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/artcc/freelingo/agents-mdgit clone --depth 1 https://github.com/artcc/freelingoWhat 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 | $0.04351 | $0.04351 |
| Opus 5 | $0.02176 | $0.02176 |
| Sonnet 5 | $0.00870 | $0.00870 |
| Haiku 4.5 | $0.00435 | $0.00435 |
Grade A, and why
freelingo 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 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.
The source is not reproduced here
Licensed AGPL-3.0
The repository is licensed AGPL-3.0, which this catalogue does not treat as permission to reproduce the file. Read it at the source.
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.
- 2d ago First seen · 179 lines · 4,351 tokens per session scan A 18b3af76500a
freelingo AGENTS.md is an instructions file published in the GitHub repository artcc/freelingo (88 stars, last pushed 7d ago), licensed AGPL-3.0. It adds 4,351 tokens to every session, about $0.0218 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 2026-08-30.
Other instructions, from other repositories
wacrm AGENTS.md
Instructions for ArnasDon/wacrm: This version has breaking changes — APIs, conventions, and file structure may all differ from your training data. Read the relevant guide in nodemodules/next/dist/docs/ before writing any code. Heed deprecation notices.
agentgram CLAUDE.md
Instructions for agentgram/agentgram, covering claude.md — agentgram development guide, project overview, tech stack, monorepo structure and core architecture patterns.
xeo-forge AGENTS.md
Instructions for lahkiri/xeo-forge, covering xeo forge v3 — agent & architecture rules, 1. what this product is, 2. hard architecture rules (non-negotiable), 3. tech stack and 4. data model (the only tables).
wacrm CLAUDE.md
Instructions for ArnasDon/wacrm, a project described as: Self-hostable CRM template for WhatsApp — shared inbox, contacts, sales pipelines, broadcasts, and no-code automations. Fork it, brand it, host it.
pleng CLAUDE.md
Claude Code instructions for mutonby/pleng, covering pleng — self-hosted ai-native paas, architecture, key directories, dev commands and coding standards.
sentou AGENTS.md
AGENTS.md instructions for TrueLineCollective/sentou, covering orientation for contributors and coding agents, stack and a real caveat, commands (all must pass before a pr is ready), where things live and conventions.