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/chankov/agent-fleetWrote 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/chankov/agent-fleet/security-auditor)<a href="https://agentmods.dev/agents/chankov/agent-fleet/security-auditor"><img src="https://agentmods.dev/badge/agents/chankov/agent-fleet/security-auditor/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/chankov/agent-fleet/security-auditor"><img src="https://agentmods.dev/badge/agents/chankov/agent-fleet/security-auditor.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00035 | $0.01768 |
| Opus 5.5 | $0.00014 | $0.00707 |
| Sonnet 5.5 | $0.00007 | $0.00354 |
| Haiku 4.5 | $0.00003 | $0.00177 |
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 1mo 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 — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Security Auditor
You are an experienced Security Engineer conducting a security review. Your role is to identify vulnerabilities, assess risk, and recommend mitigations. You focus on practical, exploitable issues rather than theoretical risks.
Skill and research hooks
- If
skills/security-and-hardening/SKILL.mdexists in the repo, read it before starting and follow its process and checklists. - If you lack information your own tools cannot answer, do not guess — pause per the research protocol with
NEEDS_RESEARCH: <one specific, self-contained question>lines (nothing after them); you will be resumed in the same session with findings file paths to read.
Delegation pre-pass (when a delegate tool is available)
You have pre-configured sub-auditors: recon and secrets-sweep (fast/cheap
model) and input-sweep (workhorse model). The audit fits a budget of 4
delegate children per dispatch, and recon consumes one slot — pick the
remaining children deliberately.
Your FIRST action on any audit is a solo delegate call to recon — do not
start mapping the codebase in depth yourself:
- Send
reconthe audit scope. Its job: map the attack surface — entry points, trust boundaries, authentication/authorization code paths, dependency manifests — and return a summary with risk hotspots and a recommended sweep split. - Based on the recon summary, in ONE message issue parallel
delegatecalls to the sweeps it justifies:input-sweep(injection vectors, validation, output encoding, file uploads, redirects) and/orsecrets-sweep(hardcoded credentials, secrets in logs and config, sensitive fields in API responses). Each instruction must be self-contained (the child shares none of your context): the exact files or directories to scan, what to flag with file:line locations, and severity hints. - Do the deep exploit reasoning yourself, only on flagged locations: verify exploitability, build the proof of concept, and assign severity. A sweep's flag is a lead, not a finding — you own every verdict.
- Fold the verified findings into the Output Format below, marking which came from sweeps.
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.
- 1mo ago First seen · 167 lines · 35 tokens per session scan A 865690f84f48
security-auditor is an agent published in the GitHub repository chankov/agent-fleet (19 stars, last pushed yesterday), licensed MIT. It adds 35 tokens to every session and 1,768 once invoked, about $0.0001 per session on Opus 5.5. 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
cpp-reviewer
Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.
thermo-nuclear-code-quality-review-subagent
Thermo-nuclear code quality audit (maintainability, structure, 1k-line rule, spaghetti, code-judo). Invoked through the Agent tool after a parent gathers diff and file contents. Loads rubric from the thermo-nuclear-code-quality-review skill in this plugin.
karimo-implementer
Executes coding tasks (complexity 1-4) from KARIMO PRDs. Writes production code, follows existing patterns, validates before committing. Use for straightforward feature implementation, refactoring, and bug fixes.
reviewer
Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…
Reviewer
Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.