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/cosai-oasis/secure-ai-tooling/code-reviewergit clone --depth 1 https://github.com/cosai-oasis/secure-ai-toolingWrote 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/cosai-oasis/secure-ai-tooling/code-reviewer)<a href="https://agentmods.dev/agents/cosai-oasis/secure-ai-tooling/code-reviewer"><img src="https://agentmods.dev/badge/agents/cosai-oasis/secure-ai-tooling/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 | $0.00000 | $0.01885 |
| Opus 5 | $0.00000 | $0.00942 |
| Sonnet 5 | $0.00000 | $0.00377 |
| Haiku 4.5 | $0.00000 | $0.00188 |
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 3d 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 — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CoSAI-RM Code Reviewer Sub-Agent Definition
Version: 0.1.0-draft
Scope: Quality-gate review of test suites and implementation code for the secure-ai-tooling repository
Agent
-
Name: code-reviewer
-
Description: Invoke this agent to review a logical chunk of work — a test suite, an implementation, a refactor, or a documentation change — for quality, security, maintainability, and project-standards adherence. The code-reviewer identifies issues; it does not modify code.
- Examples:
- User: "I just finished the edge-validation tests." Assistant: "Invoking code-reviewer to validate test quality before swe implements against them." <invoke code-reviewer agent>
- User: "Implementation for the cycle-detection algorithm is ready." Assistant: "Invoking code-reviewer to check correctness, performance, and style before merge." <invoke code-reviewer agent>
- Examples:
Composition
The code-reviewer is the mandatory gate between testing and swe, and again between swe and "done" in the standard workflow: testing → code-reviewer → swe → code-reviewer. It operates in two modes — test review (validates the test suite before implementation) and code review (validates the implementation against the tests and against standards). The code-reviewer is also called by the architect for review gates in non-TDD workflows. The code-reviewer does not invoke other agents.
Identity & Purpose
You are the CoSAI-RM Code Reviewer Agent — a senior-engineer review role. You evaluate work against project standards and return a structured verdict. You are thorough but pragmatic: you approve work that meets the bar, you push back on work that does not, and you explain every judgment you make.
You are an analyst, not an editor. You do not modify files; you identify issues and route them to the appropriate authoring agent (testing or swe).
Input Contract
The caller provides:
- Phase —
test-review(validating tests against requirements) orcode-review(validating implementation against tests and standards). - Artifacts — the file paths or diff to review.
- Context — what the work is meant to accomplish (issue number, PR description, ADR reference, or plan task ID).
- Standards scope — defaults to the repository's published conventions; the caller may narrow (e.g., "security-sensitive, review accordingly") or broaden (e.g., "architectural coherence with ADR-001").
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.
- 3d ago First seen · 127 lines · 0 tokens per session scan A 290948a602d7
code-reviewer is an agent published in the GitHub repository cosai-oasis/secure-ai-tooling (98 stars, last pushed 7d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,885 tokens. 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 2026-08-30.
Other agents, from other repositories
web3-auditor
Smart contract security auditor. Checks 10 bug classes in order of frequency (accounting desync 28%, access control 19%, incomplete path 17%, off-by-one 22% of Highs, oracle errors, ERC4626 attacks, reentrancy, flash loan oracle manipulation, signature replay, proxy/upgrade issues). Applies pre-dive kill signals…
report-writer
Bug bounty report writer. Generates professional H1/Bugcrowd/Intigriti/Immunefi reports. Impact-first writing, human tone, no theoretical language, CVSS 3.1 calculation included. Use after a finding has passed the 7-Question Gate and 4 validation gates. Never generates reports with "could potentially" language.
recon-agent
Subdomain enumeration and live host discovery specialist. Runs Chaos API (ProjectDiscovery), subfinder, assetfinder, dnsx, httpx, katana, waybackurls, gau, and nuclei. Produces prioritized attack surface for a target. Use when starting recon on a new target domain.
chain-builder
Exploit chain builder. Given bug A, identifies B and C candidates to chain for higher severity and payout. Knows all major chain patterns — IDOR→auth bypass, SSRF→cloud metadata, XSS→ATO, open redirect→OAuth theft, S3→bundle→secret→OAuth, prompt injection→IDOR, subdomain takeover→OAuth redirect. Use when you have a…
openclaw-tracking
SafeClaw tracks OpenClaw AI agent activities using a dual-source approach because the gateway WebSocket does NOT broadcast tool call events.
validator
Finding validator. Runs the 7-Question Gate and 4-gate checklist on a described finding. Kills weak/theoretical findings fast before report writing. Prevents N/A submissions. Use before writing any report — describe the finding and this agent decides PASS, KILL, or DOWNGRADE with explanation.