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 taoq-ai/ziran --skill audit-agentsgit clone --depth 1 https://github.com/taoq-ai/ziranWrote 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/taoq-ai/ziran/audit-agents)<a href="https://agentmods.dev/skills/taoq-ai/ziran/audit-agents"><img src="https://agentmods.dev/badge/skills/taoq-ai/ziran/audit-agents/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/taoq-ai/ziran/audit-agents"><img src="https://agentmods.dev/badge/skills/taoq-ai/ziran/audit-agents.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 | $0.00100 | $0.01441 |
| Opus 5.5 | $0.00040 | $0.00576 |
| Sonnet 5.5 | $0.00020 | $0.00288 |
| Haiku 4.5 | $0.00010 | $0.00144 |
Grade A, and why
audit-agents 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 3d 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 — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Audit agents with ZIRAN
ziran audit reads agent definitions without running them, maps each declared tool to a
capability and walks the pairs for dangerous chains (a file reader plus a URL fetcher is a data
exfiltration path). No LLM, no API key. Your job is the part the CLI does not do: decide which
findings are real for this agent, explain the attack in one sentence, and propose the smallest
change that removes it.
Check ziran is available
Run ziran --version. It needs ziran>=0.42.0. If it is missing, offer
pip install "ziran>=0.42.0" (or uv tool install ziran); do not install without asking.
Run the audit
PATH is a plugin root (has .claude-plugin/plugin.json), a directory with .claude/agents/, a
directory named agents, a single agent .md file, or Python agent source.
ziran audit <PATH> --format json
Read the JSON, not the table: each row has rule, severity, file, line, message, agent
and tools. Exit code 0 passed, 1 failing findings, 2 usage error (bad path or file).
Add --severity high to hide medium and low rows.
Interpret the rules
| Rule | Meaning | What to tell the user |
|---|---|---|
CC001 |
A dangerous chain over the agent's tools, e.g. data_exfiltration via Read -> WebFetch |
Name the chain type, say how an injected instruction would use it, and give its ATLAS techniques from atlas-chains.md. |
SA003 |
A dangerous tool on its own (Bash, WebFetch, Write ...) |
Ask whether the agent's task needs it. |
SA004 |
A wildcard tool (Bash(*), mcp__server, mcp__server__*) |
Replace with the specific tools or rules it uses. |
SA007 |
No tools: key, so the agent inherits every tool |
Almost always fix: add an explicit list. |
SA001 |
A secret pattern in the prompt, description or tools | Treat as a leaked credential: rotate it, then remove it. Cite file and line; never repeat the secret value. |
CC000 |
The agent file could not be parsed | Fix the frontmatter first; other results are incomplete. |
BL001-BL004 |
Widening against a baseline: new tool, lost tools: key, new chain, new agent |
See "Baseline" below. |
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.
- 3d ago First seen · 113 lines · 100 tokens per session scan A 87c9750b066f
audit-agents is a skill published in the GitHub repository taoq-ai/ziran (11 stars, last pushed yesterday), licensed Apache-2.0. It adds 100 tokens to every session and 1,441 once invoked, about $0.0004 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 2026-10-19.
Other skills, from other repositories
integrate-arcjet-guard-agents
Integrate Arcjet security into a Vercel AI SDK (v7) application using @arcjet/guard — wrap agent tools with guard checks, enforce rules on risky app actions, and emit audit events joined by one correlation ID. Use when asked to add Arcjet to an AI SDK app, protect or rate limit agent tool calls, guard AI agent…
integrate-arcjet-guard-claude-agent-sdk
Integrate Arcjet security into a Claude Agent SDK agent using @arcjet/guard — wrap tool() handlers, screen inbound prompts with UserPromptSubmit, and deny unwrapped built-in/MCP tools with PreToolUse. Use when asked to add Arcjet to a Claude Agent SDK or Claude Code agent, rate limit its tools, screen inbound…
integrate-arcjet-guard-eve
Integrate Arcjet security into a Vercel Eve agent using @arcjet/guard — add guard gates to tools and connections, screen inbound messages, and record agent lifecycle events correlated to the session. Use when asked to add Arcjet to an Eve agent, rate limit its tools, guard connection access, or screen inbound messages.
integrate-arcjet-guard-langchain
Integrate Arcjet security into a LangChain JS createAgent using @arcjet/guard — wrap tool() / StructuredTool, put guardMiddleware on createAgent({ middleware }) for MCP / unwrapped tools, and read configurable.threadid for correlation. Use when asked to add Arcjet to langchain createAgent, rate limit its tools, screen…
integrate-arcjet-guard-genkit
Integrate Arcjet security into a Genkit JS agent using @arcjet/guard — wrap ai.defineTool, put guardMiddleware on generate({ use }) for unwrapped / MCP / filesystem tools, and read a caller-owned id from generate({ context }). Use when asked to add Arcjet to genkit, rate limit its tools, screen inbound messages, or…
integrate-arcjet-guard-langgraph
Integrate Arcjet security into a LangGraph Graph API agent using @arcjet/guard — wrap tool() / StructuredTool, wrap ToolNode for unwrapped MCP tools, and read threadid for correlation. Use when asked to add Arcjet to a LangGraph StateGraph / ToolNode agent, rate limit its tools, screen inbound messages, or block…