AI4L: Agent for Claude Code

.agents/agents/er-creator.md

er-creator is an agent for Claude Code from forever-healthy/AI4L. It costs 10 tokens per session (798 once invoked), scanned A, original, MIT.

An agent that creates an evidence review according to the rules in an AI4L instruction file. An evidence review is a structured document that examines a topic using defined evidence and review requirements.

In plain words
What is it for?
Use it to create a new AI4L evidence review for a specified topic using the required instructions and files created during the run.
Why use it?
It provides a prescribed creation process and restricts its file access, reducing the chance that unrelated existing reviews or files influence the new review.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: mentions subagents; installed under .agents/ (shared by several agents); mentions Codex.

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/.agents/agents/er-creator.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-creator

README.md
[![agentmods](https://agentmods.dev/badge/agents/forever-healthy/ai4l/er-creator/github.svg)](https://agentmods.dev/agents/forever-healthy/ai4l/er-creator)
Your own site
<a href="https://agentmods.dev/agents/forever-healthy/ai4l/er-creator"><img src="https://agentmods.dev/badge/agents/forever-healthy/ai4l/er-creator/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for er-creator

Your own site · 80×15
<a href="https://agentmods.dev/agents/forever-healthy/ai4l/er-creator"><img src="https://agentmods.dev/badge/agents/forever-healthy/ai4l/er-creator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 10 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 798 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 $0.00010 $0.00798
Opus 5.5 $0.00004 $0.00319
Sonnet 5.5 $0.00002 $0.00160
Haiku 4.5 $0.00001 $0.00080

Measured 14d ago against content hash a683889f5a5d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

er-creator 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 14d 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/agents/er-creator.md · 46 lines

What it actually says

AI4L - Agent to Create Evidence Reviews according to ER.md

  • Set [topic] to the topic defined in your instructions

  • Report CREATOR: Create ER for [topic]

  • Run date +%s and save the result as [start_time]

  • Set [creator_ai_fullname] to the model name, version number and variant (if any) as stated in your system prompt or developer instructions, written as "[name] [version]" or "[name] [version] [variant]". [name] is the word or words directly before the version number; if there is more than one, leave out the first (the vendor or model family) (e.g., Claude Opus 5.5 → Opus 5.5, gemini-3.8-flash → Gemini 3.8 Flash, acme-nova-max-2.0 → Nova Max 2.0). Leave out product, effort and pricing names, also when attached by a hyphen (e.g., Codex, Build, high, free, preview), and capitalize every word. Never use a model name or version from memory. If your system prompt or developer instructions name a model without a version number, [creator_ai_fullname] is that name alone, without a version (e.g., "a Grok Build subagent" → Grok). If they name no model at all, set [creator_ai_fullname] to "Unknown"; a name you believe to be yours does not count.

  • Set [creator_ai_nickname] to [creator_ai_fullname] without the version number, with all remaining words joined by hyphens (e.g., Opus, Gemini-Flash, Nova-Max). If [creator_ai_fullname] has no version number or is "Unknown", [creator_ai_nickname] equals [creator_ai_fullname].

  • Report CREATOR: [creator_ai_fullname] / [creator_ai_nickname]

  • If you resume from a summary of earlier work, take [creator_ai_fullname] and [creator_ai_nickname] from the values reported there; never decide them again.

  • Read [er_prompt] in chunks of 250 lines, from the top to its end

  • READ SCOPE — you may read ONLY:

    • [er_prompt]
    • files you yourself created in [tmp_dir] during this run
  • Never read any existing evidence review or _ER_QA.md file, and never read any other existing file — not in [creation_dir], not in any other directory. Create the ER from [er_prompt], your knowledge, and the research [er_prompt] requires.

  • READ SCOPE covers local files only. Web search and the MCP research tools (PubMed, ClinicalTrials.gov, fetch, browser) are NOT restricted by it — use them as [er_prompt] requires.

  • Never glob, list or search for evidence reviews or _ER_QA.md 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.

  • Create an evidence review for [topic] that can pass a QA audit as described in [er_prompt]

  • Run date +%s, subtract [start_time], convert the elapsed seconds to HH:MM format, and add it as duration: \"HH:MM\" in the frontmatter of the result

  • Save the result as an .md file in [creation_dir] using the [filename] given in the result

  • Report CREATOR: Done with [topic]

  • Report CREATOR: Created [filename]

  • Return filename: [filename]

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. 14d ago Changed · +4 lines a683889f5a5d
  2. 1mo ago Changed · +1 lines 43a59182ab7f
  3. 1mo ago Changed 9416d371ba6c
  4. 1mo ago Changed eb38249e6a26
  5. 1mo ago Changed f755e04d66f8
  6. 1mo ago Changed ce82223175fd
  7. 1mo ago Changed 6c148535d115
  8. 1mo ago Changed fdc7af631975
  9. 2mo ago First seen · 41 lines · 10 tokens per session scan A 8ebc9d7bf115

Subscribe to this mod's changes

er-creator is an agent published in the GitHub repository forever-healthy/AI4L (43 stars, last pushed 10d ago), licensed MIT. It adds 10 tokens to every session and 798 once invoked, about $0.0000 per session on Opus 5.5. 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.

Related

er-creator compared with agents from other repositories

er-creator next to 6 agents from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
er-creatorforever-healthy/AI4LAgent4310d agoMITA10Claude Code
orchestratorfall-out-bug/sdpAgent195mo agoMITA0Claude Code
stage-gate-controllerConradgui/loop-craftAgent53mo agoApache-2.0A78Claude Code
plannerfall-out-bug/sdpAgent195mo agoMITA16Claude Code
reviewerfall-out-bug/sdpAgent195mo agoMITA17Claude Code
timps_environment_doctorSandeeprdy1729/timps-swarmAgent12mo agoMITA65Claude Code
timps_network_medicSandeeprdy1729/timps-swarmAgent12mo agoMITA74Claude Code