docs

A command workflow for updating project documentation, such as the README, changelog, and architecture notes.

In plain words
What is it for?
Recording changed installation steps, usage, configuration, dependencies, features, fixes, and system structure.
Why use it?
It helps keep documentation aligned with code changes and waits for approval before creating commits.

Command for Claude Code

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/qwickapps/ai-sdlc-workflows/docs
Clone the repo
git clone --depth 1 https://github.com/qwickapps/ai-sdlc-workflows

Made for: Claude Code.

Per session 3 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 520 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 $0.00003 $0.00520
Opus 5 $0.00002 $0.00260
Sonnet 5 $0.00001 $0.00104
Haiku 4.5 $0.00000 $0.00052

Measured yesterday against content hash 17b29ad38f17, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 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.

claude/.claude/commands/docs.md · 134 lines

What it actually says

Documentation Update Workflow

You are now in Documentation Mode. Use this when updating documentation only.

Input: $ARGUMENTS (what changed or needs documentation)

CRITICAL RULES

  1. Accurate and current - docs must reflect actual code state
  2. NEVER auto-commit - wait for user approval
  3. No attributions in commits

Interactive Setup

Check if $ARGUMENTS is provided.

If $ARGUMENTS is empty, ask:

"What documentation needs updating? Please describe:

  • What code or feature changed
  • Which docs might be affected
  • Any specific sections to update"

Wait for response before proceeding.

Documentation Checklist

README.md

Update when:

  • Installation steps changed
  • Usage examples changed
  • Configuration options changed
  • Dependencies changed

CHANGELOG.md

Update when:

  • New feature added
  • Bug fixed
  • Breaking change made
  • Any releasable change

Format:

## [Unreleased]

### Added

- {new feature}

### Changed

- {changed behavior}

### Fixed

- {bug fix}

### Removed

- {removed feature}

ARCHITECTURE.md

Update when:

  • System structure changed
  • New components added
  • Data flow changed
  • Integration points changed

Code Comments

Add/update when:

  • Complex logic needs explanation
  • Non-obvious decisions made
  • API contracts defined

Process

Step 1: Identify What Needs Updating

  1. What code changed?
  2. What docs reference that code?
  3. Are any docs now outdated?

Step 2: Make Updates

  1. Update each affected doc
  2. Keep changes minimal and focused
  3. Maintain existing style/format

Step 3: Review

Present changes to user:

## Documentation Updates

### Files Changed

- {file}: {what changed}

### Summary

{brief description}

Step 4: Commit (after approval)

docs(<scope>): update documentation

- {what was updated}
- {why}

Abort

User can say "abort" or "cancel" at any time.

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 · 134 lines · 3 tokens per session scan A 17b29ad38f17

Subscribe to this mod's changes

docs is a command published in the GitHub repository qwickapps/ai-sdlc-workflows (2 stars, last pushed 5mo ago), licensed MIT. It adds 3 tokens to every session and 520 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 2026-08-31.