic-reviewed external plugin. 7 external plugins in directory. Last listed 2026-08-22.

#16

test firstBoth runtimes28 / 35

comet-ml/opik repo

Open-source LLM observability, evaluation, and monitoring platform from CometML. Captures multi-step agent traces: LLM calls, tool executions, retrieval steps, and agent activity in a searchable trace tree. Includes LLM-as-a-judge evaluation metrics, production dashboards, online evaluation rules, guardrails, and a PyTest integration for CI/CD evaluation on every commit.

What it does for you: AXION runs daily agent routines with no visibility into token usage, latency, prompt quality, or eval scores between runs. Opik adds an always-on trace layer that captures every AXION agent run in a searchable dashboard. YY can compare scout run quality across days, debug slow or failing nightly routines, and run automated evals on the scout newsletter output before it deploys.

In practice: Approximately 21,500 GitHub stars, 1,700 forks as of 2026-08-22. MIT license. Fifth consecutive day as a council-carry test first. Last listed 2026-08-22 with verdict test first.

For: Both runtimes. Python SDK plus self-hosted Docker or Opik Cloud. AXION or Hermes agents call it via a decorator or SDK wrapper. Provider-agnostic: works with any LLM.

Security4

Quality4

Auditability4

Useful to you4

Useful to community4

Buildable now4

Hermes4

Verdict: test first. 28 total. Council carry: score of 28 is at the watch floor for a repo, but all 7 axes scored 4 with no weak score and AXION has zero eval/tracing coverage today. Self-hosted Docker install is one-command. Listed as test first with this justification noted per invariant 6.

Build #16 comet-ml/opik: use the ai-implementation-build-intake skill to build this safely. Source: https://github.com/comet-ml/opik. Save canonical skill/agent under AXION\Skills and AXION\Agents. Copy

Source · Approximately 21,500 GitHub stars, 1,700 forks as of 2026-08-22. MIT license. pip install opik. Self-hosted via Docker or Opik Cloud. Last listed 2026-08-22.

#17

watchBoth runtimes28 / 35

microsoft/agent-framework repo

Microsoft's open framework for building, orchestrating, and deploying AI agents and multi-agent workflows in Python and .NET. Key features: multiple LLM provider support, middleware system for request/response processing, graph-based workflows with sequential/concurrent/handoff/group collaboration patterns, checkpointing, streaming, human-in-the-loop, and time-travel debugging. Blog at devblogs.microsoft.com/agent-framework/.

What it does for you: AXION orchestrates multi-step workflows manually today, losing state on failure. agent-framework provides graph-based checkpointed workflows with human-in-the-loop as a native primitive. The Python package is pip-installable and provider-agnostic; Anthropic support needs verification against the current provider list, but the framework design is directly applicable to AXION's orchestrator-worker pattern.

In practice: 13,008 GitHub stars, 2,203 forks, 85 stars on 2026-08-22. Microsoft organization, MIT-compatible license. Last listed 2026-08-22 with verdict watch.

For: Both runtimes. Python package and .NET SDK. Hermes can use the Python package directly. Provider-agnostic across multiple LLM providers.

Security4

Quality4

Auditability4

Useful to you4

Useful to community5

Buildable now3

Hermes4

Verdict: watch. 28 total. Scores 28 which is the watch level for repos (test first starts at 29). Adopting the framework requires code migration, not just installation. Watch until a concrete AXION workflow migration target is identified, then upgrade to test first.

Build #17 microsoft/agent-framework: use the ai-implementation-build-intake skill to build this safely. Source: https://github.com/microsoft/agent-framework. Save canonical skill/agent under AXION\Skills and AXION\Agents. Copy

Source · 13,008 GitHub stars, 2,203 forks, 85 stars on 2026-08-22. Blog at devblogs.microsoft.com/agent-framework/. Python and .NET SDK. Last listed 2026-08-22.

#18

watchBoth runtimes27 / 35

Alishahryar1/free-claude-code repo

Python tool that proxies Claude Code, Codex, Pi, and OpenCode through Google Gemini's free API tier, providing access to 1 billion or more free tokens per month via Google AI Studio. Ships an optional voice interface called OpenClaw. The author claims ToS-friendly operation because it uses the Gemini API legitimately rather than spoofing Claude. MIT license, 46,462 stars, 7,680 forks as of 2026-08-22.

What it does for you: AXION development work uses API tokens for every agent run, including experimental builds, skill testing, and scout newsletter runs. This tool would let YY run those experimental and non-critical sessions through Gemini's free tier instead of consuming paid Claude API quota. Compare actual output quality against a native Claude session before routing any production AXION work through it.

In practice: 46,462 GitHub stars, 7,680 forks as of 2026-08-22. MIT license. First listed 2026-08-22 with verdict watch; carry from yesterday's new-item find.

For: Both runtimes. Python CLI that wraps a Gemini-to-OpenAI-compatible proxy. Works as a drop-in for any agent CLI that accepts an OpenAI-compatible endpoint, including Claude Code, Codex, Hermes, and OpenCode.

Security3

Quality4

Auditability4

Useful to you4

Useful to community5

Buildable now4

Hermes3

Verdict: watch. 27 total. Security score is 3 because the proxy inserts a third-party intermediary into every agent session; any AXION context sent through it is routed via Google AI Studio. Useful for non-sensitive experimental work, but verify the ToS-friendly claim independently before routing MCL content or AXION credentials through the proxy.

Build #18 Alishahryar1/free-claude-code: use the ai-implementation-build-intake skill to build this safely. Source: https://github.com/Alishahryar1/free-claude-code. Save canonical skill/agent under AXION\Skills and AXION\Agents. Copy

Source · 46,462 GitHub stars, 7,680 forks as of 2026-08-22. MIT license. Google AI Studio free tier documented as providing 1 billion or more tokens per month at no cost. First listed 2026-08-22 with verdict watch.

#19

newwatchBoth runtimes27 / 35

zjunlp/LightMem repo

Python library implementing LightMem, accepted at ICLR 2026. A structured compression algorithm for LLM agent memory that reduces token usage by 117x and API calls by 159x while improving benchmark accuracy by 10.9% on LongMemEval. The algorithm selectively compresses and deduplicates past context before injecting it into the active session window. MIT license, Python. Updated 15 hours before this issue.

What it does for you: AXION and Hermes agents accumulate session context across multi-step workflows, consuming tokens even for information already acted on. LightMem would let AXION compress the running context window before expensive LLM calls, cutting API spend on long agent runs. The 117x token reduction measured on LongMemEval translates directly to lower cost and faster responses on multi-step AXION nightly routines. Install today with pip and test on one of the longer nightly routines.

In practice: 1,100 GitHub stars. Python, MIT license. Accepted at ICLR 2026. Updated 15 hours before this issue, signalling active development. New item, first appearance in this registry.

For: Both runtimes. Python package implementing a memory compression algorithm. Provider-agnostic: AXION and Hermes agents call it to compress the running context window before passing to any LLM. No vendor lock-in.

Security4

Quality4

Auditability4

Useful to you4

Useful to community3

Buildable now4

Hermes4

Verdict: watch. 27 total. Score falls in the watch range for repos (test first starts at 29). useful_community scored 3 at 1,100 stars; the research paper has not yet accumulated broad community adoption. Watch until a stable pip release with broader community usage is confirmed, then upgrade to test first.

Build #19 zjunlp/LightMem: use the ai-implementation-build-intake skill to build this safely. Source: https://github.com/zjunlp/LightMem. Save canonical skill/agent under AXION\Skills and AXION\Agents. Copy

Source · 1,100 GitHub stars. ICLR 2026 accepted paper. 117x token reduction, 159x API call reduction, 10.9% accuracy improvement on LongMemEval benchmark. MIT license, Python. Updated 15 hours before this issue. First appearance in this registry.

#20

watchBoth runtimes27 / 35

PostHog/posthog repo

Open-source analytics and AI observability platform. Captures LLM traces including model, prompt, response, token cost, latency, and eval scores across every provider and framework. Ships a Self-driving feature: a scout watches cost, latency, errors, volume, and eval regressions and routes investigation reports to a human inbox when a slice regresses against its baseline. MCP server available for steering from Claude Code or any MCP client.

What it does for you: AXION runs daily agent routines with no eval or regression visibility. PostHog's AI observability layer would capture every AXION agent run in a trace tree and automatically surface regressions, quality drops, or cost spikes as inbox reports. The Self-driving scout stops at a human-routed report rather than opening PRs autonomously, which fits AXION's approval-gate model. Compare with comet-ml/opik at rank 16 before choosing an observability platform.

In practice: 38,584 GitHub stars, 288 new stars today. MIT-compatible license. Last listed 2026-08-22 with verdict watch.

For: Both runtimes. Python SDK that AXION or Hermes agents call to emit trace events. Self-hostable via Docker. MCP server ships for steering from any MCP client including Claude Code.

Security4

Quality5

Auditability4

Useful to you3

Useful to community5

Buildable now3

Hermes3

Verdict: watch. 27 total. Comprehensive platform but buildable_now scored 3 because self-hosting PostHog for AI observability alone is oversize for AXION's current need. Watch alongside opik at rank 16; upgrade to test first once AXION has a specific eval metric to track.

Build #20 PostHog/posthog: use the ai-implementation-build-intake skill to build this safely. Source: https://github.com/PostHog/posthog. Save canonical skill/agent under AXION\Skills and AXION\Agents. Copy

Source · 38,584 GitHub stars, 288 new stars today (trending 2026-08-23). MIT-compatible license. AI observability docs at posthog.com/docs/ai-observability. Last listed 2026-08-22.