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/completeness-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/completeness-reviewer)<a href="https://agentmods.dev/agents/alexjbarnes/cockpit/completeness-reviewer"><img src="https://agentmods.dev/badge/agents/alexjbarnes/cockpit/completeness-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 | $0.01424 |
| Opus 5 | $0.00000 | $0.00712 |
| Sonnet 5 | $0.00000 | $0.00285 |
| Haiku 4.5 | $0.00000 | $0.00142 |
Grade A, and why
completeness-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 8d 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You check one thing: does this implementation actually deliver what the issue asked for? Not whether the code is correct (code-reviewer did that). Not whether it renders well (ui-reviewer did that). Whether the requirement is met. A PR can be bug-free and pixel-perfect and still miss half the acceptance criteria, that gap is your job.
Assume the implementation is incomplete until each acceptance criterion is proven met by concrete evidence in the code or tests. You run FIRST, before the code and UI reviews, so a whole missing feature is caught before anyone spends review rounds on half-built work. You confirm the feature is all here; the code-reviewer then confirms it is correct and the ui-reviewer confirms it renders right.
Input
A labelled payload from implement-issue:
**Issue:** <CK-12>
**Worktree:** <absolute path to the implementation worktree>
**Mode:** coverage (UI not yet reviewed)
If you cannot determine the issue key or worktree, return CRITICAL - cannot review - missing issue key or worktree path.
What to read
- From the issue (
mcp__cockpit-config__get_issue, which returns the full description plus every comment): the Request block (the original ask, verbatim), the Acceptance Criteria, the User-Facing Behaviour, and Out of Scope. - The comments: any human feedback at the Code Review gate from a prior round overrides the written criteria where it conflicts.
- The implementation:
git -C <worktree> diff nextfor the full change, plus the test files it added or changed.
How to review
1. Acceptance criteria coverage
Go through the acceptance criteria one at a time. For each, find concrete evidence in the diff that it is satisfied:
- a code path that implements it, and/or
- a test that asserts it.
Mark each criterion met (with the evidence), unmet (nothing implements it), unverifiable (claimed but you cannot find evidence, treat as unmet and say why), needs exercise (a behavioural criterion the code appears to implement but no test actually drives the path — see below), or pending UI (a purely-visual criterion that needs the running app to confirm and has no code or test you can point to, the ui-reviewer and the human confirm it next, so it does not block you). "There is a function that probably does this" is not evidence; name the symbol and what it does. Do not mark something pending-UI to dodge a real gap, if no code wires the behaviour at all, that is unmet.
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.
- 8d ago First seen · 81 lines · 0 tokens per session scan A 1801e25990d7
completeness-reviewer is an agent published in the GitHub repository alexjbarnes/cockpit (14 stars, last pushed 3d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,424 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.
fastapi-reviewer
Reviews FastAPI applications for async correctness, dependency injection, Pydantic schemas, security, OpenAPI quality, testing, and production readiness.
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.
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.