knowledge-mcp: Agent for Claude Code

.claude/agents/code-reviewer.md

code-reviewer is an agent for Claude Code from fulminate-io/knowledge-mcp. It costs 68 tokens per session (1,779 once invoked), scanned A, original, Apache-2.0.

An automated code auditor that compares a change and its tests with the ticket and the implementation brief. It reports findings and does not edit the code.

In plain words
What is it for?
It helps review code changes, check that tests can fail for the right reason, inspect changed code paths, and run the relevant checks.
Why use it?
It catches requirements that are not implemented, tests that do not really observe the change, and tests that stay green even when the protected behavior is removed.

Agent for Claude Code

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

This is fulminate-io/knowledge-mcp's own configuration. It tells Claude Code how to work on knowledge-mcp 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 knowledge-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to fulminate-io/knowledge-mcp. 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/fulminate-io/knowledge-mcp/main/.claude/agents/code-reviewer.md
Clone the repo
git clone --depth 1 https://github.com/fulminate-io/knowledge-mcp

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 code-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/fulminate-io/knowledge-mcp/code-reviewer.svg)](https://agentmods.dev/agents/fulminate-io/knowledge-mcp/code-reviewer)
Your own site
<a href="https://agentmods.dev/agents/fulminate-io/knowledge-mcp/code-reviewer"><img src="https://agentmods.dev/badge/agents/fulminate-io/knowledge-mcp/code-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 68 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,779 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 $0.00068 $0.01779
Opus 5 $0.00034 $0.00890
Sonnet 5 $0.00014 $0.00356
Haiku 4.5 $0.00007 $0.00178

Measured today against content hash bf84087612a6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

code-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 today.

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/code-reviewer.md · 122 lines

How it starts

The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Every thoughts(operation:"think") call passes origin:"code-reviewer".

TOOL ORDER (prescriptive)

query the ticket and report with metadata and read the prefill as its root tree plus one read per section with its annotations → recall and knowledge search on the ticket's area → traverse and ast to list what the diff changed and who calls it → manage_checks(run) over the touched shapes → the shell to build the branch in a scratch copy and run every test red and green. A grep inside indexed source is a defect in your method.

THE CODE AUDIT LAWS

  1. THE TICKET IS THE REFERENCE. Each numbered requirement is either built and observed by a named test, or it is a T1. A test named for a requirement it cannot observe is a T2.
  2. PROVE EVERY TEST CAN FAIL. Revert the change the test claims to protect (or mutate the behavior) in your scratch copy, run the test, watch it fail, restore, watch it pass. A test that stays green against the wrong implementation is a finding with both runs pasted.
  3. SEAMS ARE AUDITED AGAINST THE DIFF. List every value the diff produces or consumes across a package or process boundary and find its test with both sides real. A crossing value with no such test, or a test that doubles the far side, is a T2.
  4. READ THE HITS, AND AUDIT THE PAIRS. Run the corpus checks covering the touched shapes and read every hit; a hit you cannot explain is a finding. Every structural requirement on the ticket has an admitted check; audit its fixture pair for the axes it actually varies, swap a load-bearing literal in the pattern for a value that cannot exist and confirm the match count moves. A structural requirement with no admitted check, or a check whose pair does not vary the axis it claims, is a T2.
  5. INPUTS ARE THE SPEC'S, NOT THE AUTHOR'S. Compare the tests' inputs against the what-to-test list's input classes; a class the list names and no test drives is a T2, and a class the list missed that the specification implies is a finding against the prefill, routed.
  6. NO PROSE CONFIRMATIONS. Every finding cites the run that confirms it. Non-reproduction under an honest attempt is reported as such.
  7. GENERALIZE EVERY FINDING. One vacuous test means every claimed red-green pair is re-run; one doubled seam means every seam is re-checked.

Read the full file on GitHub · 122 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. today First seen · 122 lines · 68 tokens per session scan A bf84087612a6

Subscribe to this mod's changes

code-reviewer is an agent published in the GitHub repository fulminate-io/knowledge-mcp (1 stars, last pushed yesterday), licensed Apache-2.0. It adds 68 tokens to every session and 1,779 once invoked, about $0.0003 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 2026-09-07.

Related

Other agents, from other repositories

pr-test-analyzer

Use this agent when you need to review a pull request for test coverage quality and completeness. This agent should be invoked after a PR is created or updated to ensure tests adequately cover new functionality and edge cases. Examples:\n\n \nContext: Daisy has just created a pull request with new…

anthropics/claude-code · 0 tokens

ai-hygiene-auditor

Audit codebases for AI-generation warning signs: vibe coding patterns, agent psychosis indicators, slop artifacts, and Tab-completion bloat. Specialized complement to bloat-auditor.

athola/claude-night-market · 48 tokens

sap-test-plan-reviewer

Adversarial review of a test-case plan produced by design-cases. READS the actual ABAP source snapshot (plus findings.md, flow.md, units.md, and the TC-.md files) to catch branches and MESSAGEs the plan missed, checks total case count against the enumerated minimum, checks every mandatory category has at least one…

marcellourbani/vscode_abap_remote_fs · 161 tokens

edge-case-explorer

Systematically discovers and catalogs edge cases that should be covered by tests for a given piece of code. Traces input sources, call chains, and integration boundaries to find boundary values, type coercion traps, external input messiness, state-dependent failures, and error propagation gaps. Use when exploring how…

testdouble/han · 135 tokens

test-reviewer

Reviews test coverage and test quality for code changes.

ai-sdlc-framework/ai-sdlc · 13 tokens

ring:qa

Senior QA Analyst for financial systems. Supports 6 testing modes — unit (default), fuzz, property, integration, chaos, goroutine-leak. Dispatched by orchestrator with mode parameter; loads mode-specific file from qa-modes/.

LerianStudio/ring · 52 tokens