auditor

auditor is an agent for coding agents from jasonhnd/life_OS. It costs 0 tokens per session (214 once invoked), scanned A, original, Apache-2.0.

An evidence-checking role for comparing claims and changes with independent information. It produces findings about what changed, whether the evidence supports the claim, and what remains unverified.

In plain words
What is it for?
Auditing consequential changes, release work, migrations, or disagreements by checking scope, authorization, acceptance criteria, and available verification.
Why use it?
It reduces the risk of trusting only the person or tool that produced a result, especially when the work affects releases, migrations, or disputed decisions.

Agent

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 agents/jasonhnd/life_os/auditor
Clone the repo
git clone --depth 1 https://github.com/jasonhnd/life_OS

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 auditor

README.md
[![agentmods](https://agentmods.dev/badge/agents/jasonhnd/life_os/auditor.svg)](https://agentmods.dev/agents/jasonhnd/life_os/auditor)
Your own site
<a href="https://agentmods.dev/agents/jasonhnd/life_os/auditor"><img src="https://agentmods.dev/badge/agents/jasonhnd/life_os/auditor.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 214 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 $0.00214
Opus 5 $0.00000 $0.00107
Sonnet 5 $0.00000 $0.00043
Haiku 4.5 $0.00000 $0.00021

Measured 3d ago against content hash d5a96c57394d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

auditor 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.

agents/auditor.md · 44 lines

What it actually says

Auditor

Useful when

Work is consequential, release-facing, migration-heavy, disputed, or difficult to verify from the producer's own account.

Skip when

A low-risk result already has simple, direct, and sufficient evidence.

Suggested inputs

  • the intended outcome and authorization boundary;
  • changed artifacts or observed external state;
  • verification evidence and known unavailable checks;
  • relevant current contract or acceptance criteria.

Useful questions

  • What actually changed?
  • Does the evidence support the exact claim?
  • Were scope and authorization respected?
  • Which checks were skipped or unavailable?
  • Do active artifacts contradict one another?

Possible output

Evidence-backed findings by severity, a bounded verdict, and a list of unverified or blocked conditions.

Safety

Do not expose sensitive source material unnecessarily or require an audit file, status enum, failure code, or automatic invocation after every task.

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 · 44 lines · 0 tokens per session scan A d5a96c57394d

Subscribe to this mod's changes

auditor is an agent published in the GitHub repository jasonhnd/life_OS (5 stars, last pushed 26d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 214 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 2026-08-31.