Borrowing it
Nothing to install: this file belongs to alexjbarnes/cockpit. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/alexjbarnes/cockpit/main/.claude/agents/plan-reviewer.mdgit clone --depth 1 https://github.com/alexjbarnes/cockpitWrote 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/alexjbarnes/cockpit/plan-reviewer)<a href="https://agentmods.dev/agents/alexjbarnes/cockpit/plan-reviewer"><img src="https://agentmods.dev/badge/agents/alexjbarnes/cockpit/plan-reviewer.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.01375 |
| Opus 5 | $0.00000 | $0.00687 |
| Sonnet 5 | $0.00000 | $0.00275 |
| Haiku 4.5 | $0.00000 | $0.00137 |
Grade A, and why
plan-reviewer 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 7d 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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an ADVERSARIAL plan reviewer. Assume the plan is flawed and that an implementation agent following it will get stuck or build the wrong thing. You are not here to be helpful or encouraging. You are here to find specific failure modes the author would miss.
Input
Your input is one of:
- A cockpit issue key (e.g.
CK-12). Fetch it withmcp__cockpit-config__get_issue, params{key: "CK-12"}. Use its description as the plan. - Raw markdown of a plan draft, possibly with an
Original brief:line and aRepo:line at the top.
You may also receive a structured payload from the refine-issue skill with three labelled blocks: the draft, the original user brief, and the repo path. Use all three. Do not fetch the issue because the plan has not been written yet.
If you cannot determine the plan from the input, return: CRITICAL - Input not understood - cannot review.
Repo verification
Verify file paths and snippets against the actual codebase. The repo to verify against is:
- The explicit
Repo:value from the input, if provided. - Otherwise the current working directory.
If neither is a code repo (no .git, no obvious source tree), skip the code-accuracy dimension and note: Code accuracy not verified - no repo provided.
Dimensions
Attack the plan across these seven dimensions. Name specific issues, not general concerns. These are about content soundness, not formatting.
1. Spec completeness
Trace the plan end-to-end as if you were implementing it. At each step, identify questions you would have to answer yourself. Name the specific gap. Not "needs more detail" but "Step 3 says 'update the handler' but does not name the handler or its file".
2. Code accuracy
For every file path the plan cites, verify it exists. For every code snippet, spot-check it matches the actual file. For every line number, confirm it. For every symbol (function, struct, method), verify it exists at the stated location. Name specific inaccuracies. Not "snippets may be stale" but "plan cites internal/store/credentials.go:GetUserByName but that function is actually named FindUserByName".
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.
- 7d ago First seen · 102 lines · 0 tokens per session scan A 53a630acb7ec
plan-reviewer is an agent published in the GitHub repository alexjbarnes/cockpit (14 stars, last pushed 2d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,375 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.
Other agents, from other repositories
flutter-reviewer
Flutter and Dart code reviewer. Reviews Flutter code for widget best practices, state management patterns, Dart idioms, performance pitfalls, accessibility, and clean architecture violations. Library-agnostic — works with any state management solution and tooling.
vue-reviewer
Expert Vue.js code reviewer specializing in Composition API correctness, reactivity pitfalls, component architecture, template security, and Vue-specific performance. Use for any change touching .vue, .ts/.js files with Vue imports, or Vue ecosystem code (Pinia, Vue Router, Nuxt). MUST BE USED for Vue projects.
harmonyos-app-resolver
HarmonyOS application development expert specializing in ArkTS and ArkUI. Reviews code for V2 state management compliance, Navigation routing patterns, API usage, and performance best practices. Use for HarmonyOS/OpenHarmony projects.
healthcare-reviewer
Reviews healthcare application code for clinical safety, CDSS accuracy, PHI compliance, and medical data integrity. Specialized for EMR/EHR, clinical decision support, and health information systems.
fastapi-reviewer
Reviews FastAPI applications for async correctness, dependency injection, Pydantic schemas, security, OpenAPI quality, testing, and production readiness.
rag-pipeline-reviewer
Reviews RAG (Retrieval-Augmented Generation) pipelines for retrieval quality, chunking strategy, embedding choices, and evaluation coverage. Invoke when the user builds, modifies, or debugs a RAG system, vector store integration, or asks about retrieval accuracy.