audit-local

audit-local is a command for Claude Code from semiotic-ai/agentsec. It costs 8 tokens per session (111 once invoked), scanned A, original, MIT.

A command that runs the agentsec security checker on local end-to-end test fixtures. It builds the project first, then checks whether the complete audit process works.

In plain words
What is it for?
Use it to build the packages, audit the local test fixtures, and report or fix problems found by the full audit pipeline.
Why use it?
It helps catch build failures, broken audit steps, regressions, and unexpected security findings before changes are accepted.

Command for Claude Code

Install

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.

agentmods
npx agentmods add commands/semiotic-ai/agentsec/audit-local
Clone the repo
git clone --depth 1 https://github.com/semiotic-ai/agentsec

Made for: Claude Code.

Wrote 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.

agentmods badge for audit-local

README.md
[![agentmods](https://agentmods.dev/badge/commands/semiotic-ai/agentsec/audit-local.svg)](https://agentmods.dev/commands/semiotic-ai/agentsec/audit-local)
Your own site
<a href="https://agentmods.dev/commands/semiotic-ai/agentsec/audit-local"><img src="https://agentmods.dev/badge/commands/semiotic-ai/agentsec/audit-local.svg" alt="Measured on agentmods" height="20"></a>
Per session 8 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 111 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00008 $0.00111
Opus 5 $0.00004 $0.00056
Sonnet 5 $0.00002 $0.00022
Haiku 4.5 $0.00001 $0.00011

Measured 3d ago against content hash 8da5fb679a05, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

audit-local 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.

.claude/commands/audit-local.md · 12 lines

What it actually says

Run the agentsec CLI against the local E2E test fixtures to verify the full audit pipeline works end-to-end.

Steps:

  1. Build all packages: bun run build (or turbo build)
  2. Run the CLI: bun packages/cli/src/cli.ts audit --path ./e2e/fixtures --verbose
  3. Report the results — highlight any regressions or unexpected findings
  4. If there are build errors, fix them before running the audit
Changes

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.

  1. 3d ago First seen · 12 lines · 8 tokens per session scan A 8da5fb679a05

Subscribe to this mod's changes

audit-local is a command published in the GitHub repository semiotic-ai/agentsec (5 stars, last pushed 2mo ago), licensed MIT. It adds 8 tokens to every session and 111 once invoked, about $0.0000 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.