Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add choucrifahed/agent-plugins/plugin install bmad-githubWrote 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.
[](https://agentmods.dev/skills/choucrifahed/agent-plugins/bmad-github-story-review)<a href="https://agentmods.dev/skills/choucrifahed/agent-plugins/bmad-github-story-review"><img src="https://agentmods.dev/badge/skills/choucrifahed/agent-plugins/bmad-github-story-review/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.
<a href="https://agentmods.dev/skills/choucrifahed/agent-plugins/bmad-github-story-review"><img src="https://agentmods.dev/badge/skills/choucrifahed/agent-plugins/bmad-github-story-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00075 | $0.01136 |
| Opus 5 | $0.00037 | $0.00568 |
| Sonnet 5 | $0.00015 | $0.00227 |
| Haiku 4.5 | $0.00007 | $0.00114 |
Grade A, and why
bmad-github-story-review 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 9d 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.
How it starts
The opening of the file, as written. The whole thing — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Story Review: BMAD Code Review + Push (NO "done")
You are performing an adversarial code review on a story. This skill runs the BMAD code-review operation but overrides the final status transition: the story stays at review, NOT done.
The "done" transition only happens via Story Sync (SS) after the user merges the PR on GitHub. The user is the sole reviewer and merger of PRs — this is the quality gate.
IMPORTANT: This skill MUST be run from the story's worktree directory (created by Story Dev), NOT from the main repo.
Pre-flight Checks
-
Detect the story context from the current worktree:
git branch --show-currentThe branch name should be
story/<story_key>. Extract the story key and story ID from the branch name.If the branch doesn't match the
story/pattern, STOP and tell the user this skill must be run from a story worktree. -
Find the story file in
<output_folder>/implementation-artifacts/matching the story key. -
Verify a PR exists for this branch:
gh pr view --json number,url,stateIf no PR exists, tell the user to run Story Dev (SD) first.
Phase 1: Run BMAD code-review
Read and follow ${CLAUDE_PLUGIN_ROOT}/references/bmad-workflow-loader.md with <operation> = code-review.
CRITICAL OVERRIDE: Do NOT Set Status to "done"
When the BMAD code-review operation reaches its final step where it would normally set the story status to done:
DO NOT change the story status to done. Keep it at review.
The reason: The "done" transition is controlled by the GitHub PR merge flow:
- User reviews the PR on GitHub
- User merges the PR (which auto-closes the GitHub issue via
Closes #N) - User runs Story Sync (SS) which detects the closed issue and marks BMAD as done
This ensures the user is the quality gate — no story is marked done without human review and approval.
Phase 2: Git Automation
If Code Changes Were Made (Fixes Applied)
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.
- 9d ago First seen · 148 lines · 75 tokens per session scan A 075d24bc8d8a
bmad-github-story-review is a skill published in the GitHub repository choucrifahed/agent-plugins (7 stars, last pushed 1mo ago), licensed MIT. It adds 75 tokens to every session and 1,136 once invoked, about $0.0004 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.
Other skills, from other repositories
tech-lead/technical-standards
A set of coding rules and best practices for naming, organising, testing, and handling errors in software.
tech-lead/code-review
A checklist-based method for examining code for correctness, security, performance, clarity, and ease of maintenance.
bmad-review
Runs one or more installed review lenses — adversarial critique, edge cases, verification gaps, structure, prose — and reports triaged findings. Use when, and only when, the user asks you to review a diff, a pull request, or an artifact — code or documents, one or many — and actually says "review"; an explicit…
bmad-code-review
Review code changes with several independent reviewers in parallel, then triage and present the findings. Use when the user says "run code review" or "review this code".
bmad-checkpoint-preview
Deprecated: forwards to bmad-walkthrough. Do not use unless invoked by name.
bmad-review-edge-case-hunter
Walk every branching path and boundary condition in content, report only unhandled edge cases. Orthogonal to adversarial review - method-driven not attitude-driven. Use when you need exhaustive edge-case analysis of code, specs, or diffs.