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 commands/afiqiqmal/claude-security-audit/security-auditgit clone --depth 1 https://github.com/afiqiqmal/claude-security-auditWrote 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/commands/afiqiqmal/claude-security-audit/security-audit)<a href="https://agentmods.dev/commands/afiqiqmal/claude-security-audit/security-audit"><img src="https://agentmods.dev/badge/commands/afiqiqmal/claude-security-audit/security-audit.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 5.1 | $0.00073 | $0.09823 |
| Opus 5 | $0.00036 | $0.04911 |
| Sonnet 5 | $0.00015 | $0.01965 |
| Haiku 4.5 | $0.00007 | $0.00982 |
Grade B, and why
security-audit scanned grade B with 2 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 6d 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.
Cloud metadata endpointmediumServer-side request forgery
One request to 169.254.169.254 can return temporary IAM credentials.
1. **Broken Access Control** [A01:2025 | PR.AA] - IDOR, privilege escalation, missing middleware, role bypass, horizontal/vertical access violations, CORS misconfiguration, metadata manipulation, SSRF (user-controlled UR Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
allowed-tools: Read, Grep, Glob, Bash(grep:*), Bash(find:*), Bash(cat:*), Bash(wc:*), Bash(head:*), Bash(tail:*), Bash(composer:*), Bash(npm:*), Bash(pip:*), Bash(bundle:*), Bash(govulncheck:*), Bash(dotnet:*), Bash(git How it starts
The opening of the file, as written. The whole thing — 629 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Security Audit Command
You are an expert application security engineer. Perform a white-box and gray-box security audit on THIS project, scanning every attack surface. Map all findings to both OWASP Top 10:2025 and NIST Cybersecurity Framework (CSF) 2.0.
Mode Selection
Based on $ARGUMENTS:
- full (default if empty) - All phases: recon + white-box + gray-box + hotspots + smells (Phases 1-5)
- quick - CRITICAL and HIGH severity issues only across all white-box categories, skip gray-box, hotspots and smells (Phases 1-2 only)
- gray - Gray-box testing only: role-based access, API probing, credential boundaries, rate limits and error differentials (Phases 1 and 3 only)
- focus:auth - Deep dive on authentication and authorization (Phase 1 + Phase 2 categories A01, A07 + Phase 4 auth hotspots only)
- focus:api - Deep dive on API security, input validation and rate limiting (Phase 1 + Phase 2 categories A01, A05, A06 for APIs + Phase 4 input/output hotspots only)
- focus:config - Deep dive on configuration, supply chain and infrastructure (Phase 1 + Phase 2 categories A02, A03, A08 + Phase 4 config hotspots only)
- diff - Scan only files changed since last commit (
git diff HEAD), skip gray-box and smells (Phases 0, 1, 2, 4) - diff:BRANCH - Scan only files changed compared to a branch (e.g.,
diff:main), skip gray-box and smells (Phases 0, 1, 2, 4) - recheck:PATH - Re-audit specific files or directories (e.g.,
recheck:src/authorrecheck:src/auth,src/api). Runs Phase 1 (full recon for context) then Phase 2 + Phase 4 scoped to the specified paths only - triage - Interactive triage of an existing report. Requires
./security-audit-report.mdto exist. Walks through each finding and asks the developer to Accept, Defer, Dismiss or Escalate. Outputs./security-audit-triage.md - phase:1 - Reconnaissance only - map project structure, tech stack, entry points, data flow and custom checks
- phase:2 - White-box analysis only - run all 20 attack categories against the full codebase
- phase:3 - Gray-box testing only - role-based access, API probing, credential boundaries, rate limits, error differentials
- phase:4 - Security hotspots only - flag sensitive code areas that need careful review
- phase:5 - Code smells only - structural, data handling, error handling, dependency and design patterns
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.
- 6d ago First seen · 629 lines · 73 tokens per session scan B 52af81c759c0
security-audit is a command published in the GitHub repository afiqiqmal/claude-security-audit (22 stars, last pushed 6mo ago), licensed MIT. It adds 73 tokens to every session and 9,823 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it B with 2 findings (cloud metadata endpoint, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
constitution
Create or update the project constitution from interactive or provided principle inputs.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.