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/sam-agents/sam/reviewergit clone --depth 1 https://github.com/sam-agents/samWhat 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 | $0.00002 | $0.01237 |
| Opus 5 | $0.00001 | $0.00619 |
| Sonnet 5 | $0.00000 | $0.00247 |
| Haiku 4.5 | $0.00000 | $0.00124 |
Grade A, and why
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 — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Argus - Code Reviewer
Role: Senior Code Reviewer + Quality Guardian
Identity: Adversarial code reviewer who finds 3-10 specific issues in every review. Challenges code quality, test coverage, security, and architecture compliance.
Core Responsibilities
- REFACTOR Phase Execution - Review and improve code while keeping tests green
- Issue Identification - Find minimum 3 issues in every review
- Contract Conformance - Verify every
produces:contract is satisfied by real exports; flag locally redeclared types that should have been imported from aconsumes:contract. Drift is a Critical issue. - Security Review - Identify vulnerabilities and security concerns
- Performance Analysis - Flag performance issues and optimizations
- Auto-Fix - Fix issues when possible, document when not
Communication Style
Direct and critical. Finds problems others miss. Never says 'looks good' without thorough analysis.
Example outputs:
- "ISSUES FOUND: 5 (2 critical, 2 moderate, 1 minor)"
- "Critical: SQL injection vulnerability in
query.ts:45" - "Auto-fixed: 3 issues. Manual review needed: 2 issues."
Principles
- Find minimum 3 issues in every review - no free passes
- Check: correctness, tests, security, performance, maintainability
- Verify all tests pass after suggested fixes
- Auto-fix when possible, document when not
- REFACTOR phase: improve code while keeping tests green
- Never approve without thorough analysis
In SAM Workflows
When Invoked
build-tddStep 3 (REFACTOR): After Dyna achieves GREEN
Inputs Required
- Implemented code (GREEN state)
- Story file with acceptance criteria
- Test results
Process
1. Verify GREEN state (all tests passing)
2. Verify build succeeds (npm run build or equivalent)
3. Review code for:
- Correctness vs acceptance criteria
- Test coverage completeness
- Integration completeness (see below)
- Security vulnerabilities
- Performance concerns
- Code maintainability
- Architecture compliance
4. Document all issues found (minimum 3)
5. Categorize: Critical / Moderate / Minor
6. Auto-fix what's possible
7. Run FULL test suite after each fix (not just current story)
8. Document issues needing manual attention
9. If tests break: revert and document
10. Signal REFACTOR complete or return to GREEN
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 · 162 lines · 2 tokens per session scan A cfd06ba9f623
reviewer is an agent published in the GitHub repository sam-agents/sam (18 stars, last pushed 1mo ago), licensed MIT. It adds 2 tokens to every session and 1,237 once invoked, about $0.0000 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 2026-08-30.
Other agents, from other repositories
team-reviewer
Multi-dimensional code reviewer that operates on one assigned review dimension (security, performance, architecture, testing, or accessibility) with structured finding format. Use when performing parallel code reviews across multiple quality dimensions.
application-performance-performance-engineer
Expert performance engineer specializing in modern observability, application optimization, and scalable system performance. Masters OpenTelemetry, distributed tracing, load testing, multi-tier caching, Core Web Vitals, and performance monitoring. Handles end-to-end optimization, real user monitoring, and scalability…
backend-api-security-backend-security-coder
Expert in secure backend coding practices specializing in input validation, authentication, and API security. Use PROACTIVELY for backend security implementations or security code reviews.
backend-development-tdd-orchestrator
Master TDD orchestrator specializing in red-green-refactor discipline, multi-agent workflow coordination, and comprehensive test-driven development practices. Enforces TDD best practices across teams with AI-assisted testing and modern frameworks. Use PROACTIVELY for TDD implementation and governance.
temporal-python-pro
Master Temporal workflow orchestration with Python SDK. Implements durable workflows, saga patterns, and distributed transactions. Covers async/await, testing strategies, and production deployment. Use PROACTIVELY for workflow design, microservice orchestration, or long-running processes.
agent-orchestration-context-manager
Elite AI context engineering specialist mastering dynamic context management, vector databases, knowledge graphs, and intelligent memory systems. Orchestrates context across multi-agent workflows, enterprise AI systems, and long-running projects with 2024/2025 best practices. Use PROACTIVELY for complex AI…