Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add thinkjones/awesome-apm-stacks --skill apm-retrofitgit clone --depth 1 https://github.com/thinkjones/awesome-apm-stacksWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/thinkjones/awesome-apm-stacks/apm-retrofit)<a href="https://agentmods.dev/skills/thinkjones/awesome-apm-stacks/apm-retrofit"><img src="https://agentmods.dev/badge/skills/thinkjones/awesome-apm-stacks/apm-retrofit/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/thinkjones/awesome-apm-stacks/apm-retrofit"><img src="https://agentmods.dev/badge/skills/thinkjones/awesome-apm-stacks/apm-retrofit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00168 | $0.03806 |
| Opus 5 | $0.00084 | $0.01903 |
| Sonnet 5 | $0.00034 | $0.00761 |
| Haiku 4.5 | $0.00017 | $0.00381 |
Grade A, and why
apm-retrofit scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 197 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Retrofit a repo for APM compliance
This skill converts an existing agent-config repo into a package that Microsoft APM (apm install owner/repo) can resolve, install, and compile to any supported runtime. It is a deliberate extension of apm init (which only drops a stub manifest) — this skill introspects what's actually in the repo, classifies every primitive, and emits a manifest that reflects reality.
You are operating on the repo in the current working directory. Never touch repos outside it. Never run apm install, git push, or any non-local command without explicit user approval.
Ground rules
- Never overwrite an existing
apm.ymlsilently. If one is present, read it, diff your proposal against it, and surface the conflict for the user to resolve. - Never delete existing files. This skill adds and (on approval) edits — it does not remove
plugin.json,CLAUDE.md,AGENTS.md, or anything else. APM is explicitly brownfield-friendly. - Fail loudly on ambiguity. If the repo has no recognisable primitives, stop and tell the user — don't write a meaningless stub manifest.
- Don't guess versions. If no prior version signal exists, propose
0.1.0and ask the user to confirm. - No magic. Every field you emit must be grounded in something you actually observed in the repo. Cite the source (file path) in your report.
Workflow
1. Inventory
Use Glob and Read (not Bash find) to scan the repo. Record every match with its path.
| Primitive | Look in | Evidence |
|---|---|---|
| Claude/Agent Skills | SKILL.md (root), skills/*/SKILL.md, .apm/skills/*/SKILL.md, */SKILL.md |
YAML frontmatter with name: and description: |
| Plugin manifest | plugin.json, .github/plugin/plugin.json, .claude-plugin/plugin.json, .cursor-plugin/plugin.json |
JSON with name and version |
| Sub-agents | agents/*.agent.md, .claude/agents/*.md, .apm/agents/*.agent.md |
Markdown with agent frontmatter |
| Slash commands / prompts | commands/*.md, .claude/commands/*.md, prompts/*.prompt.md, .apm/prompts/*.prompt.md |
Command files |
| Hooks | hooks/*.json, hooks.json, .claude/settings.json (with hooks: key), settings.json |
JSON with hooks |
| MCP servers | .mcp.json, .github/.mcp.json, mcp.json, or mcpServers key inside plugin.json |
JSON server definitions |
| Instructions | AGENTS.md, CLAUDE.md, .github/instructions/*.instructions.md, .apm/instructions/*.instructions.md, .cursorrules |
Markdown/MDC |
| Chatmodes | .github/chatmodes/*.chatmode.md, .apm/chatmodes/*.chatmode.md |
Markdown with chatmode frontmatter |
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 11d ago First seen · 197 lines · 168 tokens per session scan A e8d1c9c2f817
apm-retrofit is a skill published in the GitHub repository thinkjones/awesome-apm-stacks (2 stars, last pushed 3mo ago), licensed MIT. It adds 168 tokens to every session and 3,806 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
skillnote
Self-hosted skill registry for OpenClaw. Stores procedures your team writes (name, description, body), syncs them to disk before each task, and collects which-helped/which-failed signals from the agent so the registry improves over time.
skill-push
Create and push reusable skills to SkillNote from Codex when repeated instructions are detected or the user says "create a skill", "save this pattern", "push a skill". Guides drafting, review, collection selection, and publishing.
skillnote-doctor
A diagnostic tool for OpenClaw agents -- checks skill registry connectivity, AGENTS.md setup, config file validity, and installed skill health. Use when your setup seems broken, skills aren't loading, or you want to audit your agent's configuration.
collection
Choose which SkillNote skill collection is active for this Codex project. Use when the user says "change collection", "switch skills", "use frontend skills", or "show collections".
complete-skill
Rate a SkillNote skill after using it in Codex. Called after applying a skill to record a 1-5 rating and outcome.
skillnote
Show the active SkillNote collection and the skills synced into this project for Codex. Use when the user says "skillnote", "what skills do I have", "show my collection", or wants a SkillNote status/dashboard.