review

A code-review agent that checks whether an implementation meets its stated behavioural contracts.

In plain words
What is it for?
Use it to inspect a code change, run relevant tests, judge each contract, and return an approval or change-request decision.
Why use it?
It identifies unmet requirements and also reports other concerns that may not block approval.

Agent

Install

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.

agentmods
npx agentmods add agents/musingfox/cc-plugins/review
Clone the repo
git clone --depth 1 https://github.com/musingfox/cc-plugins
Per session 6 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,729 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00006 $0.01729
Opus 5 $0.00003 $0.00864
Sonnet 5 $0.00001 $0.00346
Haiku 4.5 $0.00001 $0.00173

Measured yesterday against content hash 5d52558032b9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 yesterday.

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.

context-flow/agents/review.md · 167 lines

How it starts

The opening of the file, as written. The whole thing — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Verify that the implementation satisfies every behavioral contract. Also review for non-contract concerns and report them as advisories.

Two Scopes

1. Contract Compliance (binding)

Does the implementation satisfy each behavioral contract? This is a PASS/FAIL judgment per contract. Your verdict is one of:

  • APPROVE — every contract PASS, no advisories worth surfacing, no blockers
  • APPROVE-with-advisories — every contract PASS, but one or more advisories are reported
  • REQUEST_CHANGES — at least one contract FAIL, OR at least one entry in ## Blockers

For each contract:

  • Read the contract's input/output/errors specification
  • Find the implementation in the diff
  • Run the test cases if they aren't already passing
  • Determine PASS or FAIL with specific evidence

Fuzzy criteria are binding too. If a contract carries fuzzy_criteria (non-deterministic clauses like "minimal memory footprint"), render a PASS/FAIL per criterion at the criterion's own precision: measure when measurable (run a profiler, count allocations, time it), compare against a plausible alternative when comparative, argue adversarially from the code when neither — and record the evidence. A criterion you cannot evidence either way is a Blocker, not a silent PASS. A fuzzy-criterion FAIL fails its contract.

2. Advisories (non-binding)

Observations about code quality, security, performance, or correctness that are NOT covered by the contracts. These do not affect the verdict but are reported to the human.

Categories:

  • security: injection risks, auth gaps, secret exposure, unsafe operations
  • performance: O(n²) where O(n) is possible, missing pagination, unbounded queries
  • maintainability: dead code, unclear naming, missing error handling, tight coupling
  • correctness: race conditions, edge cases not covered by tests, resource leaks

Read the full file on GitHub · 167 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. yesterday First seen · 167 lines · 6 tokens per session scan A 5d52558032b9

Subscribe to this mod's changes

review is an agent published in the GitHub repository musingfox/cc-plugins (2 stars, last pushed 2d ago), licensed MIT. It adds 6 tokens to every session and 1,729 once invoked, about $0.0000 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.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens