apm-retrofit

apm-retrofit is a skill for Claude Code from thinkjones/awesome-apm-stacks. It costs 168 tokens per session (3,806 once invoked), scanned A, original, MIT.

A conversion guide for adding an APM manifest to an existing repository of agent skills, plugins, commands, hooks, or related files. APM is a package manager that installs agent configurations across supported runtimes.

In plain words
What is it for?
Use it to inspect a repository, classify its agent components, and create or update an apm.yml manifest.
Why use it?
It makes an existing repository installable through APM while preserving its current files and reflecting what the repository actually contains.

Skill for Claude Code

Written for Claude Code: Claude Code plugin machinery. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions subagents.

Good fit Use it to inspect a repository, classify its agent components, and create or update an apm.yml manifest.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/thinkjones/awesome-apm-stacks/apm-retrofit
Install

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.

Any agent
npx skills add thinkjones/awesome-apm-stacks --skill apm-retrofit
Clone the repo
git clone --depth 1 https://github.com/thinkjones/awesome-apm-stacks

Made for: Claude Code.

Wrote 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.

agentmods badge for apm-retrofit

README.md
[![agentmods](https://agentmods.dev/badge/skills/thinkjones/awesome-apm-stacks/apm-retrofit/github.svg)](https://agentmods.dev/skills/thinkjones/awesome-apm-stacks/apm-retrofit)
Your own site
<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.

agentmods 80×15 button for apm-retrofit

Your own site · 80×15
<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>
Per session 168 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,806 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 11d ago against content hash e8d1c9c2f817, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

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.

ai-tooling/.apm/skills/apm-retrofit/SKILL.md · 197 lines

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.yml silently. 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 0.1.0 and 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

Read the full file on GitHub · 197 lines

Changes

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.

  1. 11d ago First seen · 197 lines · 168 tokens per session scan A e8d1c9c2f817

Subscribe to this mod's changes

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.

Related

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.

luna-prompts/skillnote · 54 tokens

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.

luna-prompts/skillnote · 50 tokens

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.

luna-prompts/skillnote · 54 tokens

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".

luna-prompts/skillnote · 39 tokens

complete-skill

Rate a SkillNote skill after using it in Codex. Called after applying a skill to record a 1-5 rating and outcome.

luna-prompts/skillnote · 32 tokens

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.

luna-prompts/skillnote · 49 tokens