AI4L: Agent for Claude Code

.claude/agents/er-fixer.md

er-fixer is an agent for Claude Code from forever-healthy/AI4L. It costs 12 tokens per session (1,743 once invoked), scanned A, original, MIT.

An agent for auditing and fixing an evidence review according to a specified AI4L process. An evidence review is a structured collection of material and quality checks used to assess a subject.

In plain words
What is it for?
Use it to inspect the named review and its quality-assurance files, then apply the required audit or fixes.
Why use it?
It limits the work to the selected review and its permitted files, reducing accidental use of unrelated review data.

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-fixer.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-fixer

README.md
[![agentmods](https://agentmods.dev/badge/agents/forever-healthy/ai4l/er-fixer.svg)](https://agentmods.dev/agents/forever-healthy/ai4l/er-fixer)
Your own site
<a href="https://agentmods.dev/agents/forever-healthy/ai4l/er-fixer"><img src="https://agentmods.dev/badge/agents/forever-healthy/ai4l/er-fixer.svg" alt="Measured on agentmods" height="20"></a>
Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,743 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 $0.00012 $0.01743
Opus 5 $0.00006 $0.00872
Sonnet 5 $0.00002 $0.00349
Haiku 4.5 $0.00001 $0.00174

Measured 2d ago against content hash 0cb74ea896c3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

er-fixer 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 2d 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-fixer.md · 113 lines

How it starts

The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AI4L - Agent to Audit & Fix 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.

  • Report FIXER: evidence_review: [evidence_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 a QA audit on [evidence_review] by following the instructions in [ai4l_prompt]

  • If the [pass_rate] of the audit is not 100% {

    • Report FIXER: pass_rate: [pass_rate]. Will fix the issues found in the audit.

    • Fix the issues found in [evidence_review] during the audit

    • When fixing a link that failed 5.10, 5.11 or 5.13, repair it in exactly one of two ways: replace the URL with one that retrieves the cited source and itself satisfies Section 5, or remove the link and its annotation when no such URL exists. Never leave a failing link in place, and never rewrite the annotation to match a different page.

    • Save the fixed version of the [evidence_review]

    • Report FIXER: ER fixed: [evidence_review]

    • Report FIXER: Documenting the fixes in a markdown file...

    • Create a [temporary_file] [audit_filename]_fixes.md with the following content:

    • Start with ## Fixes [audit_date reformatted as '%d/%m/%Y %H:%M']

    • Then note all the fixed issues in this format:

      • Analog to the ## Issues section, but with the following changes/similarities:

      • Numbered list

      • Each entry: 1. **{item# of the issue} — {short label, a 3-6 word condensed summary}:** {What was changed, from-to if helpful. 1-2 sentences max.}

      • {item# of the issue} MUST be the exact section.item reference from the ## Issues section (e.g., 6.1, 17.2), NOT the sequential list position number

      • Bold covers only the item number(s) and the {short label} , followed by a colon

      • If one fix covers multiple items, combine: **6.1 / 6.10 — {short label}:**

      • Example: 3. **7.5 — PMC link format:** Replaced PMC link for Johnston et al. 2006 with s format. (here 3 is the list position, 7.5 is the issue reference — they are different)

    URL Changes

    • When a fix adds, removes or replaces a url, what follows the bold **{item#} — {short label}:** prefix is, after a blank line and indented to the list item's text column, a machine-parseable record as a single-row headerless table with three pipe-separated fields: | <MARKER>: <urls> | tried: <tools> | outcome: <why> |

    • The record row stands alone: no header row, and no | --- | --- | --- | after it — a trailing delimiter row stops it from rendering as a table.

    • Every url in the <urls> field is written as an inline markdown link whose link text is the url itself — [https://example.org/page](https://example.org/page) — so it renders as a clickable hyperlink. Never leave a bare url; it renders as plain text. When the url itself contains parentheses, wrap the destination in angle brackets: [https://example.org/a_(b)](<https://example.org/a_(b)>).

Read the full file on GitHub · 113 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. 2d ago First seen · 113 lines · 12 tokens per session scan A 0cb74ea896c3

Subscribe to this mod's changes

er-fixer is an agent published in the GitHub repository forever-healthy/AI4L (38 stars, last pushed 10d ago), licensed MIT. It adds 12 tokens to every session and 1,743 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.