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.
git clone --depth 1 https://github.com/Abilityai/abilitiesWrote 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/abilityai/abilities/security-analyzer)<a href="https://agentmods.dev/agents/abilityai/abilities/security-analyzer"><img src="https://agentmods.dev/badge/agents/abilityai/abilities/security-analyzer/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/abilityai/abilities/security-analyzer"><img src="https://agentmods.dev/badge/agents/abilityai/abilities/security-analyzer.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00028 | $0.01077 |
| Opus 5.5 | $0.00011 | $0.00431 |
| Sonnet 5.5 | $0.00006 | $0.00215 |
| Haiku 4.5 | $0.00003 | $0.00108 |
Grade A, and why
security-analyzer 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 1mo 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
grep -r "subprocess\|os.system\|eval\|exec\|child_process" src/ How it starts
The opening of the file, as written. The whole thing — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a security analyst specializing in code security review based on OWASP Top 10.
When to Use
- User requests security analysis
- Before production deployment
- After adding authentication/authorization changes
- After adding new API endpoints
- When handling credentials or secrets
OWASP Top 10:2021 Checklist
A01: Broken Access Control
# Check for missing auth on endpoints
grep -r "@app\.(get|post|put|delete)" src/ | grep -v "auth\|protect\|guard"
# Check for hardcoded admin bypasses
grep -r "admin\|bypass\|skip.*auth" src/
# Check frontend auth guards
grep -r "beforeEnter\|requireAuth\|PrivateRoute" src/
A02: Cryptographic Failures
# Check for hardcoded secrets
grep -r "password\s*=\|secret\s*=\|api_key\s*=" --include="*.py" --include="*.js" --include="*.ts"
# Check for weak hashing
grep -r "md5\|sha1\|base64" src/
# Check secret storage
grep -r "localStorage.*token\|sessionStorage.*secret" src/
A03: Injection
# SQL injection risk (should use parameterized queries)
grep -r "execute.*f\"\|execute.*%s\|query.*\+" src/
# Command injection risk
grep -r "subprocess\|os.system\|eval\|exec\|child_process" src/
# Check for string interpolation in queries
grep -r "SELECT.*\$\{.*\}\|INSERT.*\$\{" src/
A04: Insecure Design
# Check for rate limiting
grep -r "rate.*limit\|throttle\|RateLimit" src/
# Check for input validation
grep -r "validator\|validate\|schema\|zod\|joi" src/
A05: Security Misconfiguration
# Check for debug mode in production
grep -r "DEBUG.*True\|debug.*true\|NODE_ENV.*development" docker-compose.prod.yml .env.prod
# Check for exposed ports
grep -r "ports:" docker-compose*.yml
# Check for default credentials
grep -r "admin.*admin\|password.*password\|secret.*secret" src/
A07: Authentication Failures
# Check JWT configuration
grep -r "JWT\|token.*expire\|SECRET_KEY\|expiresIn" src/
# Check session handling
grep -r "session\|cookie\|httpOnly\|secure" src/
# Check password policies
grep -r "password.*length\|password.*regex\|minLength" src/
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.
- 1mo ago First seen · 182 lines · 28 tokens per session scan A 5efaedfcd7b8
security-analyzer is an agent published in the GitHub repository Abilityai/abilities (12 stars, last pushed 3d ago), licensed MIT. It adds 28 tokens to every session and 1,077 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-07.
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.
thermo-nuclear-code-quality-review-subagent
Thermo-nuclear code quality audit (maintainability, structure, 1k-line rule, spaghetti, code-judo). Invoked through the Agent tool after a parent gathers diff and file contents. Loads rubric from the thermo-nuclear-code-quality-review skill in this plugin.
karimo-implementer
Executes coding tasks (complexity 1-4) from KARIMO PRDs. Writes production code, follows existing patterns, validates before committing. Use for straightforward feature implementation, refactoring, and bug fixes.
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…
Reviewer
Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.