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/sebyx07/claude-code-bible/claude-mdgit clone --depth 1 https://github.com/sebyx07/claude-code-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/sebyx07/claude-code-bible/claude-md)<a href="https://agentmods.dev/instructions/sebyx07/claude-code-bible/claude-md"><img src="https://agentmods.dev/badge/instructions/sebyx07/claude-code-bible/claude-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 | $0.00858 | $0.00858 |
| Opus 5 | $0.00429 | $0.00429 |
| Sonnet 5 | $0.00172 | $0.00172 |
| Haiku 4.5 | $0.00086 | $0.00086 |
Grade A, and why
claude-code-bible CLAUDE.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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
What this repo is
A prose book — "The Claude Code Bible" — distributed as Markdown. No source code, no build, no tests, no CI. Edits ship by committing .md files.
README.md— landing page and chapter index (TOC table, quick wins, license).docs/NN-<slug>.md— numbered chapters, 01 through 12. Read top-to-bottom as a book.LICENSE— MIT..gitignoreignores.claude/, so local agent config here is never committed.
Default branch: main. Remote: origin. No tags, no release process — readers consume from GitHub directly.
Chapter layout
Chapters are numbered so the TOC order in README.md matches filename order. Adding a new chapter means:
- Create
docs/NN-<slug>.mdwith the next number. - Add a row to the TOC table in
README.md(keep columns aligned:#, Chapter link, "What it covers"). - Cross-links between chapters use relative paths like
[ch. 11](docs/11-compressed-config.md)from the README, or[ch. 11](11-compressed-config.md)from insidedocs/.
Renumbering = renaming files and rewriting every inter-chapter link. Avoid unless necessary.
Writing conventions (this repo eats its own dog food)
The rules in docs/11-compressed-config.md govern this repo's own prose. When editing any .md here, follow them:
- Lead with the rule, not the reason. Fragments over sentences where natural.
- Tables for any ≥3-row structured data (see README TOC, ch. 11 cost table).
- Code blocks, shell commands, file paths, URLs, and version strings stay verbatim — compress the prose around them, not these.
- No meta-framing ("This section covers…"), no rhetoric ("this is critical"), no trailing summary paragraphs.
- One rule per line in rule lists; imperative voice.
- Size budgets per file type (from ch. 11):
CLAUDE.md<600 lines ·SKILL.md<80 · agent <50 · command <30. Chapters themselves aren't capped but aim for high info density — current chapters run ~100–400 lines.
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 · 61 lines · 858 tokens per session scan A 7e8c2a3d0b37
claude-code-bible CLAUDE.md is an instructions file published in the GitHub repository sebyx07/claude-code-bible (5 stars, last pushed 1mo ago), licensed MIT. It adds 858 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
agent-skills-standard CLAUDE.md
Claude Code instructions for HoangNguyen0403/agent-skills-standard, covering agent protocol and self-learning protocol.
openacme CLAUDE.md
Instructions for sandydasari/openacme, covering openacme — claude code guide, workspace layout, the agent loop — request path, why sse-only and custom data parts.
Alex_Skill_Mall falsifiability-deadlines.instructions.md
Every new or edited brain artefact (instruction / skill / prompt / agent) must declare a specific falsification deadline — a literal date, an observable event, or count+time bound — not 'after N passes' or 'when conditions warrant'.
Alex_Skill_Mall mall-maintenance-rules.instructions.md
Always-on routing for Mall maintenance work — fires the right Mall skill at the right moment. Distinguishes Mall-owned automation from out-of-scope editorial work.
Alex_Skill_Mall lint-discipline.instructions.md
Fix lint always — if I edited a file, I own its lint state on exit, even for pre-existing findings.
swarm-357 CLAUDE.md
Instructions for TechTideOhio/swarm-357, covering claude.md, what this repo is, python package (packages/techtide-swarm/), or from pypi and key classes.