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 skills add sergeyklay/.agents --skill audit-agentgit clone --depth 1 https://github.com/sergeyklay/.agentsWrote 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/skills/sergeyklay/.agents/audit-agent)<a href="https://agentmods.dev/skills/sergeyklay/.agents/audit-agent"><img src="https://agentmods.dev/badge/skills/sergeyklay/.agents/audit-agent/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/skills/sergeyklay/.agents/audit-agent"><img src="https://agentmods.dev/badge/skills/sergeyklay/.agents/audit-agent.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 | $0.00095 | $0.01355 |
| Opus 5 | $0.00048 | $0.00678 |
| Sonnet 5 | $0.00019 | $0.00271 |
| Haiku 4.5 | $0.00010 | $0.00136 |
Grade A, and why
audit-agent 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 6d 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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Audit an Agent Run
Reconstruct measurements from persisted records, not from the run's own summary. A native counter is evidence only after its scope, update semantics, and run boundary are known.
Evidence contract
- Keep the audit read-only. Never modify, vacuum, delete, migrate, or import into the runner's session store.
- Treat transcripts and tool inputs as sensitive. Emit structural counts and identifiers by default; sanitize exports before they leave the machine.
- Classify the result as
exact,estimate, orsnapshot.Exactrequires a closed boundary and a successful second-path reconciliation. A live or resumable session is asnapshotthrough an explicit cutoff. - Preserve vendor categories. Report input, cache read, cache write, output, reasoning, and recorded cost separately; combine counters only when the schema proves they do not overlap.
- Distinguish user turns, assistant messages, model steps, and tool calls. Never label one of them simply
turns.
Script paths are relative to this skill directory, not the project working directory. If a command cannot resolve scripts/, prefix it with the skill directory reported by the platform.
Route by evidence source
Identify the runner and installed version before reading records, then load only the matching adapter:
- OpenCode with
opencode db: read references/opencode.md. This is the preferred and tested route. - Codex CLI local rollout JSONL or a saved
codex exec --jsonstream: read references/codex.md. - GitHub Copilot CLI: read references/copilot-cli.md.
- Claude Code JSONL: read references/claude-code.md.
- Gemini CLI JSONL: read references/gemini.md.
- Another runner, an export with unknown schema, or raw logs: read references/generic-logs.md.
- Comparisons, duplicated reads, retries, or artifact yield: also read references/analysis.md.
What ships with it
11 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- agents/openai.yaml 127 B
- references/analysis.md 4.4 KB
- references/claude-code.md 5.5 KB
- references/codex.md 5.2 KB
- references/copilot-cli.md 5.4 KB
- references/gemini.md 2.1 KB
- references/generic-logs.md 3.8 KB
- references/opencode.md 5.0 KB
- scripts/audit_claude_code.py 15 KB runs code
- scripts/audit_opencode.py 29 KB runs code
- scripts/audit_usage.py 18 KB runs code
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.
- 6d ago First seen · 89 lines · 95 tokens per session scan A b0115bb8c011
audit-agent is a skill published in the GitHub repository sergeyklay/.agents (5 stars, last pushed yesterday), licensed Apache-2.0. It adds 95 tokens to every session and 1,355 once invoked, about $0.0005 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 2026-09-05.
Other skills, from other repositories
chatdoc-studio-api
ChatDOC Studio API usage guide - complete documentation and examples for PDF parsing, chat applications, agent applications, content retrieval, and data extraction APIs.
war-room
Multi-agent research war room. Personas debate in sequential turns through two phases — ideation and proposal writing. Persona persistence and drift detection are enforced every turn via the persistent-persona skill.
system-info
Probe system resources — CPU, RAM, disk, GPU/CUDA/MPS — and translate findings into experiment design recommendations. Run this at the start of any compute-intensive project.
persistent-persona
Mechanism for keeping an agent anchored to a caller-defined persona across sessions. Covers the biplate private memory system for drift detection and self-correction.
memory-checkpoint
Defines how to save and load agent state as checkpoint files.
ChatDOC Studio--KnowledgeMate
Create and operate ChatDOC Studio knowledge bases through pdrouter using a Bearer API key and JavaScript helpers. Use when Codex needs to upload one or more PDF/DOC/DOCX files, skip failed files without aborting the whole job, create a knowledge base from successful uploads, or call the ChatDOC Studio knowledge-base…