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.
npx skills add JeonJe/claude-plugins --skill ma-reviewgit clone --depth 1 https://github.com/JeonJe/claude-pluginsWrote 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/jeonje/claude-plugins/ma-review)<a href="https://agentmods.dev/skills/jeonje/claude-plugins/ma-review"><img src="https://agentmods.dev/badge/skills/jeonje/claude-plugins/ma-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/jeonje/claude-plugins/ma-review"><img src="https://agentmods.dev/badge/skills/jeonje/claude-plugins/ma-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 | $0.00143 | $0.01066 |
| Opus 5 | $0.00072 | $0.00533 |
| Sonnet 5 | $0.00029 | $0.00213 |
| Haiku 4.5 | $0.00014 | $0.00107 |
Grade A, and why
ma-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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/ma-review
Run an evidence-backed review of MA artifacts. Load only the selected mode; plan and code have different inputs, mutation boundaries, and completion gates.
Invocation
/ma-review <issue-key> [plan|code] [--project=<project>] [--auto-apply]
| Input | Action | Output |
|---|---|---|
/ma-review PROJ-123 plan |
Review PRD/design/all target PLANs before implementation | {stateRoot}/PROJ-123/review-plan.md |
/ma-review PROJ-123 code --project=example-backend |
Review the worktree diff against contracts and evidence | {stateRoot}/PROJ-123/review-result.md |
/ma-review PROJ-123 |
Infer from artifacts and worktree state; ask once if ambiguous | One mode-specific report |
Resolve the mode
- Use explicit
planorcodewhen provided. - Choose
codewhen a target worktree has implementation diff plus HANDOFF/PLAN/dispatch evidence. - Choose
planwhen PRD/design/temporary PLANs exist and implementation evidence does not. - Ask once if both or neither condition is decisive. Never review code under plan scope or mutate code while resolving the mode.
Load only the selected workflow
plan: readreferences/modes/plan.mdandchecklists/artifact-consistency.md.code: readreferences/modes/code.md, then load extraction/verification/output and conditional fallback checklists named there.
References index
| File | When to read |
|---|---|
| references/modes/plan.md | Plan mode — full workflow |
| references/modes/code.md | Code mode — full workflow |
| checklists/artifact-consistency.md | Plan mode — mechanical consistency pass before qualitative review |
| checklists/extraction.md | Code mode — shared context/AC extraction |
| checklists/verification.md | Code mode — finding verification pass |
| checklists/output-format.md | Code mode — review-result.md format |
| checklists/code-fallback.md | Code mode — no dedicated code-risk reviewer available |
| checklists/cross-project.md | Code mode — multiple projects or a cross-project contract changed |
| agents/architect.md | Code mode — contract/architecture review lane |
| agents/qa-manager.md | Code mode — acceptance/scenario review lane |
What ships with it
10 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- agents/architect.md 864 B
- agents/qa-manager.md 1.2 KB
- checklists/artifact-consistency.md 6.2 KB
- checklists/code-fallback.md 1.9 KB
- checklists/cross-project.md 962 B
- checklists/extraction.md 2.7 KB
- checklists/output-format.md 4.1 KB
- checklists/verification.md 2.7 KB
- references/modes/code.md 3.5 KB
- references/modes/plan.md 4.2 KB
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 · 65 lines · 143 tokens per session scan A 6eefbe111139
ma-review is a skill published in the GitHub repository JeonJe/claude-plugins (3 stars, last pushed 1mo ago), licensed MIT. It adds 143 tokens to every session and 1,066 once invoked, about $0.0007 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
issue-creation
Trigger: issue creation, bug reports, feature requests, or issue approval. Create and triage GitHub issues from repository evidence.
sdd-tasks
Break an SDD change into implementation tasks. Trigger: orchestrator launches task planning for a change.
systemic-issue-triage
Trigger: new issue, bug report, triage, backlog, issue flood, community report, root cause, dead-end, blocked user. Attack issues by root class, never one-by-one; fixes must shrink the system, not grow it.
feature-dev
Guide a feature implementation through a structured seven-phase workflow with deep codebase understanding, clarifying questions, parallel architecture design, and quality review. Use this skill when the user asks to build a new feature, add functionality, or wants a methodical approach to implementation rather than…
ln-51-opportunity-evaluator
Evaluates new product opportunities using demand, channels, competition, and economics. Not for committed-backlog or implementation planning.
change-review
Validate CRM/PM changes before PR.