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.
npx agentmods add instructions/forever-healthy/ai4l/agents-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/instructions/forever-healthy/ai4l/agents-md)<a href="https://agentmods.dev/instructions/forever-healthy/ai4l/agents-md"><img src="https://agentmods.dev/badge/instructions/forever-healthy/ai4l/agents-md.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 | $0.00261 | $0.00261 |
| Opus 5 | $0.00130 | $0.00130 |
| Sonnet 5 | $0.00052 | $0.00052 |
| Haiku 4.5 | $0.00026 | $0.00026 |
Grade A, and why
AI4L AGENTS.md 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
_2026-Forever_Healthy-573D7D.svg){kind=icon}
OpenAI Codex Instructions
Canonical Paths
When running in Codex, use .codex/skills and .codex/agents as the canonical repo-local skill and agent paths.
These paths may be symlinks. When inspecting them from the shell, follow symlinks, for example with find -L.
Do not use .claude/skills or .claude/agents as the primary path unless explicitly asked or unless resolving the .codex symlink target.
Sub-Agent Defaults
Never set model or reasoning_effort when spawning Codex sub-agents unless the user explicitly asks for a specific model or reasoning effort in the current turn.
Do not set fork_context: true when spawning Codex sub-agents. Sub-agents must start without inherited conversation history and receive only the explicit task instructions, relevant repo paths, globals, and target filenames needed for their assigned work.
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 · 20 lines · 261 tokens per session scan A 827c04beb4ee
AI4L AGENTS.md is an instructions file published in the GitHub repository forever-healthy/AI4L (38 stars, last pushed 9d ago), licensed MIT. It adds 261 tokens to every session, about $0.0013 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 instructions, from other repositories
breathe-cli CLAUDE.md
Claude Code instructions for marekkowalczyk/breathe-cli, covering breathe cli, spec, key constraints, default invocation (omakase) and safety constraints (non-negotiable).
flyto-core AGENTS.md
AGENTS.md instructions for flytohub/flyto-core, covering flyto-core agent rules, flyto2 project memory contract, flyto2 frontend quality gate and repo notes.
Taiwan-Health-MCP CLAUDE.md
Instructions for healthymind-tech/Taiwan-Health-MCP, covering claude.md, language, 文件網站是雙語的 —— 改內容時兩份一起改, gstack and project overview.
icuvisor CLAUDE.md
Claude Code instructions for ricardocabral/icuvisor, covering claude.md, what this project is, authoritative documents, hard rules and project layout.
gccli CLAUDE.md
Claude Code instructions for bpauli/gccli, covering claude.md, project overview, build & quality commands, architecture and key packages.
FreeReps CLAUDE.md
Instructions for meltforce/FreeReps, covering freereps, gotchas, repository & ci/cd, data source documentation and repo documents.