audit

audit is a command for coding agents from airbone42/360-data-athlete. It costs 0 tokens per session (890 once invoked), scanned A, original, MIT.

A command that checks a training-coaching system for conflicting information across its configuration, helper agents, instructions, exercise mapping, and intervals.icu notes.

In plain words
What is it for?
Run it to create a Markdown audit report in data/audits/. It can check online sources or skip them with the --offline option, and proposed fixes require athlete approval.
Why use it?
It helps find when advice or settings have drifted apart before they cause inconsistent training plans.

Command

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the aicoach-framework plugin — 7 commands, 16 agents shipped together

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/airbone42/360-data-athlete/audit
Clone the repo
git clone --depth 1 https://github.com/airbone42/360-data-athlete

Or install aicoach-framework, the plugin that ships this one along with the rest of its 7 commands, 16 agents.

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

README.md
[![agentmods](https://agentmods.dev/badge/commands/airbone42/360-data-athlete/audit.svg)](https://agentmods.dev/commands/airbone42/360-data-athlete/audit)
Your own site
<a href="https://agentmods.dev/commands/airbone42/360-data-athlete/audit"><img src="https://agentmods.dev/badge/commands/airbone42/360-data-athlete/audit.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 890 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 $0.00000 $0.00890
Opus 5 $0.00000 $0.00445
Sonnet 5 $0.00000 $0.00178
Haiku 4.5 $0.00000 $0.00089

Measured 5d ago against content hash 63ffe817900f, 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 5d 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.

commands/audit.md · 109 lines

How it starts

The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/audit — Consistency audit of the knowledge base

Scans the coach system for contradictions between config/ files, sub-agents, prompts, the exercise mapping, and external sources (intervals.icu NOTEs). Findings are refined by the config-auditor (fresh context) and written as a markdown report to data/audits/. Fixes go through the config-fixer (fresh context) after athlete approval.

Arguments

$ARGUMENTS Optional: --offline (skip intervals.icu roundtrip — faster, but NOTE drift and shoes are not checked).


Workflow

Step 1: Run the mechanical scanner

Default is online — the most important drift sources (NOTE-vs-static, intervals.icu gear/shoes) need API access.

python3 "${CLAUDE_PLUGIN_ROOT:-.}"/scripts/audit_consistency.py > /tmp/audit_raw.json

For --offline in arguments:

python3 "${CLAUDE_PLUGIN_ROOT:-.}"/scripts/audit_consistency.py --offline > /tmp/audit_raw.json

Check online_error in the JSON. If present → inform the athlete and continue with the available findings.

Step 2: Launch config-auditor as subagent

Launch the config-auditor agent as a subagent (Task tool) to guarantee fresh context — not inside the active coach pane.

In the prompt, pass:

  • Path /tmp/audit_raw.json (or the JSON content directly, if small)
  • Current date for the output path
  • Mode (online/offline)

The auditor:

  1. Reads the scanner JSON
  2. Refines each finding semantically (drop, severity adjustment, context enrichment)
  3. Adds its own semantic checks (phase-vs-restriction, LTHR drift, mapping plausibility, equipment match, exercise-log drift, recovery week activities)
  4. Writes a report to data/audits/YYYY-MM-DD-HHMM-audit.md
  5. Returns a compact summary (HIGH/MEDIUM/LOW counts + top HIGH findings)

Step 3: Present summary

Show the athlete the auditor summary 1:1, plus the report path. Ask:

"Which findings should I fix? (e.g. 'F001, F003' or 'all HIGH' or 'nothing')"

Step 4: Fixes via config-fixer (fresh context)

Read the full file on GitHub · 109 lines

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. 5d ago First seen · 109 lines · 0 tokens per session scan A 63ffe817900f

Subscribe to this mod's changes

audit is a command published in the GitHub repository airbone42/360-data-athlete (22 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 890 tokens. 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.