A command for updating documentation after an implementation has passed review. It uses the actual task changes to decide which documentation needs updating and checks that the files belong to the task.

Use it after a successful task review to bring project documentation in line with the completed code.

It prevents documentation from being updated for unreviewed or failed code and limits edits to what the implementation actually changed. A PASS review means the recorded review found no blocking issues.

How bredmond1019/claude-sdk-rs configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to bredmond1019/claude-sdk-rs. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/bredmond1019/claude-sdk-rs/main/.claude/commands/document.md

Clone the repo

git clone --depth 1 https://github.com/bredmond1019/claude-sdk-rs

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/commands/bredmond1019/claude-sdk-rs/document/github.svg)](https://agentmods.dev/commands/bredmond1019/claude-sdk-rs/document)

Your own site

<a href="https://agentmods.dev/commands/bredmond1019/claude-sdk-rs/document"><img src="https://agentmods.dev/badge/commands/bredmond1019/claude-sdk-rs/document/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/commands/bredmond1019/claude-sdk-rs/document"><img src="https://agentmods.dev/badge/commands/bredmond1019/claude-sdk-rs/document.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,479 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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 5.1	$0.00000	$0.01479
Opus 5.5	$0.00000	$0.00592
Sonnet 5.5	$0.00000	$0.00296
Haiku 4.5	$0.00000	$0.00148

Measured 11d ago against content hash ea9e4d419b52, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

document 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 11d 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/document.md · 109 lines

How it starts

The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Document — Update docs to reflect a completed, reviewed implementation.

Gates on the review verdict being PASS. Scopes doc updates surgically from the real diff, scoped to this task's branch/commit, cross-checked against the recorded file list.

Variables

$ARGUMENTS — path to the task spec with optional task number. Same format as /implement.

Examples:

planning/<spec-slug>/tasks.md — document all tasks in the spec
planning/<spec-slug>/tasks.md 3 — document task 3 only

Instructions

If $ARGUMENTS is not provided, stop:

"Usage: /document planning//tasks.md [N]"
Parse $ARGUMENTS: split on the last space. Trailing number = task N; remainder = spec path.
Run /prime to orient to the codebase before reading any files.
Derive the spec dir: planning/<spec-slug>/tasks.md → planning/<spec-slug>/sdlc/.
Read sdlc/state.json's top-level review.verdict (spec-wide) or tasks["<N>"].status (task-scoped). If the verdict is not PASS, STOP immediately:

"Cannot document: review verdict is [FAIL/PARTIAL]. Resolve all blocking issues and re-run /review-task [args] until the verdict is PASS." If no state file / no review recorded, STOP with the same message, naming the missing state.
Derive the changed-file list from the real diff, scoped to this task's branch/commit — not the whole working tree, which may hold unrelated concurrent-session noise in a shared index. Run git diff --name-only <base>...HEAD (or, for an uncommitted worktree, git diff --name-only HEAD) against the branch or commit this implement/review pass produced, not a bare git status over the shared index. This diff is the authoritative list of changed source files.

Then read sdlc/state.json's tasks["<N>"].files_changed as a cross-check. If the two disagree — a file the state entry claims but the diff doesn't show, or vice versa — treat the mismatch itself as a finding: note it in the worklog entry's Docs Checked line rather than silently trusting either side, and prefer the diff's list for scoping the doc-update work in step 8.

Read the full file on GitHub · 109 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.

11d ago First seen · 109 lines · 0 tokens per session scan A ea9e4d419b52

Subscribe to this mod's changes

document is a command published in the GitHub repository bredmond1019/claude-sdk-rs (23 stars, last pushed 1mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,479 tokens. 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 2026-10-26.

Project management Writing and docs

document next to 6 commands from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
documentbredmond1019/claude-sdk-rs	Command	23	1mo ago	Apache-2.0	A	0	Claude Code
checklistgithub/spec-kit	Command	148k	yesterday	MIT	A	13	Claude Code
clarifygithub/spec-kit	Command	148k	yesterday	MIT	A	27	Claude Code
specifygithub/spec-kit	Command	148k	yesterday	MIT	A	13	Claude Code
analyzegithub/spec-kit	Command	148k	yesterday	MIT	A	26	Claude Code
convergegithub/spec-kit	Command	148k	yesterday	MIT	A	35	Claude Code
implementgithub/spec-kit	Command	148k	yesterday	MIT	A	14	Claude Code

claude-sdk-rs: Command for Claude Code