Borrowing it
Nothing to install: this file belongs to ariel-lee-1023/Books-to-Skill-Refs. 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/ariel-lee-1023/Books-to-Skill-Refs/main/AGENTS.mdgit clone --depth 1 https://github.com/ariel-lee-1023/Books-to-Skill-RefsWrote 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/ariel-lee-1023/books-to-skill-refs/agents-md)<a href="https://agentmods.dev/instructions/ariel-lee-1023/books-to-skill-refs/agents-md"><img src="https://agentmods.dev/badge/instructions/ariel-lee-1023/books-to-skill-refs/agents-md/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.
<a href="https://agentmods.dev/instructions/ariel-lee-1023/books-to-skill-refs/agents-md"><img src="https://agentmods.dev/badge/instructions/ariel-lee-1023/books-to-skill-refs/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.01213 | $0.01213 |
| Opus 5.5 | $0.00485 | $0.00485 |
| Sonnet 5.5 | $0.00243 | $0.00243 |
| Haiku 4.5 | $0.00121 | $0.00121 |
Grade A, and why
Books-to-Skill-Refs 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 5d 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.
How it starts
The opening of the file, as written. The whole thing — 38 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Agent Instructions
Local staging and publication order
For all future new deliverables from this local project, read /Users/AI products/Git-deliverables/WORKFLOW.md before selecting output paths. Set OUTPUT_ROOT to /Users/AI products/Git-deliverables and build <repository-name>/ there first. Use host scratch or /Users/AI products/Git-deliverables/_work/<run-id>/ for intermediate extraction files. Do not generate new destination repositories under this tool's outputs/ or root.
Finish the published-repository layout and validation in staging, then move the project to /Users/AI products/GIthub/<repository-name>/, then commit and push from that location. This is the user's standing workflow for future builds; explicit draft-only or no-publication instructions override it. It does not relocate existing deliverables. Ask only for missing destination information when necessary, rather than repeating authorization for the workflow. The local profile overrides generic output defaults in SKILL.md. If used on another machine without the local document, obtain applicable paths rather than inventing them.
Building and publishing skill libraries
When the user asks in this local project to build a new skill and references, complete repository packaging and publication as part of the standing workflow above, unless that task explicitly requests a draft or no publication. Do not stop after generating the runtime files.
Follow the published-repository layout, modeled on Cognitive Neuroscience Expert. Use a root SKILL.md, root references/, a project AGENTS.md, a complete README.md, a suitable LICENSE, .gitignore, and .agents/skills/<skill-name> -> ../.. for project discovery. The alias name must match the skill's frontmatter slug. Keep one canonical copy of the runtime files.
Name the directory for source provenance, coverage, fidelity, evaluation, and validation records fidelity-ledger/. Do not call it docs/ in generated destinations, and do not place these maintainer records in references/. Load only the runtime skill and relevant references when answering domain questions.
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.
- 5d ago Changed · +8 lines · +275 tokens per session fc038cd335a8
- 1mo ago Changed · +37 tokens per session 470592c6067c
- 1mo ago Changed · +2 lines · +74 tokens per session 861c885c228a
- 1mo ago First seen · 28 lines · 827 tokens per session scan A b2896804a46c
Books-to-Skill-Refs AGENTS.md is an instructions file published in the GitHub repository ariel-lee-1023/Books-to-Skill-Refs (2 stars, last pushed 6d ago), licensed MIT. It adds 1,213 tokens to every session, about $0.0049 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 2026-09-13.
Books-to-Skill-Refs AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| Books-to-Skill-Refs AGENTS.mdariel-lee-1023/Books-to-Skill-Refs | Instructions file | 2 | 6d ago | MIT | A | 1,213 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |