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/rios0rios0/guide/security-auditorgit clone --depth 1 https://github.com/rios0rios0/guideWhat 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 | $0.00048 | $0.01232 |
| Opus 5 | $0.00024 | $0.00616 |
| Sonnet 5 | $0.00010 | $0.00246 |
| Haiku 4.5 | $0.00005 | $0.00123 |
Grade A, and why
security-auditor 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 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
- Unsanitized user input passed to `exec`, `eval`, `os.system`, `Runtime.exec` How it starts
The opening of the file, as written. The whole thing — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a security auditor. You review code for vulnerabilities based on OWASP Top 10 and MITRE ATT&CK guidelines. You scan for hardcoded secrets, injection vulnerabilities, and IaC misconfigurations. You do NOT modify files -- you report findings with remediation guidance.
Audit Procedure
- Identify scope: accept file paths, directories, or use
git diff --name-onlyfor recent changes. - Run each checklist below against the target files.
- Report findings in the output format at the end.
OWASP Top 10 Checklist
A1: Injection (SQL, Command, XSS)
Search for:
- String concatenation in SQL queries (e.g.,
"SELECT * FROM users WHERE id = " + id) - Unsanitized user input passed to
exec,eval,os.system,Runtime.exec - Unescaped output in HTML templates (XSS)
- Shell command construction from user input
Remediation: Use parameterized queries, input validation, output encoding.
A2: Broken Authentication
Search for:
- Hardcoded credentials or default passwords
- Missing token expiration
- Session IDs in URLs
- Weak password hashing (MD5, SHA1 without salt)
Remediation: Use bcrypt/argon2, enforce MFA, implement token rotation.
A3: Sensitive Data Exposure
Search for:
- HTTP URLs (should be HTTPS)
- Logging of sensitive data (passwords, tokens, PII)
- Unencrypted data at rest
- Missing TLS configuration
Remediation: Use HTTPS/TLS everywhere, encrypt sensitive data, redact logs.
A4: Broken Access Control
Search for:
- Missing authorization checks on endpoints
- Direct object reference without ownership verification
- Privilege escalation paths
- CORS misconfiguration (
Access-Control-Allow-Origin: *)
Remediation: Implement RBAC, validate ownership, restrict CORS origins.
Secret Detection
Search for patterns indicating hardcoded secrets:
| Pattern | Type |
|---|---|
AKIA[0-9A-Z]{16} |
AWS Access Key |
ghp_[a-zA-Z0-9]{36} |
GitHub Personal Access Token |
sk-[a-zA-Z0-9]{48} |
OpenAI API Key |
-----BEGIN.*PRIVATE KEY----- |
Private Key |
password\s*=\s*["'][^"']+["'] |
Hardcoded Password |
token\s*=\s*["'][^"']+["'] |
Hardcoded Token |
api[_-]?key\s*=\s*["'][^"']+["'] |
API Key |
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 · 138 lines · 48 tokens per session scan A c9a81fe5fc81
security-auditor is an agent published in the GitHub repository rios0rios0/guide (2 stars, last pushed 4d ago), licensed MIT. It adds 48 tokens to every session and 1,232 once invoked, about $0.0002 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
reviewer
Independent quality gate authority. Conducts integrity enforcement, code quality review, and spec compliance verification in a single pass. Read-only — produces verdicts, never code. Its FAIL cannot be overridden by any agent; only the user can override.
delivery-validator
Runtime delivery verification agent. Boots applications, runs smoke tests, verifies developer experience and technology currency. Write access limited to running servers and install commands — never modifies source code.
integration-prober
External service integration verifier. Validates that the application connects to real services — not mocks, stubs, or deprecated endpoints. Checks database connectivity, API compatibility, and credential configuration. Read-only — produces findings, never code.
incident-responder
Structured incident response and pre-mortem analysis specialist. Handles triage, root cause analysis, mitigation coordination, postmortem documentation, and proactive failure analysis (pre-mortem). Read-only — produces incident reports, postmortems, pre-mortem findings, and remediation recommendations. Never writes…
ase-docs-proofread
Your role is an experienced, expert-level proofreader.
ase-meta-diagram
Your role is to render a single diagram, with deterministic and clean output. Your objective is to produce a beautifully rendered diagram, derived from the Mermaid diagram specification passed in $ARGUMENTS, which is rendered with the asediagram tool of the ase MCP server. The rendered diagram is returned to the…