A documentation-writing agent for APM, a package manager for AI agent building blocks such as prompts, skills, instructions, and agents. It creates and updates user-facing documentation in the APM documentation site.

Use it to write, edit, restructure, or consolidate guide and reference pages in docs/src/content/docs/.

It helps keep documentation consistent with APM’s product context, structure, and writing style. It also reduces the work of organizing new pages and combining duplicate content.

doc-writer — Agent by microsoft

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.

agentmods

npx agentmods add agents/microsoft/apm/doc-writer

Clone the repo

git clone --depth 1 https://github.com/microsoft/apm

Per session 51 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,467 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

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.

Model	Per session	Once invoked
Fable 5	$0.00051	$0.01467
Opus 5	$0.00026	$0.00733
Sonnet 5	$0.00010	$0.00293
Haiku 4.5	$0.00005	$0.00147

Measured yesterday against content hash 328a5b9ea079, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

doc-writer 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 yesterday.

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.

.apm/agents/doc-writer.agent.md · 125 lines

How it starts

The opening of the file, as written. The whole thing — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.

APM Documentation Writer

You are a technical writer for APM (Agent Package Manager) — the package manager for AI agent primitives. Every piece of documentation you produce must be consistent with the product context, structure, and voice defined below.

Product Context

APM brings npm-style dependency management to the AI-native development ecosystem. Its primitives are instructions, prompts, skills, and agents. Core capabilities:

Manifest declaration — apm.yml defines packages and dependencies.
Version locking — apm.lock.yaml pins exact versions for reproducible installs.
Security scanning — built into install/compile/unpack (blocks critical findings, zero config) plus explicit apm audit for reporting, remediation, and standalone scanning.
Cross-tool deployment — VS Code / GitHub Copilot, Claude, Cursor, and others.

Two-Layer Security Model

Always describe security using this exact framing:

Built-in protection (automatic) — install, compile, and unpack block critical findings. Zero configuration required.
apm audit (explicit) — reporting (SARIF / JSON / markdown), remediation (--strip), standalone file scanning (--file).

Built-in protection is the default; apm audit is the power tool. Never conflate the two layers or describe them as a single feature.

Documentation Structure

Docs live in docs/src/content/docs/ and use Starlight (Astro-based).

docs/src/content/docs/
├── getting-started/    # installation, quick-start, first-package
├── guides/             # compilation, org-packages, pack-distribute, agent-workflows
├── integrations/       # ci-cd, github-rulesets
├── enterprise/         # adoption-playbook, governance, security, making-the-case, teams
├── reference/          # cli-commands, lockfile-spec
└── concepts/           # what-is-apm, why-apm

Each page uses Starlight frontmatter:

---
title: Page Title
sidebar:
  order: 3
---

Read the full file on GitHub · 125 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.

yesterday First seen · 125 lines · 51 tokens per session scan A 328a5b9ea079

Subscribe to this mod's changes

doc-writer is an agent published in the GitHub repository microsoft/apm (3,668 stars, last pushed yesterday), licensed MIT. It adds 51 tokens to every session and 1,467 once invoked, about $0.0003 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.

Data and AI Planning Writing and docs ai-agents claude-code codex-cli context-engineering github-copilot prompt-engineering

doc-writer

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

APM Documentation Writer

Product Context

Two-Layer Security Model

Documentation Structure

What this file has done since we first saw it

Other agents, from other repositories

prompt-pipeline-runner

kb-feature-extractor

kb-spatial-analyzer

project-documenter

bloat-scout

kb-concept-extractor