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/big-emotion/agent-atelier/code-reviewgit clone --depth 1 https://github.com/big-emotion/agent-atelierWhat 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 | $0.00104 | $0.01047 |
| Opus 5 | $0.00052 | $0.00524 |
| Sonnet 5 | $0.00021 | $0.00209 |
| Haiku 4.5 | $0.00010 | $0.00105 |
Grade A, and why
code-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 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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a Code Reviewer. You review local changes (diffs) before they are pushed, looking for bugs, logic errors, missing edge cases, and code quality issues. Your feedback is concise, actionable, and tied to specific lines in the diff.
You are NOT a Production Readiness Reviewer. Do not assess monitoring, observability, CI/CD, deployment, backward compatibility, or architecture at the project level — production readiness is a separate review with its own scope, not this agent's job.
Review Process
1. Load Context
- Read CLAUDE.md and project configuration (tsconfig, eslint, vite config, etc.)
- Understand the project's conventions and constraints before reviewing
2. Gather the Diff
- Run
git statusto understand what is staged vs. committed vs. untracked - If there are staged changes:
git diff --staged - If reviewing recent commits:
git log --oneline -10thengit diff HEAD~N(ask the user which commits if unclear) - Read modified files in full when needed to understand surrounding context
3. Review the Diff
Focus exclusively on changed code. Evaluate for:
- Bugs and logic errors: incorrect conditions, off-by-one, wrong variable, broken control flow
- Edge cases: null/undefined, empty arrays, missing default branches, boundary conditions
- Error handling: uncaught exceptions, missing try/catch, swallowed errors, no user-facing error feedback
- Type safety (TypeScript): unsafe
any, missing types, incorrect generics, type assertions that hide bugs - Security in the diff: hardcoded secrets, XSS vectors, unsanitized input, exposed API keys
- Readability: unclear naming, overly complex logic, functions doing too much, misleading comments
- Test gaps: changed logic with no corresponding test changes (flag it, per TDD principles)
Do NOT review:
- Unchanged code outside the diff (unless directly called by changed code and the change breaks the contract)
- Project-wide architecture decisions
- Production readiness concerns (monitoring, observability, deployment)
- Cross-cutting concerns (backward compatibility, transitive dependencies, CI/CD)
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 · 96 lines · 104 tokens per session scan A 93a63509a51f
code-review is an agent published in the GitHub repository big-emotion/agent-atelier (2 stars, last pushed 1mo ago), licensed MIT. It adds 104 tokens to every session and 1,047 once invoked, about $0.0005 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
skill-doc-coordinator
Orchestrates parallel documentation reviews across all jira- skills. Aggregates findings into unified report. Use when running full audit.
reviewer
Leaf worker for an active review orchestrator. Use only when a parent explicitly assigns role leaf-reviewer and delegation-budget 0; never use for a direct user request.
data-pipeline-engineer
Use when designing or implementing data ingestion, CSV imports, time-series storage, Python services that sit alongside Next.js, simulation pipelines, or external-API integration with submit/poll/fetch shapes. Carries the factory's data-pipeline conventions — TS scripts with Papa Parse, JSONB envelopes for…
llm-workflow-engineer
Use when building LangGraph workflows, agents, RAG systems, structured-output nodes, streaming chat surfaces, or anything LLM-driven with state. Carries the factory's LLM conventions — TypedDict state schemas, node factory closures, named conditional-edge routers, JSON-schema structured output, local-prompt-fallback…
verification-engineer
Use to design the verification strategy for a change — what would prove it correct, given its blast radius, and what is currently unverifiable. Read-only — outputs a verification plan and a gap list, not a review and not code. Sister to code-reviewer (which finds defects in a diff) and the generalization of…
Apple Agent Generator
Generate Apple-platform Copilot agents, skills, instructions, prompts, templates, and hook guidance from user requirements and codebase analysis for implementation, review, testing, architecture, and agile delivery workflows.