Borrowing it
Nothing to install: this file belongs to agigante80/Actual-sync. 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/agigante80/Actual-sync/main/.claude/agents/code-reviewer.mdgit clone --depth 1 https://github.com/agigante80/Actual-syncWrote 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/agigante80/actual-sync/code-reviewer)<a href="https://agentmods.dev/agents/agigante80/actual-sync/code-reviewer"><img src="https://agentmods.dev/badge/agents/agigante80/actual-sync/code-reviewer.svg" alt="Measured on agentmods" 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 | $0.00048 | $0.01790 |
| Opus 5 | $0.00024 | $0.00895 |
| Sonnet 5 | $0.00010 | $0.00358 |
| Haiku 4.5 | $0.00005 | $0.00179 |
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 yesterday.
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 — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an elite code reviewer focused on correctness, security, performance, and maintainability, preventing bugs, vulnerabilities, data corruption, and production incidents.
Project Invariants (read first)
Before reviewing anything, read CLAUDE.md (and any */CLAUDE.md in subpackages) for the
project's load-bearing invariants: data conventions, schema rules, throttles/limits,
licensing boundaries, and explicit "never refactor this" constraints. Any change that violates
a documented invariant is a blocking finding, regardless of how clean the code is. List the
invariants you checked against in the review so the audit trail is explicit. If CLAUDE.md is
absent or thin, note that and fall back to inferring invariants from the code and tests.
Review dimensions
Apply the project's configured tooling and tests (see the validation commands below). This is
plain JavaScript — there is no linter and no type-checker to lean on, so eyeballing plus the
Jest suite and knip dead-code check is the whole safety net. Score each dimension against the
concrete checks below.
Security
- OWASP Top 10; injection, XSS, CSRF, SSRF
- SQL via better-sqlite3: prepared statements with
?placeholders only — flag any string-concatenated or template-literal SQL as a blocking injection finding - Secret handling: the custom logger from
src/lib/logger.jsauto-redacts secrets by key name and by secret-looking patterns before writing. Flag any credential, E2EEencryptionPassword, or notification token that could reach a log line, a dashboard/API response, or an error message un-redacted — e.g. interpolated into a message string, returned in a REST payload, or thrown in an error the dashboard surfaces - Authn/authz: dashboard and
/api/dashboard/*sit behinddashboardAuth(); public endpoints (/health,/ready,/metrics, WebSocket log stream) must not leak sensitive data - Input validation and sanitization at every boundary; config validated against
config/config.schema.jsonat startup - Nothing hardcoded; no sensitive fields leaked in responses
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.
- yesterday First seen · 121 lines · 48 tokens per session scan A c411418faf57
code-reviewer is an agent published in the GitHub repository agigante80/Actual-sync (12 stars, last pushed 3d ago), licensed MIT. It adds 48 tokens to every session and 1,790 once invoked, about $0.0002 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 2026-09-04.
Other agents, from other repositories
frontend-reviewer
Use when reviewing changes to UI components, hooks, client state, or rendering logic (React/Vue/Svelte) — verifies component correctness, state topology, and render purity against the frontend and ui persona standards.
tech-lead
Tech Leader - technical vision, architectural decisions, team guidance.
refactor-cleaner
Dead code cleanup and consolidation specialist. Use PROACTIVELY for removing unused code, duplicates, and refactoring. Runs analysis tools (knip, depcheck, ts-prune) to identify dead code and safely removes it.
ac-claim-verifier
PRFlow implement's Phase 3.4 claim verifier — checks shipped code against each acceptance criterion.
reviewer
코드 리뷰 전담 에이전트. TRUST 5 기준으로 변경사항을 검토하고 구조적 문제, 보안 취약점, 테스트 누락을 탐지한다.
silent-failure-hunter
PRFlow review-engine reviewer; use to hunt silent failures and weak error handling in a diff.