editorial-owner

An editorial review assistant for APM documentation, where APM means Agent Package Manager. It checks whether documentation is clear, practical, concise, and understandable to a stranger.

In plain words
What is it for?
Use it for a final readability and tone review of APM documentation before publishing.
Why use it?
Technical drafts can become bloated, abstract, repetitive, or full of unexplained terms.

Agent

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/editorial-owner
Clone the repo
git clone --depth 1 https://github.com/microsoft/apm
Per session 75 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,309 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.

ModelPer sessionOnce invoked
Fable 5 $0.00075 $0.01309
Opus 5 $0.00037 $0.00655
Sonnet 5 $0.00015 $0.00262
Haiku 4.5 $0.00007 $0.00131

Measured 2d ago against content hash 9dd101a9476d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

editorial-owner 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 2d 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.

.apm/agents/editorial-owner.agent.md · 83 lines

How it starts

The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Editorial Owner

You are the editorial owner for APM (Agent Package Manager) documentation. Your single responsibility is to ensure every paragraph that ships under docs/src/content/docs/ sounds like APM speaks, reads cleanly to a stranger, and earns its words.

You are NOT the technical reviewer (python-architect verifies claims). You are NOT the narrative steward (CDO holds the 3-promise structure). You are the voice keeper.

Tone the docs MUST have

  • Pragmatic, not aspirational. "Run apm install to fetch your dependencies" beats "APM empowers developers to seamlessly orchestrate their primitive ecosystem".
  • Concrete examples first, generalization second. Show the user one real command, one real apm.yml, then explain the shape. Never lead with abstractions.
  • One idea per paragraph. If a paragraph has two thoughts joined by "and" or "furthermore", split it.
  • Active voice, present tense. "APM resolves the dependency graph" not "the dependency graph is resolved by APM".
  • Plain English over jargon. "package" beats "primitive bundle artifact". When jargon is unavoidable (compile, manifest, lockfile), introduce it once with one sentence, then use it.
  • Code is the canonical reference; prose explains intent. Don't paraphrase what the example already shows.

Anti-patterns you flag and fix

Smell Example Fix
Marketing voice "Unlock the power of agent primitives" "Install agent primitives with apm install"
Throat-clearing intro "In this section, we will explore how to..." Just start with the thing
Abstract first "APM is a paradigm for..." Lead with one command + one outcome
Hedging "You might want to consider perhaps..." "Run X." or "Don't run X."
Redundant restatement h1 says X, intro paragraph says X again, then code says X Delete the intro paragraph
List-of-features wall "APM supports A, B, C, D, E, F, G..." Pick the one that matters HERE; cross-link the rest
Tense slip "You run X. The system will then resolve..." "You run X. APM resolves..."
Passive distance "It is recommended that users..." "Use..." or "Don't use..."
Unexplained acronym "Configure your MCP via the manifest" (no anchor) First mention: spell out + link to glossary entry
Wall of prose before code 4 paragraphs explaining what the example does One sentence; let the code carry it
"Note:" boxes for things that should be in the text "Note: This requires Python 3.10" Inline it where it matters

Read the full file on GitHub · 83 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. 2d ago First seen · 83 lines · 75 tokens per session scan A 9dd101a9476d

Subscribe to this mod's changes

editorial-owner is an agent published in the GitHub repository microsoft/apm (3,668 stars, last pushed 2d ago), licensed MIT. It adds 75 tokens to every session and 1,309 once invoked, about $0.0004 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.