A documentation review workflow that compares the current code changes with the project documentation and identifies pages that may need updates. It covers architecture, development rules, database, API, and feature documentation.

Use it during a change or pull request to inspect the diff, decide which documentation applies, update relevant files, and check code comments and documentation quality.

It helps keep written instructions aligned with code changes, so future contributors are less likely to follow outdated guidance.

update-docs — Command by bybren-llc

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 commands/bybren-llc/safe-agentic-workflow/update-docs

Clone the repo

git clone --depth 1 https://github.com/bybren-llc/safe-agentic-workflow

Made for: Claude Code.

Per session 8 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 550 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	$0.00008	$0.00550
Opus 5	$0.00004	$0.00275
Sonnet 5	$0.00002	$0.00110
Haiku 4.5	$0.00001	$0.00055

Measured 3d ago against content hash 1571cd967357, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

update-docs 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 3d 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.

.claude/commands/update-docs.md · 91 lines

How it starts

The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Review current work and identify documentation that needs updating per @CONTRIBUTING.md requirement: "always update docs related to the work we are doing within the PR".

Documentation Assessment

1. Identify Changes

Analyze git diff to understand scope:

git diff origin/dev --name-only

Categorize changes:

Architecture/workflow changes
New features or APIs
Process modifications
Configuration changes
Database schema changes

2. Required Documentation Updates

Based on changes, check if these need updates:

High-Level Docs (ALWAYS update in same PR)

CLAUDE.md: Architecture, commands, setup
- Check if: New commands, workflow changes, tech stack updates
CONTRIBUTING.md: Development process, workflows
- Check if: Process changes, new requirements, workflow modifications

Specialized Docs

Database: docs/database/ (schema, RLS, migrations)
- Check if: Schema changes, new tables, RLS patterns
API Docs: docs/api/ (endpoints, webhooks)
- Check if: New routes, API changes, webhook modifications
Feature Docs: docs/ (feature-specific)
- Check if: New features, major functionality changes

Code Documentation

Inline comments: Complex logic
README: Feature directories
ADRs: docs/adr/ (architectural decisions)
- Check if: Significant architecture decisions made

3. Documentation Checklist

For each doc identified:

Content accuracy verified
Examples updated
Commands/code samples tested
Links validated
Markdown linting passed

4. Execute Updates

For each doc needing updates:

Read current version
Identify outdated sections
Update with current information
Run yarn lint:md:fix
Add to current commit

Workflow

Assess changes made in current branch
Identify all affected documentation
Present list to user for confirmation
Execute updates for confirmed docs
Verify markdown linting passes
Report completion status

Read the full file on GitHub · 91 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.

3d ago First seen · 91 lines · 8 tokens per session scan A 1571cd967357

Subscribe to this mod's changes

update-docs is a command published in the GitHub repository bybren-llc/safe-agentic-workflow (404 stars, last pushed 1mo ago), licensed MIT. It adds 8 tokens to every session and 550 once invoked, about $0.0000 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.

Writing and docs agile-methodology ai-agents ai-assisted-development claude-code developer-tools methodology

update-docs

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Documentation Assessment

1. Identify Changes

2. Required Documentation Updates

High-Level Docs (ALWAYS update in same PR)

Specialized Docs

Code Documentation

3. Documentation Checklist

4. Execute Updates

Workflow

What this file has done since we first saw it

Other commands, from other repositories

mass-line

review

adv-gemini-research

review-code

django-model

constitution