A command that checks completed work against its task specification and acceptance criteria, the conditions that define success. It can review all tasks in a specification or one numbered task.

Use it with a task-specification path, optionally followed by a task number. It reviews the source, recorded state, work log, and relevant changes.

It helps reveal missing requirements or validation before work is considered complete. It also reads prior task history and project orientation for context.

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/review-task.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/review-task/github.svg)](https://agentmods.dev/commands/bredmond1019/claude-sdk-rs/review-task)

Your own site

<a href="https://agentmods.dev/commands/bredmond1019/claude-sdk-rs/review-task"><img src="https://agentmods.dev/badge/commands/bredmond1019/claude-sdk-rs/review-task/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/review-task"><img src="https://agentmods.dev/badge/commands/bredmond1019/claude-sdk-rs/review-task.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 1,469 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	$0.01469
Opus 5.5	$0.00000	$0.00588
Sonnet 5.5	$0.00000	$0.00294
Haiku 4.5	$0.00000	$0.00147

Measured 11d ago against content hash 44304aa57932, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

review-task 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/review-task.md · 96 lines

How it starts

The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Review Task — Verify a completed task against its spec and acceptance criteria.

Variables

$ARGUMENTS — path to the task spec, with an optional task number suffix (same format as /implement).

Examples:

planning/phase0-blockC/tasks.md — review all tasks in the spec
planning/phase0-blockC/tasks.md 1 — review only Task 1
planning/phase0-blockC/tasks.md 3 — review only Task 3

Instructions

If $ARGUMENTS is not provided, stop and ask the user for the task spec path.
Parse $ARGUMENTS: split on the last space. If the trailing token is a number, treat it as the task number to review; the remainder is the task spec path.
Run /prime to orient to the codebase before reading any files.
Derive the spec dir: planning/phase0-blockC/tasks.md → planning/phase0-blockC/sdlc/.
Read the task spec in full.
Read prior step history as context, from sdlc/state.json and sdlc/worklog.md: a. Read sdlc/state.json's tasks["<N>"] entry, if present — summary, files_changed, validated. If absent, note it and continue from source alone. b. Read sdlc/worklog.md's ## Task <N> — TEST ... section(s), if present, for the historical test result. Do NOT treat it as authoritative — a fresh test run is required in step 8. If absent, note that /test was not run before this review; the fresh run below covers it.
Read every file listed in tasks["<N>"].files_changed (or, if absent, read the files most likely touched by the task based on the spec). Verify the actual content — do not trust the recorded summary alone.
Run a fresh test suite as the authoritative verification. Do NOT rely on the historical test worklog entry — run the commands now and capture the results.
- Task-scoped: run the spec's Validation Commands section exactly as written.
- Full block: run the spec's complete Validation Commands block. If none exist, run the project's checks from planning/harness.json (validation.checks[]); if that is absent too, stop and ask the user for the validation commands. The checks marked gates: true in planning/harness.json are authoritative for the verdict (a typical project gates its test suite and build). Also enforce any project-specific gate written in CLAUDE.md. A failing gated check always prevents PASS, even if all acceptance criteria appear MET from reading the code.
Check every Acceptance Criterion in the spec against the actual code and fresh test output:
- For each criterion: state whether it is MET, PARTIAL, or NOT MET, and cite the evidence (file + line, test name, command output).
- A criterion is MET only when you can point to code or test output that directly satisfies it.
- Do not mark anything MET based solely on the recorded summary — verify in source.
Record the verdict (see Record) and summarize to the user.

Read the full file on GitHub · 96 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 · 96 lines · 0 tokens per session scan A 44304aa57932

Subscribe to this mod's changes

review-task 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 1,469 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.

Code review Project management

review-task next to 6 commands from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
review-taskbredmond1019/claude-sdk-rs	Command	23	1mo ago	Apache-2.0	A	0	Claude Code
diff-reviewcoco-research/coco	Command	785	yesterday	Apache-2.0	A	11	Claude Code
review-branchdamusix/atomic-claude	Command	115	4d ago	MIT	A	35	Claude Code
refactorRchGrav/claudebox	Command	1.2k	1mo ago	MIT	A	9	Claude Code
spec-trace-requirementsrjmurillo/ai-agents	Command	49	yesterday	MIT	A	0	GitHub Copilot
merge-conflict-analysisrjmurillo/ai-agents	Command	49	yesterday	MIT	A	0	GitHub Copilot
initazrtydxb/procoder	Command	211	11d ago	Apache-2.0	A	16	Claude Code

claude-sdk-rs: Command for Claude Code