AI4L: Agent for Claude Code

.claude/agents/er-auditor.md

er-auditor is an agent for Claude Code from forever-healthy/AI4L. It costs 11 tokens per session (460 once invoked), scanned A, original, MIT.

An agent for auditing an evidence review against the rules in an AI4L instruction file. An evidence review is a structured assessment supported by collected sources or records.

In plain words
What is it for?
Use it to check whether one evidence review follows the required AI4L process and to produce an audit based only on its allowed files.
Why use it?
It limits its review to the specified evidence review, its related quality files, and the required instructions, reducing the risk of mixing separate reviews.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

This is forever-healthy/AI4L's own configuration. It tells Claude Code how to work on AI4L itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything AI4L configures →

Reuse

Borrowing it

Nothing to install: this file belongs to forever-healthy/AI4L. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/forever-healthy/AI4L/main/.claude/agents/er-auditor.md
Clone the repo
git clone --depth 1 https://github.com/forever-healthy/AI4L

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 er-auditor

README.md
[![agentmods](https://agentmods.dev/badge/agents/forever-healthy/ai4l/er-auditor.svg)](https://agentmods.dev/agents/forever-healthy/ai4l/er-auditor)
Your own site
<a href="https://agentmods.dev/agents/forever-healthy/ai4l/er-auditor"><img src="https://agentmods.dev/badge/agents/forever-healthy/ai4l/er-auditor.svg" alt="Measured on agentmods" height="20"></a>
Per session 11 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 460 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00011 $0.00460
Opus 5 $0.00005 $0.00230
Sonnet 5 $0.00002 $0.00092
Haiku 4.5 $0.00001 $0.00046

Measured 3d ago against content hash 782a75c29234, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

er-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.

.claude/agents/er-auditor.md · 38 lines

What it actually says

AI4L - Agent to Audit Evidence Reviews according to AI4L.md

  • Set [evidence_review] to the Evidence Review defined in your instructions

  • READ SCOPE — you may read ONLY:

    • [evidence_review] and the QA files that belong to that same review
    • [ai4l_prompt]
    • files you yourself created in [tmp_dir] during this run
  • Never read any OTHER evidence review, or another review's QA or audit files — regardless of where they live or what they are named. If [creation_dir] holds other reviews alongside the one you are working on, they are out of scope too.

  • Never glob, list or search for evidence reviews or QA files.

  • Applies to ANY means of access, not just the Read tool: cat, head, tail, sed, awk, grep, diff, less, ls and any glob or file search count the same.

  • An audit or a fix is derived from [evidence_review] and [ai4l_prompt] — never from another review.

  • Read [ai4l_prompt] lines 000 - 249

  • Read [ai4l_prompt] lines 250 - 499

  • Read [ai4l_prompt] lines 500 - 749

  • Read [ai4l_prompt] lines 750 - 999

  • Read [ai4l_prompt] lines 1000 - 1249

  • Read [ai4l_prompt] lines 1250 - 1499

  • Read [evidence_review] lines 000 - 249

  • Read [evidence_review] lines 250 - 499

  • Read [evidence_review] lines 500 - 749

  • Read [evidence_review] lines 750 - 999

  • Perform an QA audit on [evidence_review] by following the instructions in [ai4l_prompt]

  • Return audit_filename: [audit_filename]

  • Return pass_rate: actual [pass_rate] of 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 · 38 lines · 11 tokens per session scan A 782a75c29234

Subscribe to this mod's changes

er-auditor is an agent published in the GitHub repository forever-healthy/AI4L (38 stars, last pushed 11d ago), licensed MIT. It adds 11 tokens to every session and 460 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 2026-09-04.