all-for-claudecode: Instructions file for Claude Code

CLAUDE.md

all-for-claudecode CLAUDE.md is an instructions file for Claude Code from jhlee0409/all-for-claudecode. It costs 2,058 tokens per session, scanned A, original, MIT.

Development instructions for all-for-claudecode, a Claude Code plugin that guides work through specification, planning, implementation, review, and cleanup. It uses Markdown prompts, Bash hooks, project rules, and automated linting and tests.

In plain words
What is it for?
Use them when changing its skills, hooks, project configuration, workflow, or test and quality-check commands.
Why use it?
They define the plugin's workflow, configuration format, architecture, and checks so changes fit the existing development process.

Instructions file for Claude Code

Written for Claude Code: $CLAUDE_PROJECT_DIR variable. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions subagents.

This is jhlee0409/all-for-claudecode's own configuration. It tells Claude Code how to work on all-for-claudecode 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 all-for-claudecode configures →

Reuse

Borrowing it

Nothing to install: this file belongs to jhlee0409/all-for-claudecode. 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/jhlee0409/all-for-claudecode/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/jhlee0409/all-for-claudecode

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 all-for-claudecode CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/jhlee0409/all-for-claudecode/claude-md/github.svg)](https://agentmods.dev/instructions/jhlee0409/all-for-claudecode/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/jhlee0409/all-for-claudecode/claude-md"><img src="https://agentmods.dev/badge/instructions/jhlee0409/all-for-claudecode/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 all-for-claudecode CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/jhlee0409/all-for-claudecode/claude-md"><img src="https://agentmods.dev/badge/instructions/jhlee0409/all-for-claudecode/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,058 This file is loaded in full into every session.
When invoked 2,058 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 $0.02058 $0.02058
Opus 5 $0.01029 $0.01029
Sonnet 5 $0.00412 $0.00412
Haiku 4.5 $0.00206 $0.00206

Measured 9d ago against content hash 33ae392d3ce5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

all-for-claudecode 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 9d 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 · 85 lines

How it starts

The opening of the file, as written. The whole thing — 85 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.

Build / Lint / Test

npm run lint          # shellcheck + schema validation + consistency check
npm run qa            # QA audit (hook I/O safety, test strength, UX, build integrity)
npm test              # ShellSpec BDD suite (vendor/shellspec/shellspec)
npm run test:all      # lint + qa + test combined
npm run setup:test    # install ShellSpec to vendor/shellspec/ (first-time setup)
npm run sync:cache    # sync source files to plugin cache (development only)

Single script lint: shellcheck scripts/afc-bash-guard.sh Single spec run: vendor/shellspec/shellspec spec/afc-bash-guard_spec.sh

Architecture

all-for-claudecode is a Claude Code plugin that automates the full development cycle (spec → plan → implement → review → clean) through markdown skill prompts and bash hook scripts. Project config (afc.config.md) holds CI Commands in fixed YAML format (parsed by scripts); Architecture, Code Style, and Project Context are also stored there as detailed references but are primarily delivered via .claude/rules/afc-project.md (auto-loaded by Claude Code for all conversations and sub-agents). Init auto-analyzes the project structure and generates project-local files; Setup manages the global ~/.claude/CLAUDE.md AFC routing block separately. Tasks are generated automatically at implement start from plan.md's File Change Map (no separate tasks phase). Implementation uses dependency-aware orchestration: sequential for simple tasks, parallel batch (≤5 tasks), or orchestrator-managed swarm (6+ tasks) with native TaskCreate/TaskUpdate primitives. Skill Advisor system dynamically invokes auxiliary skills (ideate, consult, architect, security, analyze, test, qa, learner) at 5 phase-boundary checkpoints (A–E) based on signal detection, with budget control (max 5 per pipeline run).

Core Layers

  • skills/ — Skill prompts with YAML frontmatter (name, description, argument-hint, allowed-tools, model, user-invocable, context). Each skill lives in skills/<name>/SKILL.md with optional reference files (progressive disclosure). Pipeline phases (spec, plan, implement, review, clean) each have standalone skills. Additional standalone utilities include consult, debug, doctor, learner, qa, research, test, analyze, architect, security, triage, issue, resolve, checkpoint, resume, principles, etc. Setup manages global CLAUDE.md configuration separately from init (project-local). Deployment tools include ideate, launch, pr-comment, release-notes.
  • agents/ — Subagents: afc-architect, afc-security (persistent memory with memory: project, security uses isolation: worktree), afc-impl-worker (ephemeral parallel worker, orchestrator-managed worktree isolation), afc-pr-analyst (PR deep analysis worker, orchestrator-managed worktree isolation for triage), 8 expert consultation agents (afc-backend-expert, afc-infra-expert, afc-pm-expert, afc-design-expert, afc-marketing-expert, afc-legal-expert, afc-appsec-expert, afc-tech-advisor — persistent memory, routed via consult skill)
  • hooks/hooks.json — Hook event declarations with handler types: command (shell scripts), prompt (LLM single-turn). Some hooks use async: true. Includes ConfigChange (settings audit), TeammateIdle (Agent Teams gate), and WorktreeCreate/WorktreeRemove (worktree lifecycle)
  • schemas/ — JSON Schema definitions (hooks.schema.json, plugin.schema.json, marketplace.schema.json) validated during npm run lint
  • scripts/ — Bash hook/utility scripts (afc-*.sh + non-afc utilities) + Node.js ESM validators (.mjs) + shared state library (afc-state.sh). Includes afc-consistency-check.sh for cross-reference validation and skill-documentation gap detection. Bash scripts follow: set -euo pipefail + trap cleanup EXIT + jq-first with grep/sed fallback
  • docs/ — Shared reference documents (critic-loop-rules.md, phase-gate-protocol.md, expert-protocol.md, learner-signals.md, skill-authoring-guide.md, agent-authoring-guide.md, context-management-harness.md, orchestration-modes.md) referenced by skills and agents. Includes domain-adapters/ subdirectory with industry-specific guardrails (fintech, ecommerce, healthcare). Single-consumer docs live inside their skill directory (e.g., skills/spec/nfr-templates.md)
  • templates/ — config template (afc.config.template.md) for CI Commands YAML + free-form sections, and project rules template (afc-project.template.md) for .claude/rules/afc-project.md (auto-loaded by Claude Code)
  • bin/cli.mjs — ESM CLI entry point (install helper)
  • .claude-plugin/ — Plugin manifest (plugin.json) and marketplace registration (marketplace.json)

Read the full file on GitHub · 85 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. 9d ago First seen · 85 lines · 2,058 tokens per session scan A 33ae392d3ce5

Subscribe to this mod's changes

all-for-claudecode CLAUDE.md is an instructions file published in the GitHub repository jhlee0409/all-for-claudecode (7 stars, last pushed 5mo ago), licensed MIT. It adds 2,058 tokens to every session, about $0.0103 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.

Related

Other instructions, from other repositories

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.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

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.

langchain-ai/langchain · 4,469 tokens

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.

deepseek-ai/deepseek-harness · 3,735 tokens