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.
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.
curl -O https://raw.githubusercontent.com/microsoft/apm/main/.agents/skills/docs-sync/SKILL.mdgit clone --depth 1 https://github.com/microsoft/apmWrote 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/microsoft/apm/docs-sync)<a href="https://agentmods.dev/skills/microsoft/apm/docs-sync"><img src="https://agentmods.dev/badge/skills/microsoft/apm/docs-sync/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/microsoft/apm/docs-sync"><img src="https://agentmods.dev/badge/skills/microsoft/apm/docs-sync.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 4 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Rogue Agent · line 128 Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
- medium Agent Snooping · line 47 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 48 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 49 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00150 | $0.02969 |
| Opus 5.5 | $0.00060 | $0.01188 |
| Sonnet 5.5 | $0.00030 | $0.00594 |
| Haiku 4.5 | $0.00015 | $0.00297 |
Grade A, and why
docs-sync 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 1mo 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 — 262 lines — stays where its author put it; the contents beside it link to each section on GitHub.
docs-sync -- per-PR documentation impact panel
The docs corpus drifts silently and constantly. This skill catches drift at PR-open time, classifies its impact, and orchestrates a persona panel to produce a patch-ready advisory comment.
The pattern is A1 PANEL + B1 FAN-OUT/SYNTHESIZER + A8 ALIGNMENT LOOP. The classifier is the cost gate (~70% of PRs short-circuit to no-change with ~1 LLM call). When the panel does fan out, every agent reads a bounded context (~10 KB) -- never the full corpus.
This skill is ADVISORY. It does not gate merge, apply verdict labels, or push to the contributor's fork. The orchestrator is the sole writer to the PR: exactly one comment per run (idempotent edit-in-place), plus optional label sweeps.
Architecture invariants
- Cost ceiling: 15 LLM calls per run. Hard-wired. The orchestrator refuses to spawn beyond. Header prints
N/15for observability. - Single-writer interlock. Only the orchestrator writes. Panelist subagents return JSON; they MUST NOT call any
ghwrite command, post comments, or touch PR state. - Idempotent comment. Exactly one comment per run, with a stable header
## Docs sync advisory. Re-runs edit-in-place usinggh pr comment --edit-last. - No fork-write. Companion docs PRs require Step 7's fresh responsible-human issue-scope checkpoint and open in the BASE repo; never pushed to the contributor's fork. Labels request advice, not implementation.
- Index-not-corpus reads. Every classifier and architect agent reads
.apm/docs-index.yml, NOT the corpus itself. The corpus is sampled only by the localizer (which reads the specific candidate pages) and by per-page panelists (which read one page each). - S7 deterministic tool bridge. The python-architect panelist MUST run real
apm --help,grep, andpython -ccommands to verify doc claims, never assert from prose.
Roster
| Role | Agent | Always active? |
|---|---|---|
| Classifier | doc-analyser inside docs-impact-classifier | Yes (every run) |
| Localizer | docs-impact-localizer | Only on in_place verdict |
| Architect | docs-impact-architect | Only on structural verdict |
| Writer | doc-writer | Per candidate page (fan-out) |
| Verifier | python-architect | Per candidate page (fan-out, S7) |
| Editorial | editorial-owner | Once across all redrafts |
| Growth | oss-growth-hacker | Once across all redrafts |
| Synthesizer | cdo | Once, with ALIGNMENT LOOP up to 3 redrafts |
What ships with it
6 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.
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.
- 1mo ago Changed · +23 lines 8587900dd05f
- 1mo ago First seen · 239 lines · 150 tokens per session scan A 2214d7ce6770
docs-sync is a skill published in the GitHub repository microsoft/apm (4,133 stars, last pushed yesterday), licensed MIT. It adds 150 tokens to every session and 2,969 once invoked, about $0.0006 per session on Opus 5.5. 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.
Other skills, from other repositories
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".
git-branch-cleanup
Analyzes and safely cleans up local Git branches. Categorizes branches by merge status, staleness, and remote tracking. Provides interactive selection with safety guards. Use when the user wants to clean up branches, delete old branches, organize Git branches, or asks about which branches can be safely deleted.
self-awareness-review
Reviews a given week of your OWN Teams meetings, chats, and sent emails to surface moments where you may have misread social signals or come across as passive-aggressive, curt, sarcastic, or dismissive — returning the exact quote, how it likely landed, and a kinder rewrite. Private self-reflection coaching for the…
audit
Audits recent work against its Definition of Done and project patterns, from a review package of the diff. Runs the test suite, compares code against the spec, tests scenarios, sabotages risk code, and reports PASS / PARTIAL / FAIL with a severity and a cause on every finding. Also runs the Critical Gate — a safety…
markdown-preview
Generate browser-viewable HTML previews from markdown, plain text, and Mermaid diagrams. Auto-validates, styles, and opens in browser.
pr-review
Intent-aware map-reduce PR review with CI/CD support, confidence gating, and intelligent comment deduplication.