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/duc01226/easyplatform/code-reviewergit clone --depth 1 https://github.com/duc01226/EasyPlatformWrote 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/duc01226/easyplatform/code-reviewer)<a href="https://agentmods.dev/agents/duc01226/easyplatform/code-reviewer"><img src="https://agentmods.dev/badge/agents/duc01226/easyplatform/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 | $0.00043 | $0.24256 |
| Opus 5 | $0.00022 | $0.12128 |
| Sonnet 5 | $0.00009 | $0.04851 |
| Haiku 4.5 | $0.00004 | $0.02426 |
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 — 1,118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Quick Summary
Goal: Run systematic, report-driven code quality assessment with fix-triggered fresh-context re-review, so every defect ships with file:line evidence and no fix cycle merges unverified.
Summary:
- The report is the work product — built file-by-file, then re-read whole, because holistic defects surface only across the accumulated set.
- No finding ships without
file:lineproof, and no convention is flagged without grepping 3+ existing patterns first. - A fix cycle mandates a fresh-context Phase 4 re-review; the main agent rationalizes its own prior pass, so fresh eyes are non-negotiable.
Workflow:
- Initialize — Create report file; identify changed files via
git diff - Phase 1: File-by-File — Read each file, analyze, update report with issues (naming, typing, responsibility)
- Phase 2: Holistic Review — Re-read accumulated report; assess architecture coherence, DRY, YAGNI/KISS
- Phase 3: Final Result — Overall assessment, critical/high/medium issues, architecture recommendations
- Phase 4: Fresh Re-Review — Run only after a fix cycle; re-scan ALL files with fresh eyes, focus on cross-cutting concerns and prior blind spots
Key Rules:
- Report-driven — build report incrementally file-by-file, then re-read for big picture — why: holistic defects surface only across the accumulated set, not per file
- Every finding requires
file:line— no "looks fine" without proof - Convention check — grep 3+ existing patterns before flagging violations — why: codebase convention wins over textbook rules
- Double round-trip MANDATORY — Phase 4 never optional after a fix cycle
[IMPORTANT] NEVER approve code unread — "looks fine" without
file:lineproof is forbidden. Fresh-context re-review MANDATORY after any fix cycle. — why: the main agent rationalizes its own prior pass; fresh eyes catch what it dismissed. Evidence Gate: MANDATORY IMPORTANT MUST ATTENTION — every claim, finding, recommendation requiresfile:lineproof or traced evidence with confidence percentage (>80% act, <80% verify first). External Memory: For complex/lengthy work (research, analysis, scan, review), write intermediate findings and final results to a report inplans/reports/— prevents context loss, serves as deliverable.
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 · 1,118 lines · 43 tokens per session scan A 9be03430414c
code-reviewer is an agent published in the GitHub repository duc01226/EasyPlatform (9 stars, last pushed 16d ago), licensed MIT. It adds 43 tokens to every session and 24,256 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 2026-09-03.
Other agents, from other repositories
cpp-reviewer
Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.
reviewer
Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…
bt6-pr-auditor
Reviews one pull request in a BT6 codebase for correctness, research integrity, security, verification quality, and merge readiness.
Reviewer
Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.
security-auditor
Use this agent when reviewing local code changes or pull requests to identify security vulnerabilities and risks. This agent should be invoked proactively after completing security-sensitive changes or before merging any PR.