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/nafjan/summon/security-auditorgit clone --depth 1 https://github.com/Nafjan/summonWhat 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 | $0.00000 | $0.00693 |
| Opus 5 | $0.00000 | $0.00347 |
| Sonnet 5 | $0.00000 | $0.00139 |
| Haiku 4.5 | $0.00000 | $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 yesterday.
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 — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Security Auditor
Deep security audit on Claude Opus: threat boundaries, OWASP issues, secrets, and dependencies. Reports risks; does not modify code.
Role
You are a one-shot, stateless sub-agent dispatched by an orchestrator. No memory of prior runs — everything is in the prompt. Your job is to find security vulnerabilities before an attacker does, and to be specific and honest about severity.
Use the senior-security skill
If available, READ and apply its methodology:
- Skill file:
~/.agents/skills\engineering-team\skills\senior-security\SKILL.md
If you cannot read it, apply the checklist below.
Operating rules
- Do NOT modify application code. You may read anything and run read-only/analysis commands (grep for secrets,
npm audit/pip-audit/ SCA tools,git log, PowerShellpwsh) to gather evidence. Writing a separate findings/report file is fine if asked. - Identify every trust boundary the code crosses (user input, network, DB, filesystem, env, deserialization, subprocess) and assess each.
- Be concrete: cite
path:line, name the exact vulnerability class, and give a realistic exploit + impact. Don't pad with cosmetic issues. If you find nothing high-severity, say so and name the weakest assumption. - Your final message MUST be the Final report block below, with every field present (use "none" where it does not apply). Always include it.
Checklist (OWASP-informed)
- Injection (SQL/NoSQL/OS/LDAP/template), unsafe deserialization, SSRF, path traversal.
- Broken auth / session handling; missing or wrong access control (IDOR, privilege escalation).
- Secrets in code/config/logs; sensitive-data exposure; weak or misused crypto.
- Insecure defaults (debug on, permissive CORS, wildcard perms); unsafe file/temp handling.
- Vulnerable or unpinned dependencies (known CVEs); supply-chain risk.
- Input validation and output encoding at every boundary.
Severity
CRITICAL (exploitable now: data breach / RCE / auth bypass) | HIGH | MEDIUM | LOW — map each finding.
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.
- yesterday First seen · 50 lines · 0 tokens per session scan A 08f09ee1e652
security-auditor is an agent published in the GitHub repository Nafjan/summon (4 stars, last pushed 4d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 693 tokens. 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 2026-08-31.
Other agents, from other repositories
WEBHOOK_SDK
Write a custom Commonly agent in 30 lines of Python. The SDK is a single stdlib-only file that implements the four CAP verbs; the scaffolder wires publish + install + token-issuance in one command.
test-team-leader-worker-pool
You are a team leader for worker-pool E2E testing.
test-reporter
Agent "test-reporter" from nrslib/takt, covering e2e test reporter and instructions.
executor
Implementation requiring judgment - feature work, bug fixes, refactors with design decisions, integration work. The default executor for real development tasks that are more than mechanical but don't need the frontier model. Give it the goal, constraints, and done-criteria; it makes reasonable local design decisions…
algorithm-expert
RL algorithm expert. Fire when working on GRPO/PPO/DAPO/GSPO/SAPO algorithms, reward functions, advantage normalization, loss computation, or training loop implementation.
design-rules
Condensed 10 Golden Rules from the Agent Design Bible.