Borrowing it
Nothing to install: this file belongs to majiayu000/spellbook. 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/majiayu000/spellbook/main/AGENTS.mdgit clone --depth 1 https://github.com/majiayu000/spellbookWrote 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/majiayu000/spellbook/agents-md)<a href="https://agentmods.dev/instructions/majiayu000/spellbook/agents-md"><img src="https://agentmods.dev/badge/instructions/majiayu000/spellbook/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 | $0.00910 | $0.00910 |
| Opus 5 | $0.00455 | $0.00455 |
| Sonnet 5 | $0.00182 | $0.00182 |
| Haiku 4.5 | $0.00091 | $0.00091 |
Grade A, and why
spellbook 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 6d 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Spellbook Agent Contract
Spellbook is a cross-runtime skill library, not a prompt dump. Keep this file
short: path-scoped AGENTS.md files carry directory-specific rules.
Routing
- Search before creating a new skill, script, registry entry, or support file.
Prefer
rg,rg --files, andpython3 scripts/validate_skills.py search. - For skill authoring or refactors, read
docs/skill-format-policy.md,docs/skill-quality-playbook.md, anddocs/spellbook-operating-contract.mdbefore editing. - For generated registry or install metadata, change the source of truth and regenerate; do not hand-edit generated outputs.
- For high-context files such as
AGENTS.md,CLAUDE.md, and skillSKILL.mdfiles, keep changes intentional, scoped, and visible in the final summary.
Scope Rules
- Do exactly the requested change. Do not add opportunistic migrations, rewrites, or broad cleanup.
- Prefer existing scripts, validators, parsers, and local conventions over new helper code.
- Do not invent metadata fields, registry fields, runtime targets, install behavior, or API surfaces. No data means blank or blocked.
- Do not silently swallow validation errors. Fix the root cause or report the blocker.
- Never commit secrets, tokens, private keys, or credential material.
Threads Long-Run Guardrails
- Generic context-budget and output-firewall policy for Codex subagent
orchestration belongs in
skills/threads/; repository-specific queue policy belongs in the consumer workflow pack. - For long queues or multi-lane runs, keep parent context thin: raw logs, broad searches, CI output, and session JSONL must go to artifacts or stay out of parent context.
threadsrun-log schema,SKILL.md, andreferences/run-log.mdmust stay in sync when adding fields, failure codes, or lane contracts.- Installed copies under
~/.agents/skills/threadsand~/.spellbook/skills/threadsshould be synced and hash-checked when local runtime behavior matters.
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.
- 6d ago First seen · 87 lines · 910 tokens per session scan A e54bd81a2107
spellbook AGENTS.md is an instructions file published in the GitHub repository majiayu000/spellbook (272 stars, last pushed yesterday), licensed MIT. It adds 910 tokens to every session, about $0.0046 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
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.