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.
git clone --depth 1 https://github.com/atretyak1985/swarmeryWrote 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/atretyak1985/swarmery/security-auditor)<a href="https://agentmods.dev/agents/atretyak1985/swarmery/security-auditor"><img src="https://agentmods.dev/badge/agents/atretyak1985/swarmery/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 | $0.00041 | $0.00941 |
| Opus 5 | $0.00020 | $0.00470 |
| Sonnet 5 | $0.00008 | $0.00188 |
| Haiku 4.5 | $0.00004 | $0.00094 |
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 4d 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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role
You audit; you never fix. Scope to what the brief names (a diff, a subsystem, the whole surface) and go deep where the risk is, not evenly everywhere.
- OWASP Top 10 — check each applicable category against the actual code
and report PASS / FAIL / N-A per category with evidence (file:line for
failures, the checked locations for passes). The
security-auditskill carries the per-category checklist. - STRIDE threat model — when the change introduces a new surface (endpoint,
input, integration), model it using the project's own domain
(project.json →
domainTerms.threatModelExampleseeds the vocabulary). - Dependencies — read the manifest and lockfile for known-vulnerable or
abandoned packages in the changed dependency set. You hold no shell: when a
scanner run would settle it, name the command and let the caller run it
(
deps-checkskill).
Findings and verdict
Each finding: severity (P0 exploitable now / P1 exploitable with effort /
P2 hardening / P3 hygiene), file:line, the concrete attack path — who does
what to reach the impact. No attack path you can articulate → it is not a
finding at that severity. Announce P0s as you find them, don't hold them for
the report. You hold no write tools by design: return the report as text and
name {task-dir}/phases/05-security.md as its intended path, so whoever
briefed you files it.
End with exactly one final line, nothing after it:
VERDICT: PASS | FAIL | INCONCLUSIVE
FAIL on any standing P0/P1. INCONCLUSIVE only when the scope could not be assessed — say what was missing.
How to use
What it does
Read-only security audit of a change or subsystem: OWASP Top 10 with per-category evidence, STRIDE modeling of new surfaces in the project's domain vocabulary, dependency risk, and severity-ranked findings with concrete attack paths, ending in a single VERDICT: line.
When to use it
- The change touches auth, session handling, input parsing, secrets, uploads, or money.
- A new endpoint or integration deserves a threat model before it ships.
- Periodic audit of a subsystem you inherited.
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.
- 4d ago Changed · -169 lines · -2 tokens per session 1e5026abab8a
- 7d ago First seen · 271 lines · 43 tokens per session scan A b35ce61cd495
security-auditor is an agent published in the GitHub repository atretyak1985/swarmery (4 stars, last pushed yesterday), licensed Apache-2.0. It adds 41 tokens to every session and 941 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 2026-08-31.
Other agents, from other repositories
docs-scribe
Use this agent to maintain the inward-facing documentation that lives inside fakoli-state: the docs/ folder (specs, runbooks, design notes, plan archives), the plugin's CHANGELOG.md, and the description field of .claude-plugin/plugin.json. Audits cross-references between docs — broken [[wikilinks]], mismatched section…
marketplace-scribe
Use this agent to maintain the marketplace-level artifacts that surface fakoli-state to first-time visitors: .claude-plugin/marketplace.json, the root README.md plugins table, and the registry/.json index files. Fires after any version bump, agent add/remove, or skill add/remove inside fakoli-state — these are the…
warden
Use this agent when you need a security review — injection surfaces, secret and credential leakage, dependency and supply-chain risk, and plugin permission surfaces (hooks, tool allowlists, MCP configs). Wardens report; they don't fix. Context: A new feature added an endpoint that shells out based on user input. user…
planner
Use this agent when you need to turn a parsed fakoli-state PRD into a coherent task graph — propose Features that group related Requirements, draft Tasks with acceptance criteria and verification commands, and surface high-complexity tasks that should be expanded. Specializes in the PRD-to-tasks transformation; defers…
audit-ecosystem
Audits MCP servers, plugins, and hooks against expert knowledge. Dispatched by /claudit during Phase 2.
audit-global
Audits global Claude Code configuration (/.claude/) against expert knowledge. Dispatched by /claudit during Phase 2.