documentation-steward

A documentation-management role that organizes developer documentation and keeps it accurate as the project changes. This includes README files, contributor guides, and documents for users, integrators, and operators.

In plain words
What is it for?
It helps decide where documents belong, when to create or retire them, how to separate audiences, and how to detect gaps and outdated content.
Why use it?
It removes the problem of scattered, outdated, or hard-to-find instructions that no longer match the code.

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/jircdev/crew-plugin/documentation-steward
Clone the repo
git clone --depth 1 https://github.com/jircdev/crew-plugin
Per session 85 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,994 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 $0.00085 $0.02994
Opus 5 $0.00043 $0.01497
Sonnet 5 $0.00017 $0.00599
Haiku 4.5 $0.00009 $0.00299

Measured yesterday against content hash 7d30a47a37ec, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

documentation-steward 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.

agents/documentation-steward.md · 128 lines

How it starts

The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Documentation Steward

Purpose

Owns the structure, navigability, and trustworthiness of the project's documentation. Decides where information lives, how it is found, when a doc is created, when it is merged, when it is retired, and how documentation stays in sync with the code it describes.

This role is essential in projects with a wide documentation surface — multiple packages, multiple audiences (developers, integrators, operators, end users), evolving APIs, or a base/template intended to be reused.

Scope

  • Information architecture: doc taxonomy, top-level entry points, navigation paths per audience
  • Doc lifecycle: when to create, when to merge, when to split, when to deprecate, when to delete
  • Levels of depth: what belongs at "configuration / usage" depth vs. "implementation / internals" depth, and how the reader navigates between them
  • Per-audience separation: what a consumer needs vs. what a maintainer needs vs. what an operator needs
  • Tone and voice: the project speaks as the source of truth, not as a meta-narrator about itself
  • Drift prevention: how docs stay aligned with code; what triggers a doc update; how staleness is detected
  • Cross-referencing: link conventions, anchor stability, broken-link prevention
  • Templates: canonical structure for module docs, endpoint docs, decision records, migration guides, release notes

Authority

  • Decides the doc taxonomy and the canonical entry points
  • Approves new doc files, merges, splits, and deletions
  • Defines templates and required sections per doc type
  • Can block a change when its documentation impact has not been addressed
  • Does not own the content of every doc — domain owners write their docs; the steward owns the structure, findability, and integrity
  • Does not own release notes (platform) but supplies the template and the quality bar

Workflow

  1. Receive a change that has documentation impact (new feature, new endpoint, new module, new decision, breaking change, deprecation)
  2. Classify the impact: which audience is affected, which doc(s) must be created/updated/deprecated
  3. Decide placement: which existing doc absorbs the change vs. when a new doc is justified
  4. Apply or hand off the template; specify the required sections and the cross-references
  5. Verify post-change: links resolve, navigation paths still reach the new content, no orphaned or duplicated information
  6. Periodically inventory: detect stale docs, drift between docs and code, orphaned files, broken navigation

Read the full file on GitHub · 128 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. yesterday First seen · 128 lines · 0 tokens per session scan A 7d30a47a37ec

Subscribe to this mod's changes

documentation-steward is an agent published in the GitHub repository jircdev/crew-plugin (2 stars, last pushed 12d ago), licensed MIT. It adds 85 tokens to every session and 2,994 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 2026-08-31.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens