audit

A structured review step for projects that use Spec Kit, a specification-driven development process.

In plain words
What is it for?
It supports reviews focused on documentation, implemented code, or tests at the appropriate stage of the Spec Kit process.
Why use it?
It helps check whether the code, documentation, or tests match the project's specifications and development plan.

Command

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/stefaniuk/loadout/audit
Clone the repo
git clone --depth 1 https://github.com/stefaniuk/loadout
Per session 59 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 352 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 $0.00059 $0.00352
Opus 5 $0.00030 $0.00176
Sonnet 5 $0.00012 $0.00070
Haiku 4.5 $0.00006 $0.00035

Measured yesterday against content hash 75883127cbe6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

audit 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 yesterday.

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.

.github/skills/insecure-defaults/commands/audit.md · 36 lines

What it actually says

Insecure defaults audit

1. Check the corpus is there.

ls -1 ${CLAUDE_PLUGIN_ROOT}/references

Must list *.md files. If it errors or lists none, stop and say so. Don't search elsewhere, don't guess, don't run the audit anyway.

2. Run it. Workflow tool:

name: "insecure-defaults:audit-pipeline"
args: { scope: "$1" or ".", pluginRoot: "${CLAUDE_PLUGIN_ROOT}" }

Pass the ${CLAUDE_PLUGIN_ROOT} value as printed above; it's already the real path.

3. Print the result, by status:

  • findings, no-findings-confirmed: print report.
  • no-candidates: the sweeps ran and matched nothing, which is a real result. There is no report; print note, including its point that this is not proof of absence.
  • report-failed: the audit completed but the write-up died. Print note, then present findings, refuted and coverage yourself.
  • anything else: the audit didn't complete, so it isn't a clean result. Print note and say the run failed.
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. yesterday First seen · 36 lines · 59 tokens per session scan A 75883127cbe6

Subscribe to this mod's changes

audit is a command published in the GitHub repository stefaniuk/loadout (1 stars, last pushed 3d ago), licensed MIT. It adds 59 tokens to every session and 352 once invoked, about $0.0003 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.