Borrowing it
Nothing to install: this file belongs to tonydzi/claude-bible. 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/tonydzi/claude-bible/main/AGENTS.mdgit clone --depth 1 https://github.com/tonydzi/claude-bibleWrote 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/tonydzi/claude-bible/agents-md)<a href="https://agentmods.dev/instructions/tonydzi/claude-bible/agents-md"><img src="https://agentmods.dev/badge/instructions/tonydzi/claude-bible/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 | $0.00864 | $0.00864 |
| Opus 5 | $0.00432 | $0.00432 |
| Sonnet 5 | $0.00173 | $0.00173 |
| Haiku 4.5 | $0.00086 | $0.00086 |
Grade A, and why
claude-bible 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 7d 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — working in this repo
Written for AI coding agents, and equally readable by a human contributor. Short on purpose.
What this repo is
The governance skeleton: how a rule for you, your team, and your AI agents is written, routed, loaded, superseded, and argued with. There is no application here — the deliverables are a spec, templates, and sanitized real examples. Treat prose as the product and review it like code.
docs/SPEC.md is normative. If a change contradicts the spec, either the change is
wrong or the spec needs the same PR.
Layout
docs/SPEC.md— rule anatomy, frontmatter schema, precedence, the routing tree.templates/rule-template.md,decision-memo-template.md,declined-decisions-template.md.examples/— real rules from a live system, sanitized.rule-objection-sparring.mdis the one born from an actual overturned verdict; it is the reference for tone.FOR-ROBOTS.md— the entry point for an agent mining this repo for patterns.ROADMAP.md,CHANGELOG.md— releases are cut twice a week, small commits daily.
How to verify a change
There is nothing to execute, so verification is structural. Before opening the PR:
- Frontmatter validates against
docs/SPEC.md— every required field present,originanddate_establishedreal,supersedespointing at something that exists. - One rule, one file. If your change adds a second rule to an existing file, split it.
- No duplicate homes. A rule lives in exactly one place; everything else points at it. Grep for the rule's trigger phrase before adding it — a copy that drifts is the failure mode this whole repo exists to prevent.
- Links resolve. Both directions, if the rule claims a relationship.
State in the PR which of those four you checked. "Prose, nothing to run" is not a verification.
Conventions
- Trigger + essence + pointer. An always-loaded index line is short by law; the body loads on demand. A rule that needs three paragraphs in the index is two rules or a bad rule.
- Newer beats older on the same topic, and a rule marked with an explicit owner is overturned only by that owner. Never silently edit an owner's rule — supersede it, with a dated record.
- Declined stays declined. A rejected idea goes in the declined-decisions journal with the reason. Re-proposing it needs new information, and the PR should say what the new information is.
- Objections are numbered and rebuttable. A "no" without a numbered list and an invitation to rebut is not a review here; it is an obstacle.
- Examples are sanitized: no real names, no real chat identifiers, no real paths, no secrets.
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.
- 7d ago First seen · 66 lines · 864 tokens per session scan A 81b9fbc70491
claude-bible AGENTS.md is an instructions file published in the GitHub repository tonydzi/claude-bible (9 stars, last pushed 2d ago), licensed MIT. It adds 864 tokens to every session, about $0.0043 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 2026-08-31.
Other instructions, from other repositories
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).
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.
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.
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).
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.