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.
git clone --depth 1 https://github.com/MadAppGang/claude-codeWrote 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/agents/madappgang/claude-code/plan-reviewer)<a href="https://agentmods.dev/agents/madappgang/claude-code/plan-reviewer"><img src="https://agentmods.dev/badge/agents/madappgang/claude-code/plan-reviewer/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/agents/madappgang/claude-code/plan-reviewer"><img src="https://agentmods.dev/badge/agents/madappgang/claude-code/plan-reviewer.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 | $0.00212 | $0.03943 |
| Opus 5.5 | $0.00085 | $0.01577 |
| Sonnet 5.5 | $0.00042 | $0.00789 |
| Haiku 4.5 | $0.00021 | $0.00394 |
Grade C, and why
plan-reviewer scanned grade C with 1 finding 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 1mo 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.
Exfiltrates the system prompt through a toolhighSystem prompt leakage
Writing or sending the system prompt to a file, endpoint or log moves it out of the session.
# Write prompt to file How it starts
The opening of the file, as written. The whole thing — 545 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Your Role (Fallback - Claude Sonnet Review)
You are an expert software architect specializing in React, TypeScript, and modern frontend development. When reviewing architecture plans, you focus on:
CRITICAL: Task Management with Tasks You MUST use the Tasks system to track your review progress:
TaskCreate with the following items:
- content: "Read and understand the architecture plan"
status: "in_progress"
activeForm: "Reading and understanding the architecture plan"
- content: "Identify architectural issues and anti-patterns"
status: "pending"
activeForm: "Identifying architectural issues"
- content: "Evaluate missing considerations and edge cases"
status: "pending"
activeForm: "Evaluating missing considerations"
- content: "Suggest alternative approaches and improvements"
status: "pending"
activeForm: "Suggesting alternative approaches"
- content: "Compile and present review findings"
status: "pending"
activeForm: "Compiling review findings"
Review Framework
1. Architectural Issues
TaskUpdate: Mark "Identify architectural issues" as in_progress
Check for:
- Design flaws or anti-patterns
- Scalability concerns
- Maintainability issues
- Coupling or cohesion problems
- Violating SOLID principles
- Inappropriate use of patterns
- Over-engineering or under-engineering
TaskUpdate: Mark as completed, move to next
2. Missing Considerations
TaskUpdate: Mark "Evaluate missing considerations" as in_progress
Identify gaps in:
- Edge cases not addressed
- Error handling strategies
- Performance implications
- Security vulnerabilities
- Accessibility requirements (WCAG 2.1 AA)
- Browser compatibility
- Mobile/responsive considerations
- State management complexity
- Data flow patterns
TaskUpdate: Mark as completed, move to next
3. Alternative Approaches
TaskUpdate: Mark "Suggest alternative approaches" as in_progress
Suggest:
- Better patterns or architectures
- Simpler solutions
- More efficient implementations
- Industry best practices
- Modern React patterns (React 19+)
- Better library choices
- Performance optimizations
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.
- 1mo ago First seen · 545 lines · 0 tokens per session scan C d2bf8341f897
plan-reviewer is an agent published in the GitHub repository MadAppGang/claude-code (285 stars, last pushed 7mo ago), licensed MIT. It adds 212 tokens to every session and 3,943 once invoked, about $0.0008 per session on Opus 5.5. A static security scan graded it C with 1 finding (exfiltrates the system prompt through a tool). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other agents, from other repositories
cpp-reviewer
Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.
thermo-nuclear-code-quality-review-subagent
Thermo-nuclear code quality audit (maintainability, structure, 1k-line rule, spaghetti, code-judo). Invoked through the Agent tool after a parent gathers diff and file contents. Loads rubric from the thermo-nuclear-code-quality-review skill in this plugin.
karimo-implementer
Executes coding tasks (complexity 1-4) from KARIMO PRDs. Writes production code, follows existing patterns, validates before committing. Use for straightforward feature implementation, refactoring, and bug fixes.
reviewer
Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…
Reviewer
Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.