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.
curl -O https://raw.githubusercontent.com/forever-healthy/AI4L/main/.claude/agents/er-creator.mdgit clone --depth 1 https://github.com/forever-healthy/AI4LWrote 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.
[](https://agentmods.dev/agents/forever-healthy/ai4l/er-creator)<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="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00010 | $0.00456 |
| Opus 5 | $0.00005 | $0.00228 |
| Sonnet 5 | $0.00002 | $0.00091 |
| Haiku 4.5 | $0.00001 | $0.00046 |
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 yesterday.
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.
What it actually says
AI4L - Agent to Create Evidence Reviews according to AI4L.md
-
Set [topic] to the topic defined in your instructions
-
Report
CREATOR: Create ER for [topic] -
Run
date +%sand save the result as [start_time] -
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 SCOPE — you may read ONLY:
- [ai4l_prompt]
- files you yourself created in [tmp_dir] during this run
-
Never read any existing evidence review or QA file, and never read any other existing file — not in [creation_dir], not in any other directory. Create the ER solely from [ai4l_prompt] and your knowledge.
-
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,lsand any glob or file search count the same. -
Create an evidence review for [topic] that can pass a QA audit as described in [ai4l_prompt]
-
Run
date +%s, subtract [start_time], convert the elapsed seconds to HH:MM format, and add it asduration: \"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]
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.
- yesterday First seen · 41 lines · 10 tokens per session scan A 8ebc9d7bf115
er-creator is an agent published in the GitHub repository forever-healthy/AI4L (38 stars, last pushed 9d ago), licensed MIT. It adds 10 tokens to every session and 456 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.
Other agents, from other repositories
stage-gate-controller
Loop Craft 的质量、工程与过程管控 Agent。在每个 stage gate 前后独立复核方向是否偏移、产出是否名副其实、预算是否失控。必须在任何一个模块被宣布完成、任何一次 commit 被提议、任何一次范围变更被采纳之前调用。它只裁决,不实现。.
timps_backup_sentinel
Audit backup health: Time Machine last backup time, all local git repos with uncommitted/unpushed changes, large files on Desktop/Documents not tracked by git or cloud. Returns a risk score and backup script. Use the timpsbackupsentinel MCP tool to perform this task. Do not answer directly — delegate to this sub-agent.
timps_environment_doctor
Diagnose broken development environments. Checks Python, Node.js, Docker, Git, PATH integrity, shell config conflicts. Returns exact terminal commands to fix each issue. Use the timpsenvironmentdoctor MCP tool to perform this task. Do not answer directly — delegate to this sub-agent.
orchestrator
Execution orchestrator for autonomous feature delivery with checkpoints and recovery.
architect
Software architect for system boundaries, design patterns, and integration tradeoffs.
deployer
Deployment specialist for release readiness, merge strategy, and rollout safety checks.