Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add dykyi-roman/awesome-claude-code/plugin install accWrote 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/dykyi-roman/awesome-claude-code/audit-security)<a href="https://agentmods.dev/commands/dykyi-roman/awesome-claude-code/audit-security"><img src="https://agentmods.dev/badge/commands/dykyi-roman/awesome-claude-code/audit-security.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 | $0.00043 | $0.01924 |
| Opus 5 | $0.00022 | $0.00962 |
| Sonnet 5 | $0.00009 | $0.00385 |
| Haiku 4.5 | $0.00004 | $0.00192 |
Grade A, and why
audit-security 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 — 237 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Security Audit
Perform a comprehensive security audit focusing on OWASP Top 10 and PHP-specific vulnerabilities.
Input Parsing
Parse $ARGUMENTS to extract path, level, and optional meta-instructions:
Format: <path> [level] [-- <meta-instructions>]
Arguments:
- path: Target directory or file (required, default: current directory)
- level: Audit depth - quick|standard|deep (optional, default: standard)
- -- meta-instructions: Additional focus areas or filters (optional)
Examples:
- /acc:audit-security ./src
- /acc:audit-security ./src deep
- /acc:audit-security ./src quick
- /acc:audit-security ./src -- focus on OWASP A01-A03
- /acc:audit-security ./src deep -- focus on injection
- /acc:audit-security ./src -- level:deep (backward compatible)
Parsing rules:
- Split
$ARGUMENTSby--(space-dash-dash-space) - First part = positional arguments, Second part = meta-instructions
- In positional arguments, check if last word is a valid level (
quick|standard|deep) - If level found → extract it; remaining = path
- Also accept
level:quick|standard|deepin meta-instructions (backward compatibility) - Priority: positional > meta-instruction > default (
standard) - Default path: current directory (if empty)
Target
- Path: First part of
$ARGUMENTS(before--) - Meta-instructions: Second part (after
--) — customize audit focus
If meta-instructions provided, adjust audit to:
- Focus on specific OWASP categories mentioned
- Skip categories if requested
- Apply additional checks
- Modify output verbosity
Pre-flight Check
-
Verify the path exists:
- If
$ARGUMENTSis empty, ask user for the project path - If path doesn't exist, report error and stop
- If
-
Verify it's a PHP project:
- Check for
composer.jsonor*.phpfiles - If not a PHP project, report and stop
- Check for
Instructions
Use the acc:security-reviewer agent to perform a comprehensive security audit:
Task tool with subagent_type="acc:security-reviewer"
prompt: "Perform security audit on [PATH]. Audit level: [LEVEL]. [META-INSTRUCTIONS if provided]
Analyze for:
1. Input Validation (A03:2021)
2. Output Encoding / XSS (A03:2021)
3. SQL Injection (A03:2021)
4. Command Injection (A03:2021)
5. Authentication Issues (A07:2021)
6. Authorization / Access Control (A01:2021)
7. CSRF Protection (A01:2021)
8. Sensitive Data Exposure (A02:2021)
9. Cryptographic Failures (A02:2021)
10. SSRF (A10:2021)
11. XXE (A05:2021)
12. Insecure Deserialization (A08:2021)
13. Path Traversal (A01:2021)
14. Dependency Vulnerabilities (A06:2021)
Provide:
- Severity classification (Critical/Major/Minor)
- CWE identifiers
- Attack vectors
- Code examples (vulnerable and fixed)
- OWASP references"
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 · 237 lines · 43 tokens per session scan A 3d7ec46b8129
audit-security is a command published in the GitHub repository dykyi-roman/awesome-claude-code (96 stars, last pushed 20d ago), licensed MIT. It adds 43 tokens to every session and 1,924 once invoked, about $0.0002 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 2026-09-03.
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.