TaskSentinel: Command for Claude Code

.claude/commands/BMad/tasks/review-story.md

review-story is a command for Claude Code from gonewx/TaskSentinel. It costs 0 tokens per session (1,146 once invoked), scanned A, original, MIT.

A workflow for reviewing a completed development story and its code changes. It checks the story requirements, developer notes, file list, architectural guidance, security points, and automated test status.

In plain words
What is it for?
For reviewing stories marked ready for review, checking acceptance criteria, and comparing the implementation with the documented design. It also verifies that listed files exist and that required tests have passed.
Why use it?
It provides a structured check before work is accepted, helping reveal missing requirements or implementation differences. It can also improve the code directly during the review.

Command for Claude Code

Written for Claude Code: installed under .claude/.

This is gonewx/TaskSentinel's own configuration. It tells Claude Code how to work on TaskSentinel itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything TaskSentinel configures →

Reuse

Borrowing it

Nothing to install: this file belongs to gonewx/TaskSentinel. 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/gonewx/TaskSentinel/main/.claude/commands/BMad/tasks/review-story.md
Clone the repo
git clone --depth 1 https://github.com/gonewx/TaskSentinel

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.

agentmods badge for review-story

README.md
[![agentmods](https://agentmods.dev/badge/commands/gonewx/tasksentinel/review-story.svg)](https://agentmods.dev/commands/gonewx/tasksentinel/review-story)
Your own site
<a href="https://agentmods.dev/commands/gonewx/tasksentinel/review-story"><img src="https://agentmods.dev/badge/commands/gonewx/tasksentinel/review-story.svg" alt="Measured on agentmods" 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 1,146 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.01146
Opus 5 $0.00000 $0.00573
Sonnet 5 $0.00000 $0.00229
Haiku 4.5 $0.00000 $0.00115

Measured 8d ago against content hash c7baf0d033ae, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

review-story 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 8d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

.claude/commands/BMad/tasks/review-story.md · 159 lines

How it starts

The opening of the file, as written. The whole thing — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/review-story Task

When this command is used, execute the following task:

review-story

When a developer agent marks a story as "Ready for Review", perform a comprehensive senior developer code review with the ability to refactor and improve code directly.

Prerequisites

  • Story status must be "Review"
  • Developer has completed all tasks and updated the File List
  • All automated tests are passing

Review Process

  1. Read the Complete Story

    • Review all acceptance criteria
    • Understand the dev notes and requirements
    • Note any completion notes from the developer
  2. Verify Implementation Against Dev Notes Guidance

    • Review the "Dev Notes" section for specific technical guidance provided to the developer
    • Verify the developer's implementation follows the architectural patterns specified in Dev Notes
    • Check that file locations match the project structure guidance in Dev Notes
    • Confirm any specified libraries, frameworks, or technical approaches were used correctly
    • Validate that security considerations mentioned in Dev Notes were implemented
  3. Focus on the File List

    • Verify all files listed were actually created/modified
    • Check for any missing files that should have been updated
    • Ensure file locations align with the project structure guidance from Dev Notes
  4. Senior Developer Code Review

    • Review code with the eye of a senior developer
    • If changes form a cohesive whole, review them together
    • If changes are independent, review incrementally file by file
    • Focus on:
      • Code architecture and design patterns
      • Refactoring opportunities
      • Code duplication or inefficiencies
      • Performance optimizations
      • Security concerns
      • Best practices and patterns
  5. Active Refactoring

    • As a senior developer, you CAN and SHOULD refactor code where improvements are needed
    • When refactoring:
      • Make the changes directly in the files
      • Explain WHY you're making the change
      • Describe HOW the change improves the code
      • Ensure all tests still pass after refactoring
      • Update the File List if you modify additional files

Read the full file on GitHub · 159 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. 8d ago First seen · 159 lines · 0 tokens per session scan A c7baf0d033ae

Subscribe to this mod's changes

review-story is a command published in the GitHub repository gonewx/TaskSentinel (18 stars, last pushed 1y ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,146 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 2026-08-30.