cockpit: Agent for Claude Code

.claude/agents/plan-reviewer.md

plan-reviewer is an agent for Claude Code from alexjbarnes/cockpit. It costs 0 tokens per session (1,375 once invoked), scanned A, original, Apache-2.0.

An adversarial review of a coding plan that assumes the plan has flaws and looks for specific ways implementation could fail or produce the wrong result.

In plain words
What is it for?
Reviewing an issue plan or draft against a code repository, checking referenced files and code excerpts, and identifying concrete failure points.
Why use it?
It helps catch missing details, incorrect assumptions, and plans that do not match the existing code before implementation begins.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

This is alexjbarnes/cockpit's own configuration. It tells Claude Code how to work on cockpit 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 cockpit configures →

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/alexjbarnes/cockpit/main/.claude/agents/plan-reviewer.md
Clone the repo
git clone --depth 1 https://github.com/alexjbarnes/cockpit

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 plan-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/alexjbarnes/cockpit/plan-reviewer.svg)](https://agentmods.dev/agents/alexjbarnes/cockpit/plan-reviewer)
Your own site
<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>
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 1,375 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 $0.01375
Opus 5 $0.00000 $0.00687
Sonnet 5 $0.00000 $0.00275
Haiku 4.5 $0.00000 $0.00137

Measured 7d ago against content hash 53a630acb7ec, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

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.

.claude/agents/plan-reviewer.md · 102 lines

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 with mcp__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 a Repo: 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:

  1. The explicit Repo: value from the input, if provided.
  2. 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".

Read the full file on GitHub · 102 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. 7d ago First seen · 102 lines · 0 tokens per session scan A 53a630acb7ec

Subscribe to this mod's changes

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.

Related

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.

affaan-m/ECC · 50 tokens

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.

affaan-m/ECC · 68 tokens

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.

affaan-m/ECC · 49 tokens

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.

affaan-m/ECC · 42 tokens

fastapi-reviewer

Reviews FastAPI applications for async correctness, dependency injection, Pydantic schemas, security, OpenAPI quality, testing, and production readiness.

affaan-m/ECC · 33 tokens

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.

affaan-m/ECC · 58 tokens