agentmods.dev

ccf CLAUDE.md

ccf CLAUDE.md is an instructions file for coding agents from naniiluja/ccf. It costs 2,692 tokens per session, scanned A, original, MIT.

Project instructions for CCF, a Claude Code plugin that makes the coding agent work from written plans and context in a strict order. The plugin consists of prompts, helper agents, hooks, templates, and distribution files rather than a running web application.

In plain words
What is it for?
Planning changes, maintaining the plugin specification, updating its commands and hooks, and preparing its marketplace package.
Why use it?
They explain the repository's structure and rules so changes follow the plugin's workflow and do not treat it like an ordinary app.

Instructions file

Installs and runs on its own, but its text points at files inside the plugin that ships it — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed.

not rated 9 25d ago A scan 2,692 tokens original MIT
View the source file naniiluja/ccf
Install

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.

agentmods
npx agentmods add instructions/naniiluja/ccf/claude-md
Clone the repo
git clone --depth 1 https://github.com/naniiluja/ccf

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 ccf CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/naniiluja/ccf/claude-md.svg)](https://agentmods.dev/instructions/naniiluja/ccf/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/naniiluja/ccf/claude-md"><img src="https://agentmods.dev/badge/instructions/naniiluja/ccf/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,692 This file is loaded in full into every session.
When invoked 2,692 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.02692 $0.02692
Opus 5 $0.01346 $0.01346
Sonnet 5 $0.00538 $0.00538
Haiku 4.5 $0.00269 $0.00269

Measured 5d ago against content hash 5c2639f31e99, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ccf 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 5d 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 · 58 lines

How it starts

The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CCF — Claude Context First (plugin source)

Managed by CCF. This project IS the source code of the CCF plugin — not an app with a DB/API/frontend. STRICTLY SEQUENTIAL: one change at a time, no parallel work on multiple things. Ground every decision about Claude Code's schema/contract in the official docs (via Context7) before writing. Keep this spec always fresh with /ccf:updatespec.

What this is

CCF is a Claude Code plugin that imposes a context-first, spec-driven, strictly sequential workflow. It has NO application runtime (no server, DB, API, UI). The entire "product" is the artifacts Claude Code loads: commands (markdown prompts), agents/subagents (markdown), hooks (.mjs scripts run by node), templates for /ccf:init to instantiate, plus distribution manifests. Users install via a marketplace, then run /ccf:* (e.g. /ccf:plan).

Repo layout

  • git init at the root (D:/projects/ccf). The root holds CLAUDE.md, .claude/, package.json, tsconfig.json, bin/, README.md, LICENSE, .claude-plugin/marketplace.json.
  • plugins/ccf/ — the plugin itself. .claude-plugin/plugin.json is the manifest (ONLY the manifest goes in .claude-plugin/); the component directories live at the plugin root:
    • commands/*.md — 6 slash commands (init, plan, check, fix, updatespec, cook; invoked via the plugin namespace, e.g. /ccf:plan).
    • agents/*.md — 6 subagents (ccf-codebase-analyzer, ccf-best-practice-researcher, ccf-implementer, ccf-spec-writer, ccf-spec-checker, ccf-debugger).
    • skills/grill-me/SKILL.md — 1 internal skill: the shared requirements-interview engine invoked by /ccf:plan//ccf:fix//ccf:init (user-invocable: false; hidden from the / menu).
    • hooks/*.mjs + hooks/hooks.json + hooks/lib/ — 9 hooks (plan-mode-guard, plan-review-gate, session-start, updatespec-nudge — advisory Stop nudges, auto-verify — an opt-in --auto-verify Stop hook that BLOCKS via decision:"block" to drive the verify chain when a task is in-review and code changed this session, context-guard — warns/optionally hard-blocks on UserPromptSubmit when context enters the degrade zone — agent-rules-inject, which on SubagentStart injects the project coding rules + active output style's coding rules into spawned ccf-implementer subagents, explore-guide-inject, which on SubagentStart (matcher Explore) injects a language-agnostic LSP/Grep/Glob exploration directive into the built-in Explore subagent, and implementer-verify-gate — an opt-in --enforce-tests SubagentStop hook (matcher ccf-implementer) that BLOCKS via decision:"block" when a spawned implementer's final message carries no TEST-RESULT: evidence) sharing lib/io.mjs (+ lib/freshness.mjs, lib/plan.mjs, lib/context-usage.mjs, lib/review-trace.mjs, lib/git-trace.mjs, lib/verify-trace.mjs, lib/verify-chain.mjs, lib/output-style.mjs, lib/explore-guide.mjs, lib/implementer-verify.mjs).
    • scripts/archive-plan.mjs — 1 human-run CLI (not a hook, not a command; nothing invokes it automatically). Retires a fully-closed iteration out of PLAN.md into ARCHIVE.md. File-MUTATING actions belong here, never in a hook — see @.claude/rules/architecture.md.
    • templates/{root,backend,frontend}/** — *.tmpl files with {{...}} placeholders for /ccf:init to instantiate.
    • .mcp.json — bundles 2 remote MCP servers (microsoft-learn, context7).
  • bin/ccf-bootstrap.mjs — the npx entry; only shells out to the claude plugin CLI, writes no files itself.

Read the full file on GitHub · 58 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. 5d ago First seen · 58 lines · 2,692 tokens per session scan A 5c2639f31e99

Subscribe to this mod's changes

ccf CLAUDE.md is an instructions file published in the GitHub repository naniiluja/ccf (9 stars, last pushed 25d ago), licensed MIT. It adds 2,692 tokens to every session, about $0.0135 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.

Building agentsagentic-engineeringai-workflowanthropicclaudeclaude-codeclaude-code-plugin
Related

Other instructions, from other repositories

coco-workflow CLAUDE.md

Instructions for skullninja/coco-workflow, covering claude.md -- coco, project overview, architecture, key files and tracker (lib/tracker.sh).

skullninja/coco-workflow · 7,598 tokens

oh-my-pm AGENTS.md

Instructions for kelegele/oh-my-pm, covering agents.md, commands, run skill structure + contract tests (fast, no model calls), install plugin from github and install plugin from a local checkout.

kelegele/oh-my-pm · 4,467 tokens

erpaval CLAUDE.md

Instructions for theagenticguy/erpaval, covering erpaval-plugin, repo structure, version management, tools and hooks.

theagenticguy/erpaval · 562 tokens

forge-skills AGENTS.md

AGENTS.md instructions for aneja5/forge-skills, covering agents.md, core rules, intent → skill mapping, define & specify and design.

aneja5/forge-skills · 3,107 tokens

SoDam-Agentic-Eng AGENTS.md

AGENTS.md instructions for sodam-ai/SoDam-Agentic-Eng, covering sodamagentic — ai 지침 (agents.md), 이 플러그인의 목적, 스킬·커맨드 목록, ai가 반드시 할 것 and ai가 절대 하지 말 것.

sodam-ai/SoDam-Agentic-Eng · 1,176 tokens

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