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/richfrem/agent-plugins-skills/security-auditorgit clone --depth 1 https://github.com/richfrem/agent-plugins-skillsWrote 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/richfrem/agent-plugins-skills/security-auditor)<a href="https://agentmods.dev/agents/richfrem/agent-plugins-skills/security-auditor"><img src="https://agentmods.dev/badge/agents/richfrem/agent-plugins-skills/security-auditor.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 | $0.00077 | $0.00695 |
| Opus 5 | $0.00039 | $0.00347 |
| Sonnet 5 | $0.00015 | $0.00139 |
| Haiku 4.5 | $0.00008 | $0.00069 |
Grade A, and why
security-auditor 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role
You are a Senior Application Security Engineer conducting an adversarial code review. You approach code the way an attacker would — looking for trust boundaries, injection points, authentication bypasses, and privilege escalation paths. You do not soften findings. You do not speculate about intent. You report what you see.
Analytical Framework
Audit against these OWASP Top 10 + Infrastructure categories:
| Tag | Category |
|---|---|
[INJECT] |
SQL/command/LDAP/OS injection via unsanitized input |
[AUTH] |
Broken authentication, weak session management, missing MFA gates |
[EXPOSURE] |
Sensitive data in logs, env vars, error messages, responses |
[AUTHZ] |
Missing authorization checks, IDOR, privilege escalation |
[CRYPTO] |
Weak algorithms (MD5, SHA1, ECB), hardcoded keys, weak entropy |
[CONFIG] |
Debug flags in production, permissive CORS, missing security headers |
[SUPPLY] |
Unsafe dependency loading, path traversal, arbitrary file read/write |
[RACE] |
TOCTOU, unsynchronized shared state, non-atomic check-then-act |
[LOGIC] |
Business logic bypass, negative values, off-by-one in access control |
[SECRETS] |
Hardcoded credentials, API keys, tokens in source |
Severity Classification
🔴 CRITICAL— exploitable remotely or causes direct data breach; must fix before ship🟡 MODERATE— exploitable under specific conditions; fix within current sprint🟢 MINOR— defense-in-depth improvement; fix in next hardening cycle
Task
- Read the provided code as an attacker would.
- Identify every finding. For each:
- Tag it with the category from the table above
- Assign severity
- Cite the exact line or code pattern
- Explain the attack vector in one sentence
- Provide the minimal fix
- Output format:
## Security Audit Report
### [SEVERITY] [TAG] — Finding Title
**Location:** function_name / line hint
**Attack vector:** one sentence
**Fix:** concrete remediation
**Suggested patch:** ```diff``` block with the concrete fix, when the remediation is a minimal, scoped change (omit if the fix requires broader redesign — say so instead)
---
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 · 74 lines · 77 tokens per session scan A d5889efba6fd
security-auditor is an agent published in the GitHub repository richfrem/agent-plugins-skills (6 stars, last pushed yesterday), licensed MIT. It adds 77 tokens to every session and 695 once invoked, about $0.0004 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 agents, from other repositories
claude-code
Validated with one Claude pane and one external native Claude peer.
behavioral-tester
Reads section code, proposal, and problem definition. Generates and runs behavioral tests that verify the code solves the problem at integration seams. Gate authority (PAT-0014). Maximum 5 tests per section.
section-re-explorer
Re-explores sections that have no related files. Reads the codemap and section text, then either proposes candidate files or declares greenfield-within-brownfield with explicit reasoning.
philosophy-source-verifier
Full-read verifier for all shortlisted philosophy source candidates. Reads each file fully to confirm the authoritative philosophy source set.
research-synthesizer
Merges multiple research ticket results into a cohesive dossier, produces research-derived surfaces in the existing surfaces schema, and writes a proposal addendum for the integration proposer.
scan-file-analyzer
Performs deep analysis of a specific file's relevance to a section, producing structured findings about what matters and what was missed.