docs: Instructions file for Claude Code

CLAUDE.md

docs CLAUDE.md is an instructions file for Claude Code from project-kessel/docs. It costs 1,568 tokens per session, scanned A, original, Apache-2.0.

A set of instructions for developing and publishing the project-kessel documentation website. The site uses Astro and Starlight, tools for building documentation websites.

In plain words
What is it for?
Use it when editing the documentation site, running its development or production build, placing content, or preparing changes for commit.
Why use it?
It defines the commands, checks, content boundaries, and commit requirements needed to keep the documentation site buildable and appropriately scoped.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code; mentions AGENTS.md.

This is project-kessel/docs's own configuration. It tells Claude Code how to work on docs itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything docs configures →

Reuse

Borrowing it

Nothing to install: this file belongs to project-kessel/docs. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/project-kessel/docs/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/project-kessel/docs

Made for: Claude Code.

Wrote 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.

agentmods badge for docs CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/project-kessel/docs/claude-md/github.svg)](https://agentmods.dev/instructions/project-kessel/docs/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/project-kessel/docs/claude-md"><img src="https://agentmods.dev/badge/instructions/project-kessel/docs/claude-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.

agentmods 80×15 button for docs CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/project-kessel/docs/claude-md"><img src="https://agentmods.dev/badge/instructions/project-kessel/docs/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,568 This file is loaded in full into every session.
When invoked 1,568 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01568 $0.01568
Opus 5.5 $0.00627 $0.00627
Sonnet 5.5 $0.00314 $0.00314
Haiku 4.5 $0.00157 $0.00157

Measured 2mo ago against content hash b4e5c5f3bdeb, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

docs 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 2mo 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.

CLAUDE.md · 88 lines

How it starts

The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Claude Code Configuration

@AGENTS.md

Build and Development Commands

This is an Astro/Starlight documentation site. When working in this repository:

Development workflow

  • Start dev server: npm run dev (serves at localhost:4321)
  • Build the site: npm run build (runs astro check && astro build, outputs to ./dist/)
  • Preview build: npm run preview (preview the built site locally)

Before committing

  • Always run npm run build to verify TypeScript checks and build pass
  • The CI pipeline runs astro check && astro build - your changes must pass this
  • If you get TypeScript errors, the build will fail - fix them before committing

Pre-commit hooks

This repository uses rh-multi-pre-commit for Red Hat security scanning. The hook runs automatically on commit. If you encounter hook failures unrelated to your changes, notify the team.

Claude Code Behavioral Preferences

Content placement

  • This repository is for public Kessel documentation only
  • Internal Red Hat-specific content (onboarding, hosted config, runbooks, monitoring) belongs in the separate internal docs repo published to InScope
  • Do not add Red Hat-specific operational content to this repository

Content creation

  • Use .mdx for pages needing Astro components (Aside, Tabs, CodeExamples, etc.)
  • Use .md for pure Markdown content
  • All frontmatter must include at minimum: title and description
  • Follow the Diataxis framework - know if you're writing tutorial, how-to, explanation, or reference

Code examples

  • Examples live in src/examples/ organized by topic
  • Use region markers for selective inclusion:
    • C-style languages (Go, TS, Java): //#region name and //#endregion
    • Hash-style languages (Python, Ruby, Bash): # region name and # endregion
  • All important code including error handling must be inside regions

TypeScript

  • Strict mode is enforced via astro/tsconfigs/strict
  • Path alias src/* maps to ./src/*
  • Zod schemas use .optional().default(false) for boolean fields - maintain this pattern

Read the full file on GitHub · 88 lines

Changes

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.

  1. 2mo ago First seen · 88 lines · 1,568 tokens per session scan A b4e5c5f3bdeb

Subscribe to this mod's changes

docs CLAUDE.md is an instructions file published in the GitHub repository project-kessel/docs (2 stars, last pushed today), licensed Apache-2.0. It adds 1,568 tokens to every session, about $0.0063 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 2026-08-31.

Related

docs CLAUDE.md compared with instructions from other repositories

docs CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
docs CLAUDE.mdproject-kessel/docsInstructions file2todayApache-2.0A1,568Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,516GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file275k3d agoMITA4,313Codex, OpenCode