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/shanraisshan/claude-code-best-practice/claude-mdgit clone --depth 1 https://github.com/shanraisshan/claude-code-best-practiceWhat 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 | $0.01830 | $0.01830 |
| Opus 5 | $0.00915 | $0.00915 |
| Sonnet 5 | $0.00366 | $0.00366 |
| Haiku 4.5 | $0.00183 | $0.00183 |
Grade B, and why
claude-code-best-practice CLAUDE.md scanned grade B 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 2d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
5. `~/.claude/settings.json`: Global personal defaults Copies of this mod
1 near-identical copy found in the catalogue:
- claude-code-best-practice-zh CLAUDE.md — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 127 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.
Repository Overview
This is a best practices repository for Claude Code configuration, demonstrating patterns for skills, subagents, hooks, and commands. It serves as a reference implementation rather than an application codebase.
Key Components
Weather System (Example Workflow)
A demonstration of two distinct skill patterns via the Command → Agent → Skill architecture:
/weather-orchestratorcommand (.claude/commands/weather-orchestrator.md): Entry point — asks user for C/F, invokes agent, then invokes SVG skillweather-agentagent (.claude/agents/weather-agent.md): Fetches temperature using its preloadedweather-fetcherskill (agent skill pattern)weather-fetcherskill (.claude/skills/weather-fetcher/SKILL.md): Preloaded into agent — instructions for fetching temperature from Open-Meteoweather-svg-creatorskill (.claude/skills/weather-svg-creator/SKILL.md): Skill — creates SVG weather card, writesorchestration-workflow/weather.svgandorchestration-workflow/output.md
Two skill patterns: agent skills (preloaded via skills: field) vs skills (invoked via Skill tool). See orchestration-workflow/orchestration-workflow.md for the complete flow diagram.
Skill Definition Structure
Skills in .claude/skills/<name>/SKILL.md use YAML frontmatter:
name: Display name and/slash-command(defaults to directory name)description: When to invoke (recommended for auto-discovery)argument-hint: Autocomplete hint (e.g.,[issue-number])disable-model-invocation: Settrueto prevent automatic invocationuser-invocable: Setfalseto hide from/menu (background knowledge only)allowed-tools: Tools allowed without permission prompts when skill is activemodel: Model to use when skill is activecontext: Set toforkto run in isolated subagent contextagent: Subagent type forcontext: fork(default:general-purpose)hooks: Lifecycle hooks scoped to this skill
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.
- 2d ago First seen · 127 lines · 1,830 tokens per session scan B 9f9a7f3e400b
claude-code-best-practice CLAUDE.md is an instructions file published in the GitHub repository shanraisshan/claude-code-best-practice (65,460 stars, last pushed today), licensed MIT. It adds 1,830 tokens to every session, about $0.0092 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
codex-cli-best-practice AGENTS.md
Instructions for shanraisshan/codex-cli-best-practice, covering agents.md, what this is, architecture, orchestration flow and key directories.
claude-code-hooks CLAUDE.md
Instructions for shanraisshan/claude-code-hooks, covering claude code hooks, project structure, critical: hook count consistency, agent hooks and workflows.
codex-cli-hooks CLAUDE.md
Claude Code instructions for shanraisshan/codex-cli-hooks, covering claude.md / agents.md, what this repo is, common commands, run a single test and manually invoke a hook (what codex does internally).
codex-cli-hooks AGENTS.md
AGENTS.md instructions for shanraisshan/codex-cli-hooks, a project described as: codex cli hooks - adding voice on each hook.
codex-cli-best-practice CLAUDE.md
Instructions for shanraisshan/codex-cli-best-practice, covering claude.md, what this is, architecture, orchestration flow and key directories.
claude-code-tresor CLAUDE.md
Instructions for alirezarezvani/claude-code-tresor, covering claude.md - development guide, 🎯 repository purpose, 🏗️ architecture, 🛠️ common development commands and building & testing.