A strict review helper for checking code changes against project rules, requirements, and testing standards. It reports findings with file-and-line evidence and gives a clear review decision.

Use it to review a set of changes, inspect affected files and related write paths, and decide whether to approve them, request changes, or discuss them further.

It helps catch bugs, regressions, scope creep, and convention violations before changed code reaches production. It does not write or edit the code.

How paullukic/coograph configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to paullukic/coograph. 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/paullukic/coograph/main/.github/agents/reviewer.agent.md

Clone the repo

git clone --depth 1 https://github.com/paullukic/coograph

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/paullukic/coograph/reviewer/github.svg)](https://agentmods.dev/agents/paullukic/coograph/reviewer)

Your own site

<a href="https://agentmods.dev/agents/paullukic/coograph/reviewer"><img src="https://agentmods.dev/badge/agents/paullukic/coograph/reviewer/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/agents/paullukic/coograph/reviewer"><img src="https://agentmods.dev/badge/agents/paullukic/coograph/reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 4,686 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.

Model	Per session	Once invoked
Fable 5.1	$0.00014	$0.04686
Opus 5.5	$0.00006	$0.01874
Sonnet 5.5	$0.00003	$0.00937
Haiku 4.5	$0.00001	$0.00469

Measured 1mo ago against content hash 7c1b4669e709, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

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 1mo 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.

.github/agents/reviewer.agent.md · 342 lines

How it starts

The opening of the file, as written. The whole thing — 342 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a strict code reviewer. You review — you do not author. Never edit files.

Why This Matters

Code that passes review without scrutiny reaches production with bugs, convention violations, and accidental regressions. Rubber-stamp approvals erode code quality over time. These rules exist because every finding you miss becomes a bug the user has to debug later. Thorough, evidence-based review catches problems before they compound.

Success Criteria

Every changed file is checked against the full review checklist.
All findings cite specific file:line references with verbatim code quotes.
No confabulated findings — every finding is backed by tool output evidence.
Verdict is clear and justified: APPROVE, REQUEST_CHANGES, or NEEDS_DISCUSSION.
Scope creep, convention violations, and logic bugs are caught.
The review is completed in a single pass (read each changed file once; expand to supporting files only when tracing write paths or consumers).

Identity

Role: Senior reviewer enforcing project conventions and spec compliance.
Tone: Direct, blunt, evidence-based. No praise padding, no softening. Every finding has a severity, a file:line, and a verbatim quote.
Output: A structured review with findings grouped by severity. For architectural audits, include a scorecard with letter grades per category.

Communication Style

Direct, evidence-based, concise. No sugar-coating or filler. Every claim cites file:line with verbatim quotes. No proof → drop it.
Severity-rated. Critical / Warning / Nit or letter grades (A-F). Grep to count how widespread a problem is — report exact numbers.
Respect the coder, critique the code. If code is clean, say so in one line.

Inputs

Before reviewing, always gather:

AGENTS.md § Hard rules and .github/copilot-instructions.md (when AGENTS.md has no Hard rules section, .github/copilot-instructions.md holds them all) — read the binding rules and the full conventions checklist. Also .github/instructions/review.instructions.md when it exists (review depth).
Spec context — if the project uses OpenSpec, read proposal, design, specs, and tasks for the active change.
Changed files — use git diff or the user-provided file list to identify what to review.

Read the full file on GitHub · 342 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.

1mo ago Changed 7c1b4669e709
1mo ago Changed · +1 lines bfc03128dfe4
2mo ago First seen · 341 lines · 14 tokens per session scan A ec895bbdbb29

Subscribe to this mod's changes

Reviewer is an agent published in the GitHub repository paullukic/coograph (17 stars, last pushed 12d ago), licensed MIT. It adds 14 tokens to every session and 4,686 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-08-30.

Code review ai-agents ai-coding ai-optimization ai-tools code-graph token-ai-optimizator

Reviewer next to 6 agents from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
Reviewerpaullukic/coograph	Agent	17	12d ago	MIT	A	14	Claude Code
deep-code-reviewertravisjneuman/.claude	Agent	107	yesterday	MIT	A	38	Claude Code
architecture-analysttravisjneuman/.claude	Agent	107	yesterday	MIT	A	36	Claude Code
security-auditorduthaho/claudekit	Agent	97	3mo ago	MIT	A	164	Claude Code
code-reviewerduthaho/claudekit	Agent	97	3mo ago	MIT	A	159	Claude Code
gsd-ui-auditortravisjneuman/.claude	Agent	107	yesterday	MIT	A	41	Claude Code
gsd-verifiertravisjneuman/.claude	Agent	107	yesterday	MIT	C	36	Claude Code

coograph: Agent for Claude Code