Borrowing it
Nothing to install: this file belongs to pjt222/agent-almanac. 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/pjt222/agent-almanac/main/CLAUDE.mdgit clone --depth 1 https://github.com/pjt222/agent-almanacWrote 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/pjt222/agent-almanac/claude-md)<a href="https://agentmods.dev/instructions/pjt222/agent-almanac/claude-md"><img src="https://agentmods.dev/badge/instructions/pjt222/agent-almanac/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.
<a href="https://agentmods.dev/instructions/pjt222/agent-almanac/claude-md"><img src="https://agentmods.dev/badge/instructions/pjt222/agent-almanac/claude-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 | $0.19041 | $0.19041 |
| Opus 5.5 | $0.07616 | $0.07616 |
| Sonnet 5.5 | $0.03808 | $0.03808 |
| Haiku 4.5 | $0.01904 | $0.01904 |
Grade C, and why
agent-almanac CLAUDE.md scanned grade C with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
Agents that may run shell commands should also carry the `REPO_SAFETY` preamble from `workflows/_template.mjs` — `mktemp -d` rather than a shared path, `cd "${DIR:?}" || exit 1`, a **braced absolute path under that direc How it starts
The opening of the file, as written. The whole thing — 796 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.
Project Overview
A documentation-first repository containing 36 guides, a skills library of 374 agentic skills, 76 agent definitions, 22 team compositions, and a curated set of code-driven workflow orchestration scripts, following the Agent Skills open standard. Almost all content is markdown and YAML; workflows are self-contained .mjs scripts run by Claude Code's Workflow tool.
The guides serve as the human entry point to the agentic system: practical walkthroughs explaining when, why, and how to interact with agents, teams, skills, and workflows through Claude Code.
Architecture
Five Content Types
-
Guides (
guides/directory): Human-readable documentation organized into five categories (workflow, infrastructure, reference, design, investigation). Each guide has YAML frontmatter (title,description,category,agents,teams,skills) and follows a standard template (guides/_template.md). Guides serve as the human entry point to the agentic system. -
Skills (
skills/directory): Machine-consumable structured procedures that agentic systems execute. Each skill lives atskills/<skill-name>/SKILL.mdwith YAML frontmatter (name,description,allowed-tools,metadata) and standardized sections (When to Use, Inputs, Procedure, Validation, Common Pitfalls, Related Skills). Skills are organized into logical domains via metadata tags (live count in the auto-generated registries section below), but the directory structure is flat. -
Agents (
agents/directory): Persona definitions for Claude Code subagents. Each agent is a markdown file with YAML frontmatter (name,description,tools,model,priority) defining who handles a task. Agents span development, compliance, review, project management, DevOps, MLOps, workflow visualization, esoteric, and specialty domains.
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.
- yesterday Changed dd019d6bdb57
- 5d ago Changed · +49 tokens per session 5f5a446d80f1
- 14d ago Changed · +29 tokens per session 4b510e06f467
- 16d ago Changed · +26 lines · +605 tokens per session 73e73a5c62a9
- 19d ago Changed · +5 lines · +272 tokens per session b65e0e7df834
- 1mo ago Changed · +19 tokens per session 84429a4ee023
- 1mo ago Changed · +35 lines · +587 tokens per session 0862a2dc5974
- 1mo ago Changed · +1 lines · +80 tokens per session 18af708392fd
- 1mo ago Changed · +2 lines · +139 tokens per session 9a11b003b974
- 1mo ago First seen · 727 lines · 17,261 tokens per session scan C c06680ee76ee
agent-almanac CLAUDE.md is an instructions file published in the GitHub repository pjt222/agent-almanac (42 stars, last pushed today), licensed MIT. It adds 19,041 tokens to every session, about $0.0762 per session on Opus 5.5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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 copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.