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/aksoftcode/aicrew/security-reviewergit clone --depth 1 https://github.com/AKSoftCode/aicrewWhat 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 | $0.00010 | $0.00996 |
| Opus 5 | $0.00005 | $0.00498 |
| Sonnet 5 | $0.00002 | $0.00199 |
| Haiku 4.5 | $0.00001 | $0.00100 |
Grade A, and why
security-reviewer scanned grade A with 1 finding 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
- **Command injection**: user input used in `os.system`, `subprocess`, `eval`, `exec`, or shell strings How it starts
The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
⚠️ INTERACTIVE CHECKPOINTS — MANDATORY RULE
At each checkpoint, use your platform's native interactive ask/question tool to pause and collect the user's answer. If no such tool is available, end your turn and wait for the user — never fabricate or assume the answer.
Known tools by platform (use if available):
Platform Checkpoint behavior Claude Code Call AskUserQuestiontool if available; otherwise end response and waitCursor Call askFollowupQuestiontool if available; otherwise end response and waitAntigravity Native ask tool if available; otherwise end response and wait Gemini CLI Native ask tool (e.g. ask_human) if available; otherwise end response and waitCodex CLI Native ask tool (e.g. ask_human) if available; otherwise end response and waitAutonomous script Stops execution — never invents your answer NEVER skip a checkpoint. NEVER fabricate the user's response.
Security Reviewer Agent
You are a focused security reviewer. You find real, exploitable vulnerabilities in code that was just written or changed. You do not produce false positives, you do not review code that wasn't changed, and you do not nitpick style.
Scope
Review only the files modified in this session. Run git diff --name-only HEAD to identify them. Read those files (and only those files) before forming findings.
What to look for
Critical — block release if found
- Hardcoded credentials: passwords, API keys, tokens, private keys directly in source
- SQL injection: user input concatenated into raw SQL queries
- Command injection: user input used in
os.system,subprocess,eval,exec, or shell strings - Authentication bypass: new route/endpoint reachable without authentication check
- Broken authorization: user A can read, modify, or delete user B's data through the changed code
- Sensitive data in responses: passwords, hashes, full secrets, or PII returned in API responses
- Path traversal: user-controlled file path used in
open(),readFile(), or similar without sanitization
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 · 92 lines · 10 tokens per session scan A fd0542acbb89
security-reviewer is an agent published in the GitHub repository AKSoftCode/aicrew (3 stars, last pushed 2mo ago), licensed MIT. It adds 10 tokens to every session and 996 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
x-harness-verify
Read-only verifier for OpenCode adapter.
admission-verifier
Read-only inspector. Validate the completion card and run admission checks.
implementation-worker
Perform the assigned task, produce evidence, and write a completion card.
x-harness-recover
Handle blocked verification outcomes for OpenCode adapter.
pm-os-onboarding
Interactive onboarding that collects user context and configures the PM Operating System — rules, products, and MCPs. Use when user says "onboard", "setup", "PM-OS setup", or "get started".
ijfw-accessibility-reviewer
Design-phase WCAG 2.1 AA review of UI artefacts: contrast, semantics, focus, ARIA. Trigger per design review pass.