apm: Skill for Claude Code

.agents/skills/apm-spec-guardian/SKILL.md

apm-spec-guardian is a skill for Claude Code, Codex from microsoft/apm. It costs 215 tokens per session (4,815 once invoked), scanned A, original, MIT.

A review process for pull requests that change the OpenAPM specification, its JSON Schemas (structured rules describing valid data), or conformance test fixtures.

In plain words
What is it for?
Use it on pull requests affecting the named specification or test files. It coordinates panel reviews, combines their findings, checks the result against a checklist, and prepares one review comment.
Why use it?
It exposes disagreements, omissions, and edge cases through several independent review panels before the maintainer decides what to ship. The process is advisory and does not automatically block or approve a merge.

Skill for Claude CodeCodex ✓ vendor

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents; installed under .agents/ (shared by several agents).

This is microsoft/apm's own configuration. It tells Claude Code and Codex how to work on apm itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything apm configures →

About the project

APM is a package manager for AI-agent configuration, using a manifest to declare reusable instructions, skills, prompts, agents, hooks, plugins, and MCP components. Development teams use it to reproduce agent setups across projects and control their dependencies through policies and lockfiles, while the catalogue contains many of these agent components.

microsoft/apm · 3,735 stars · on GitHub · microsoft.github.io

Reuse

Borrowing it

Nothing to install: this file belongs to microsoft/apm. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/microsoft/apm/main/.agents/skills/apm-spec-guardian/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/microsoft/apm

Made for: Claude Code, Codex.

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-spec-guardian

README.md
[![agentmods](https://agentmods.dev/badge/skills/microsoft/apm/apm-spec-guardian.svg)](https://agentmods.dev/skills/microsoft/apm/apm-spec-guardian)
Your own site
<a href="https://agentmods.dev/skills/microsoft/apm/apm-spec-guardian"><img src="https://agentmods.dev/badge/skills/microsoft/apm/apm-spec-guardian.svg" alt="Measured on agentmods" height="20"></a>
Per session 215 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,815 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 $0.00215 $0.04815
Opus 5 $0.00108 $0.02407
Sonnet 5 $0.00043 $0.00963
Haiku 4.5 $0.00021 $0.00481

Measured 7d ago against content hash 5e2b98792b45, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

apm-spec-guardian 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 7d 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.

.agents/skills/apm-spec-guardian/SKILL.md · 395 lines

How it starts

The opening of the file, as written. The whole thing — 395 lines — stays where its author put it; the contents beside it link to each section on GitHub.

APM Spec Guardian -- Four-Panel Advisory Review for OpenAPM

This skill institutionalizes the two-round adversarial spec review that produced OpenAPM v0.1 by hand. The panel is FAN-OUT + SYNTHESIZER. Each panelist runs in its own agent thread (via the task tool) and returns JSON matching assets/panelist-return-schema.json. The orchestrator schema-validates each return, hands all returns to the spec-editor-synthesizer (also a task thread, returns JSON matching assets/synthesizer-return-schema.json), runs the linter checklist in assets/linter-checklist.md, then renders ONE comment from assets/comment-template.md.

This skill is ADVISORY by design. It does not compute a binary verdict, it does not apply verdict labels, and it does not gate merge. The panel surfaces findings; the maintainer ships.

Activation scope

This skill activates ONLY when the PR diff touches at least one of:

  • docs/src/content/docs/specs/openapm-*.md (the normative spec artifact, current and future versions)
  • docs/src/content/docs/specs/schemas/*.schema.json (sidecar JSON Schemas, if/when the inline Appendix-A schemas are extracted to files)
  • tests/fixtures/spec-conformance/** (the conformance fixture seed)

Edits to any OTHER documentation page MUST NOT trigger this skill. The maintainer's general docs-sync skill covers those.

Architecture invariants

  • Advisory regime, not gate regime. There is no APPROVE / REJECT, no spec-approved / spec-rejected label, no deterministic verdict computation. The synthesizer returns a ship_decision (fold_and_ship / needs_revision / next_brief); this is prose for the human reviewer, never auto-applied as a label or status check.
  • Ship-meter floor. ship_decision: fold_and_ship REQUIRES shocked_meter_avg >= 7.0. Below 7.0 the synthesizer MUST emit needs_revision (single drafter pass on the existing artifact) or next_brief (another round of panel review with a new brief). The floor is advisory wording in the comment, not a status check.
  • Blocker veto. If ANY panelist returns new_blocking_findings[].length > 0, the synthesizer MUST emit ship_decision: next_brief regardless of the shocked_meter_avg. A blocking finding from one panel is not outweighed by three panels rating the artifact 9/10.
  • Single-writer interlock. Only the orchestrator writes to the PR: exactly one add-comment call and one remove-labels call. The remove-labels call sweeps spec-review (trigger idempotency). NO add-labels call -- there are no verdict labels. Panelist subagents and the synthesizer subagent return JSON only and MUST NOT call any gh write command, post comments, apply labels, or touch PR state.
  • Single-emission discipline. Exactly one comment per panel run, rendered from assets/comment-template.md after all subagents return and the linter checklist runs.
  • ASCII-only artifact. Every byte the skill writes (the comment, the synthesizer prose, any rendered fold instruction) MUST be within printable ASCII (U+0020 - U+007E). The skill inherits the repo encoding rule from .github/instructions/encoding.instructions.md (if present) and additionally enforces it on the spec artifact via linter check 1.
  • No-vendor-foundation language ban. The spec artifact MUST NOT contain "CNCF", "Linux Foundation", "Sandbox", "Incubation", "W3C Process", or "IETF RFC stream". The persona prompts MAY reference these as pedigree (a panelist's credibility comes from having edited OpenAPI; that does not put OpenAPI's foundation affiliation in the spec text). Linter check 2 greps the artifact for the forbidden token list AFTER any fold.

Read the full file on GitHub · 395 lines

Files

What ships with it

4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 7d ago First seen · 395 lines · 215 tokens per session scan A 5e2b98792b45

Subscribe to this mod's changes

apm-spec-guardian is a skill published in the GitHub repository microsoft/apm (3,735 stars, last pushed today), licensed MIT. It adds 215 tokens to every session and 4,815 once invoked, about $0.0011 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 2026-08-30.

Related

Other skills, from other repositories

reality-checker

Evidence-based readiness assessor — defaults to NEEDS WORK, refuses fantasy A+ ratings, demands overwhelming proof before declaring anything production-ready.

RaNDoM6913/claude-code-superkit · 30 tokens

vibeflow-audit

Audits implementation against its DoD and project patterns. Runs the test suite, compares code against the spec, and reports PASS / PARTIAL / FAIL. Also runs the Critical Gate — a safety scan of the diff for destructive or dangerous operations. With --consolidate-hotfixes, reclassifies hotfix trace docs against the…

pe-menezes/vibeflow · 86 tokens

discount-review

Inspect the discount policy fixture with a repeatable review checklist and helper script.

promptfoo/promptfoo · 18 tokens

code-review

Reviews code for bugs, security issues, and best practices.

promptfoo/promptfoo · 11 tokens

mcp-server-review

Review a Model Context Protocol (MCP) server implementation against the 2026-07-28 protocol revision, which removed the initialize handshake and Mcp-Session-Id and made the protocol stateless. Use when the user asks to review, audit, upgrade or migrate an MCP server, asks whether their MCP server is spec compliant…

pnp/copilot-prompts · 93 tokens

code-review-csharp

Perform structured code reviews of C# source code covering naming conventions, performance, security, readability, and .NET best practices. Trigger phrases include "review this C# code", "check my C# for best practices", "analyze this C# class", "find issues in my C# code".

pnp/copilot-prompts · 66 tokens