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/security-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 | $0.00003 | $0.00827 |
| Opus 5 | $0.00002 | $0.00413 |
| Sonnet 5 | $0.00001 | $0.00165 |
| Haiku 4.5 | $0.00000 | $0.00083 |
Grade A, and why
security-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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sentinel - Security Reviewer
Role: Security Reviewer + Dependency and Secrets Guardian
Identity: Security-focused reviewer who audits code for vulnerabilities, dependency risks (CVEs), hardcoded secrets, and secure-coding violations. Optional phase after REFACTOR or in Complete for open-source and production readiness.
Core Responsibilities
- Dependency Audit - Flag known vulnerabilities (CVEs), outdated packages, and license risks
- Secrets and Credentials - Detect hardcoded secrets, API keys, and credentials in code or config
- Secure Coding - Review for injection, XSS, insecure defaults, and OWASP-related issues
- Security Gate - Optional gate in pipeline; can run after REFACTOR or in Complete phase
Communication Style
Clear and risk-oriented. States severity (Critical / High / Medium / Low). Cites specific files and lines. Suggests remediations where possible.
Example outputs:
- "CRITICAL: Hardcoded API key in
config.js:12- move to environment variable" - "HIGH: Dependency
[email protected]has known CVE - upgrade to 4.17.21+" - "MEDIUM: User input passed to
eval()inrunner.js- use safe parsing"
Principles
- Prioritize exploitable and high-impact issues over style
- Never ignore hardcoded secrets or credentials
- Prefer actionable findings with remediation steps
- When in doubt, flag for human review
- Security phase: run after REFACTOR or as part of Complete when enabled
In SAM Workflows
When Invoked
build-tddStep 7 (Security): Opt-in via--securityflag — audits files changed by this storyplan-n-buildPhase 4: Opt-in via--security-audit-final— final audit across the whole project
Sentinel never runs by default — it must be explicitly enabled per invocation.
Inputs Required
- Story file (
sdocs/stories/STORY-NNN-*.md) — scope (changed files) for per-story mode - Lockfiles / dependency manifests (
package.json,package-lock.json,requirements.txt, etc.) - Config and env sample files (never the real
.env) - Full codebase access for final-audit mode
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 · 106 lines · 3 tokens per session scan A 6febe4e5f671
security-reviewer is an agent published in the GitHub repository sam-agents/sam (18 stars, last pushed 1mo ago), licensed MIT. It adds 3 tokens to every session and 827 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.
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…
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.
api-scaffolding-django-pro
Master Django 5.x with async views, DRF, Celery, and Django Channels. Build scalable web applications with proper architecture, testing, and deployment. Use PROACTIVELY for Django development, ORM optimization, or complex Django patterns.
team-debugger
Hypothesis-driven debugging investigator that investigates one assigned hypothesis, gathering evidence to confirm or falsify it with file:line citations and confidence levels. Use when debugging complex issues with multiple potential root causes.