audit

An onboarding audit for an existing code repository that runs its checks across the whole project and produces a prioritised plan. The audit itself does not change files.

In plain words
What is it for?
Check repository tools and setup, build its code index, review the full scorecard, order the fixes, and repeat the audit until the repository passes its checks.
Why use it?
It shows what needs attention before developers start fixing an unfamiliar codebase, including secrets, blocking problems, and lower-priority quality issues.

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/azrtydxb/procoder/audit
Clone the repo
git clone --depth 1 https://github.com/azrtydxb/procoder
Per session 27 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 364 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 $0.00027 $0.00364
Opus 5 $0.00014 $0.00182
Sonnet 5 $0.00005 $0.00073
Haiku 4.5 $0.00003 $0.00036

Measured yesterday against content hash 4d21ac092cb2, 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.

.kilo/commands/audit.md · 30 lines

What it actually says

The user invoked /procoder:audit.

The command below is the procoder binary on PATH.

This is the onboarding sweep for a repository that was not built under procoder. Nothing is modified by the audit itself — you triage, plan, and fix with the user.

  1. Run procoder doctor; if tools are missing, run procoder init first — an audit full of NOT-checked lines wastes everyone's time.
  2. Run procoder index build, then procoder audit. Read the whole scorecard.
  3. Triage in this order, and present the plan to the user BEFORE fixing:
    1. Secrets — every one needs removal AND rotation; check whether it is a false positive first (a pinned SHA, a fixture) and use gitleaks:allow or .gitleaksignore for those, with a reason.
    2. Other blocking — unformatted files (apply procoder format output), conflict markers, junk, template drift, failing terraform.
    3. Judged info findings — lint, complexity, docs gaps: fix what is real in priority order, record reasons for what you leave.
  4. Fix incrementally — one theme per commit, gate-clean after each — and re-run procoder audit until the scorecard says the repository would pass the gate.
  5. Finish by writing the repo's .procoder/ files (procoder templates prints defaults) so the standard holds from here on.
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 · 30 lines · 27 tokens per session scan A 4d21ac092cb2

Subscribe to this mod's changes

audit is a command published in the GitHub repository azrtydxb/procoder (196 stars, last pushed 2d ago), licensed Apache-2.0. It adds 27 tokens to every session and 364 once invoked, about $0.0001 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 2026-08-30.