Borrowing it
Nothing to install: this file belongs to benteigland11/Playbook. 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/benteigland11/Playbook/main/AGENTS.mdgit clone --depth 1 https://github.com/benteigland11/PlaybookWrote 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/benteigland11/playbook/agents-md)<a href="https://agentmods.dev/instructions/benteigland11/playbook/agents-md"><img src="https://agentmods.dev/badge/instructions/benteigland11/playbook/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/benteigland11/playbook/agents-md"><img src="https://agentmods.dev/badge/instructions/benteigland11/playbook/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 | $0.01246 | $0.01246 |
| Opus 5.5 | $0.00498 | $0.00498 |
| Sonnet 5.5 | $0.00249 | $0.00249 |
| Haiku 4.5 | $0.00125 | $0.00125 |
Grade A, and why
Playbook 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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Playbook
Procedures live as JSON. This repo is a small CLI and an MCP server: search by intent, then load one procedure in a single call. Python 3.10+. The runtime uses the standard library only. pytest is the optional dev extra.
Layout
playbook/ is the application:
cli.pyparses commands and prints indented JSON, including errors.mcp.pyserves MCP on stdio (JSON-RPC 2.0, one object per line).ops.pycreates, edits, searches, loads, links, and walks procedures.store.pyresolves the directory that holds procedure files.library.pykeeps the decay ledger,.library.json, beside that directory.widget_api.pyre-exports the procedure engine.
tests/ covers the CLI, the MCP server, the store, and ops.
cg/ holds four Cartograph widgets. Each has src/, tests/, examples/, and widget.json, and each has its own tests. pyproject.toml maps them into importable packages:
| Widget | Package | Role |
|---|---|---|
cg/data_gofai_procedure_python |
playbook.engine |
procedure documents |
cg/infra_app_paths_python |
playbook.app_paths |
per-user paths |
cg/universal_bm25_ngram_python |
playbook.bm25_ngram |
BM25 and character n-gram search |
cg/infra_usage_decay_ledger_python |
playbook.usage_decay_ledger |
use-it-or-lose-it ledger |
A widget is self-contained. Logic it needs is copied into its src/.
Hard rules
- Stay on Python 3.10 or newer. Keep the runtime on the standard library.
- Keep the MCP surface to
playbook_search,playbook_open, andplaybook_write. Extend one of those tools before adding another. Every tool schema is in context on every request. - Leave the
mcpsubcommand and those three tool names in place. Ben's Antigravity runsplaybook mcpfrom an editable install. - Keep
playbook mcpstdout pure JSON-RPC. MCP results stay compact. The CLI stays indented for people. - Leave the old
widgetsfield off procedures. Files that still have it load; the field is dropped on read and omitted on the next write. - Write commit messages in plain English, with no em dashes.
- Leave
.playbook/run state uncommitted (the search mark, open walks, and plan files) and leave secrets uncommitted..playbook/and.envare gitignored.
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 First seen · 73 lines · 1,246 tokens per session scan A fc81bdcde44a
Playbook AGENTS.md is an instructions file published in the GitHub repository benteigland11/Playbook (0 stars, last pushed 6d ago), licensed MIT. It adds 1,246 tokens to every session, about $0.0050 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 2026-11-13.
Playbook AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| Playbook AGENTS.mdbenteigland11/Playbook | Instructions file | 0 | 6d ago | MIT | A | 1,246 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 196k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 144k | today | MIT | A | 8,130 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 196k | today | MIT | A | 5,685 | GitHub Copilot |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 150k | today | MIT | A | 4,680 | Codex, OpenCode |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 283k | yesterday | MIT | A | 4,342 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 196k | today | MIT | A | 3,153 | GitHub Copilot |