ccf-build-and-env

ccf-build-and-env is a skill for Claude Code, Codex from BostonOrange/claude-code-framework. It costs 144 tokens per session (3,239 once invoked), scanned B, original, MIT.

Setup and environment guidance for developing the claude-code-framework repository itself. It explains how to clone the project, check required tools, and run its test suite.

In plain words
What is it for?
Use it on a new machine or fresh clone, when checking whether the repository environment works, or when local and CI test results disagree.
Why use it?
It helps distinguish a real code problem from a missing tool or difference between local development and continuous integration, the automated build system.

Skill for Claude CodeCodex

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 skills/bostonorange/claude-code-framework/ccf-build-and-env
Any agent
npx skills add BostonOrange/claude-code-framework --skill ccf-build-and-env
Clone the repo
git clone --depth 1 https://github.com/BostonOrange/claude-code-framework

Made for: Claude Code, Codex.

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-build-and-env

README.md
[![agentmods](https://agentmods.dev/badge/skills/bostonorange/claude-code-framework/ccf-build-and-env.svg)](https://agentmods.dev/skills/bostonorange/claude-code-framework/ccf-build-and-env)
Your own site
<a href="https://agentmods.dev/skills/bostonorange/claude-code-framework/ccf-build-and-env"><img src="https://agentmods.dev/badge/skills/bostonorange/claude-code-framework/ccf-build-and-env.svg" alt="Measured on agentmods" height="20"></a>
Per session 144 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,239 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 2 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 5.1 $0.00144 $0.03239
Opus 5 $0.00072 $0.01620
Sonnet 5 $0.00029 $0.00648
Haiku 4.5 $0.00014 $0.00324

Measured 5d ago against content hash 53c7bdc92eb0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade B, and why

ccf-build-and-env scanned grade B with 2 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

grep -r "{{" .claude/ CLAUDE.md | grep -v ".git" # must print nothing

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

| jq, sqlite3, curl (optional) | Only `templates/hooks/codebase-index.sh` at *target-project* runtime | `command -v jq sqlite3 curl` | Framework tests never invoke that hook; you only need these to exercise it manually (
.claude/skills/ccf-build-and-env/SKILL.md · 136 lines

How it starts

The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CCF Build & Environment

Usage

Load this skill when you need a working development environment for this repo (the framework itself): first clone, new machine, or proving your environment is healthy before/after changes. Also load it when a "works here, fails there" symptom smells environmental (missing python3, missing pwsh, macOS-vs-Linux tooling).

Do NOT use this skill for:

  • What each test gates or how to extend the suite → ccf-testing-and-qa
  • setup.sh/setup.ps1 flags, CCF_* variables, install/rollback into target projects → ccf-release-and-install
  • Why .claude/ differs from templates/ and the drift allowlist → ccf-dogfood-and-drift
  • A failing check's design intent → ccf-architecture-contract

Process: clone to verified

There is no build step. "Environment works" means the test suite passes.

git clone https://github.com/BostonOrange/claude-code-framework.git
cd claude-code-framework
python3 --version   # MUST print a version — see Trap 2 before trusting a green suite without it
bash tests/run-all.sh

Expected tail of step 4 on a clean clone (verified 2026-07-11):

RESULT: ALL TESTS PASSED (8 of 8)

Anything else: match the failing check name against ccf-testing-and-qa (what it gates) and ccf-debugging-playbook (triage). One known-benign case: check-dogfood-drift fails whenever you have untracked files under .claude/ (see Trap 3).

What this repo is

claude-code-framework is markdown + bash + PowerShell + JSON. There is nothing to compile, no npm install, no virtualenv, no lockfile to restore for framework work. The vendored app template templates/internal-nextjs-business-app/ contains a package-lock.json, but it is payload that setup.sh copies into target projects — you never install its dependencies to develop the framework (the only npm install string in setup.sh is documentation text it generates for target projects, line ~593). Full vocabulary/object model: ccf-domain-reference.

Read the full file on GitHub · 136 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 · 136 lines · 144 tokens per session scan B 53c7bdc92eb0

Subscribe to this mod's changes

ccf-build-and-env is a skill published in the GitHub repository BostonOrange/claude-code-framework (2 stars, last pushed 1mo ago), licensed MIT. It adds 144 tokens to every session and 3,239 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it B with 2 findings (reads agent configuration directories, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens