agentmods.dev

prompt-guide: Instructions file for Claude Code

CLAUDE.md

prompt-guide CLAUDE.md is an instructions file for Claude Code from pelagornis/prompt-guide. It costs 490 tokens per session, scanned A, original, MIT.

A guide for organizing layered Markdown instructions for coding tools such as Claude Code, Cursor, and Codex. A configuration file and manifest control which instruction layers are combined and in what order.

In plain words
What is it for?
Use it to configure instruction layers, define review guidance, set task presets, and copy shared rules into tool-specific directories.
Why use it?
It keeps project guidance short, modular, and easier to maintain than one large instruction file. The same source layout can be installed for different coding tools.

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 pelagornis/prompt-guide's own configuration. It tells Claude Code how to work on prompt-guide 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 prompt-guide configures →

not rated 2repo 2mo ago A scan 490 tokens original MIT
View source ↗ pelagornis/prompt-guide
Reuse

Borrowing it

Nothing to install: this file belongs to pelagornis/prompt-guide. 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/pelagornis/prompt-guide/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/pelagornis/prompt-guide

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 prompt-guide CLAUDE.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/pelagornis/prompt-guide/claude-md"><img src="https://agentmods.dev/badge/instructions/pelagornis/prompt-guide/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 490 This file is loaded in full into every session.
When invoked 490 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 $0.00490 $0.00490
Opus 5.5 $0.00196 $0.00196
Sonnet 5.5 $0.00098 $0.00098
Haiku 4.5 $0.00049 $0.00049

Measured 2mo ago against content hash 06a3acaa36ba, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

prompt-guide 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 · 27 lines

What it actually says

Project instructions (Claude Code)

This repository uses prompt-guide: layered Markdown, a single prompt.config.js, and layers.manifest.yml (merge order for bundles).

What to read first

  1. prompt.config.js — tool, platform, layers.source, layers.manifest, context, task presets.
  2. layers.manifest.yml (repo root) — ordered system: paths relative to layers.source; review.path for review mode.
  3. Layer tree under layers.source (default .claude/) — init copies the same layout to .cursor/, .claude/, codex/ (no …/ai/ subfolder).

Prefer opening those Markdown files over assuming a single monolithic instruction block.

After prompt-guide install with tool: 'claude'

  • .claude/rules/ai-core.md — system bundle from the manifest.
  • .claude/rules/ai-review.md — review bundle.

Keep this file short (Anthropic recommends concise project instructions); put detail in .claude/ (Markdown tree) and prompts/.

Conventions this template follows

  • Cursor / IDE agents: version-controlled rules under .cursor/rules/, small composable .mdc / .md files with YAML frontmatter where applicable (Cursor docs — Rules).
  • Codex / similar: AGENTS.md at the project root when using tool: 'codex' (common pattern for repo-level agent instructions).
  • Claude Code: root CLAUDE.md plus optional .claude/rules/*.md (Claude Code best practices).

Regenerate tool outputs when you change tool in prompt-guide install; edit .claude/ Markdown and layers.manifest.yml without reinstalling for file-based tools (Cursor).

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 · 27 lines · 490 tokens per session scan A 06a3acaa36ba

Subscribe to this mod's changes

prompt-guide CLAUDE.md is an instructions file published in the GitHub repository pelagornis/prompt-guide (2 stars, last pushed 2mo ago), licensed MIT. It adds 490 tokens to every session, about $0.0020 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.

Building agentsclipelagornispromptprompt-guide
Related

prompt-guide CLAUDE.md compared with instructions from other repositories

prompt-guide CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
prompt-guide CLAUDE.mdpelagornis/prompt-guideInstructions file22mo agoMITA490Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,516GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,093GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA2,022GitHub Copilot