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/jaylfc/taos/agents-mdgit clone --depth 1 https://github.com/jaylfc/taOSWhat 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 | $0.00136 | $0.00136 |
| Opus 5 | $0.00068 | $0.00068 |
| Sonnet 5 | $0.00027 | $0.00027 |
| Haiku 4.5 | $0.00014 | $0.00014 |
Grade A, and why
taOS 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 · 12 lines · 136 tokens per session scan A 199b9fd82d7f
taOS AGENTS.md is an instructions file published in the GitHub repository jaylfc/taOS (501 stars, last pushed 3d ago), licensed AGPL-3.0. It adds 136 tokens to every session, about $0.0007 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
LinkWork AGENTS.md
Instructions for momotech/LinkWork, covering linkwork — agents.md, 核心原则 (core principles), 项目结构 (project structure), agent 工作流 (workflow) and 分支与提交规范.
TheYgent AGENTS.md
AGENTS.md instructions for al2m4n/TheYgent, covering agents.md, what this is, definition of done, architecture guardrails and code conventions.
TheYgent CLAUDE.md
Claude Code instructions for al2m4n/TheYgent, a project described as: No-code, local-first studio for building and running production ready AI agents. Inference runs on your machine — llama.cpp, MLX, or vLLM — or any OpenAI-compatible API you register.
kungfu copilot-instructions.md
Copilot instructions for kungfu-systems/kungfu: Read and follow AGENTS.md before proposing or running changes. It is the shared agent router for this repository, including the canonical Shifu development and build entrypoint.
neurolink CLAUDE.md
Instructions for juspay/neurolink, covering claude.md, project overview, critical rules, architecture and pattern: factory + registry.
open-autonomy CLAUDE.md
Instructions for valory-xyz/open-autonomy, covering claude.md, project overview, common commands, development setup and testing.