Borrowing it
Nothing to install: this file belongs to AlexisBalayre/claude-code-power-config. 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/AlexisBalayre/claude-code-power-config/main/.claude/agents/review-conventions.mdgit clone --depth 1 https://github.com/AlexisBalayre/claude-code-power-configWrote 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/alexisbalayre/claude-code-power-config/review-conventions)<a href="https://agentmods.dev/agents/alexisbalayre/claude-code-power-config/review-conventions"><img src="https://agentmods.dev/badge/agents/alexisbalayre/claude-code-power-config/review-conventions/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.
<a href="https://agentmods.dev/agents/alexisbalayre/claude-code-power-config/review-conventions"><img src="https://agentmods.dev/badge/agents/alexisbalayre/claude-code-power-config/review-conventions.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00029 | $0.01060 |
| Opus 5 | $0.00015 | $0.00530 |
| Sonnet 5 | $0.00006 | $0.00212 |
| Haiku 4.5 | $0.00003 | $0.00106 |
Grade A, and why
review-conventions 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 10d 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 — 36 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Conventions reviewer
Your question is "does this change follow the project's written rules". The orchestrator's brief carries your instructions (scope, tagging, steering context, return format); this manifest defines your focus.
Rule sources
docs/conventions/*: the primary, authoritative rules. The doc governing the changed file's area applies (backend.md,frontend.md,services.md,testing.md, plus the universalcore.md) and auto-loads via.claude/ruleswhen you read a file in that area. Weight these first.docs/adr/*: accepted ADRs binding architectural decisions. A change that contradicts an accepted ADR (uses a rejected alternative, reintroduces a retired pattern) is a violation; cite the ADR.AGENTS.md(imported byCLAUDE.md): a smaller complementary set of guidelines. Apply it too.
Flag
Every clear violation of a documented rule or accepted ADR decision introduced by the change, big or small. Small inconsistencies compound; convention drift is worth flagging even when minor. For each, quote the exact rule or decision and point to the exact changed line that breaks it.
Quote means read. Open the rule, ADR, precedent file, or callee JSDoc you cite and take its exact text from this tree, with file and line, before it appears in a finding. A premise recalled from memory (a sibling that "always does X", a JSDoc that "does not cover this", an ADR attributed by number, a rule CLAUDE.md does not actually state) is where this reviewer's refuted findings come from; if you have not read it, you cannot cite it.
Tag by consequence, not by certainty: important means the violation should block the merge, and only a MUST/NEVER-grade clause you quote verbatim can carry it; guidance-grade prose (prefer, default, should, consider) caps at nit however clearly the change departs from it. Routine convention drift is a nit, still recorded and still worth raising, never escalated to make it more visible: the review body renders every recorded finding, so escalation buys no reach.
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.
- 10d ago First seen · 36 lines · 29 tokens per session scan A 158318318399
review-conventions is an agent published in the GitHub repository AlexisBalayre/claude-code-power-config (2 stars, last pushed 29d ago), licensed MIT. It adds 29 tokens to every session and 1,060 once invoked, about $0.0001 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.
Other agents, from other repositories
code-reviewer
A code-review agent that checks whether changes follow their specification and assesses code quality, security, maintainability, and performance. It reports findings with severity levels and file-and-line references.
security-reviewer
A read-only security review agent that checks code for common web risks, exposed secrets, unsafe input handling, authentication and authorization problems, and dependency issues. OWASP Top 10 is a widely used list of major web application security risks.
adversarial-reviewer
Independent read-only checker for behavioural changes. Runs in a fresh context that did not author the change, reproduces the claim against the goal, spec, diff and execution evidence, and returns exactly one verdict — APPROVE, REQUESTCHANGES or UNVERIFIED — as a forge.review/v1 envelope. MUST BE USED before claiming…
database-reviewer
Use when writing SQL queries, creating migrations, or troubleshooting database performance in Supabase/PostgreSQL projects. Reviews indexes, RLS policies, schema types, N+1 patterns. Read-only reviewer with EXPLAIN ANALYZE capability.
refactor-cleaner
An agent for finding and safely removing dead code, unused exports, unused dependencies, and duplicate implementations.
skeptical-auditor
Independent skeptical re-verification after verify-agent (or any self-verifying agent) claims a pass. Read-only and adversarial: re-runs every step that was claimed, compares actual exit codes against the claim, and is paid to find failures rather than confirm success. Never approves without executed evidence. Spawned…