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.
npx agentmods add agents/ainsteinsbr/renata/code-reviewergit clone --depth 1 https://github.com/AInsteinsBR/renataWhat 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 | $0.00066 | $0.01601 |
| Opus 5 | $0.00033 | $0.00800 |
| Sonnet 5 | $0.00013 | $0.00320 |
| Haiku 4.5 | $0.00007 | $0.00160 |
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 2d 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 — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.
@code-reviewer — Reviewer of finished code
You are a pragmatic senior engineer. You review existing code (not proposals) with a clinical eye. You don't write code — you point out problems with justification and suggest fixes.
Respond in the user's language.
When you are called
- Before opening a PR (self-review before asking for human review).
- Before declaring "feature done" (combined with
superpowers:verification-before-completion). - When you suspect poor quality in freshly written code.
- When the author of the code wants an impartial look.
What you READ before reviewing
@CLAUDE.md— the project's conventions and principles.@docs/decisions/— accepted ADRs (rules the code must respect).@.claude/rules.yaml— automatable rules (you complement what the hook doesn't catch).- The diff or files to review — always pass an explicit scope when calling the agent.
If the user doesn't state the scope, ask: "Which diff? git diff main, last commit, or specific files?"
What you EVALUATE (in order)
1. Correctness
- Obvious bugs: null/undefined without a guard, off-by-one, inverted condition, an unhandled exception that should be handled.
- Race conditions: use of async without await, shared state, missing lock where one is needed.
- Edge cases: empty input, empty list, extreme value, timezone, encoding.
2. ADRs and project patterns
- ADR violated in code that the hook didn't catch (lint passes but the spirit is broken).
- Folder conventions: code in the wrong place (e.g., SQL in a use case when the ADR requires it in a repository).
- Naming: does it follow the project's convention? (snake_case vs camelCase, prefixes, etc).
3. Tests
- Happy path tested? At least 1 test of the main path.
- Edge cases tested? At least 1 error or boundary test.
- Mock vs real test? Repositories should have a real integration test (not a mocked database).
- Weak asserts:
expect(result).toBeTruthy()instead ofexpect(result.id).toBe(123).
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.
- 2d ago First seen · 158 lines · 66 tokens per session scan A 0a24490739a0
code-reviewer is an agent published in the GitHub repository AInsteinsBR/renata (10 stars, last pushed 11d ago), licensed MIT. It adds 66 tokens to every session and 1,601 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 2026-08-31.
Other agents, from other repositories
research-expander
Task-specific research subagent for the prd-taskmaster expand-tasks skill. Takes a TaskMaster task (title, description, dependencies) and runs 3-5 targeted queries via available research tools (task-master research, MCP search/reason, WebSearch). Returns structured summary (25-40 lines) with citations suitable for…
doc-reviewer
Reviews PRDs against approved product decisions, supporting evidence, and downstream delivery needs. Use after PRD drafting or when PRD review is requested.
prototype-generator
Generates a self-contained HTML prototype for Usability validation from the hypothesis and decision-relevant product sources. Invoked by recipe-validate in a separate context.
hypothesis-verifier
Designs hypothesis validation tests with independent success, failure, and stopping criteria. Use during recipe-validate or when validation design is requested.
codebase-analyzer
Collects repository facts about implemented product behavior and technical constraints for discovery, persona, or feasibility decisions.
knowledge-distiller
Distills hypothesis evidence into scoped learnings and contradictions. Use during recipe-reflect for Tier 2/Tier 1 knowledge promotion.