What is install-framework?

A setup tool that installs the Claude Code Framework into the repository you are currently working in. It clones the framework from GitHub and runs its installer for your operating system.

Use it when a repository does not yet contain the Claude Code Framework. It requires Git, and macOS or Linux also require Python 3.

It removes the manual work of finding, cloning, and installing the framework. It also checks whether the framework is already present before changing files.

install-framework — Skill by BostonOrange

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/install-framework

Any agent

npx skills add BostonOrange/claude-code-framework --skill install-framework

Clone the repo

git clone --depth 1 https://github.com/BostonOrange/claude-code-framework

Made for: Claude Code, Codex.

Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,385 The whole file, excluding the scripts and references it only reads on demand.

Security scan D 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.

Model	Per session	Once invoked
Fable 5	$0.00048	$0.01385
Opus 5	$0.00024	$0.00692
Sonnet 5	$0.00010	$0.00277
Haiku 4.5	$0.00005	$0.00138

Measured yesterday against content hash 43f2d1f40f0e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade D, and why

install-framework scanned grade D 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 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.

Reads agent configuration directoriesmediumAgent snooping

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

grep -R "{{[A-Z_][A-Z_]*}}" CLAUDE.md .claude 2>/dev/null | grep -v ".claude/state" | grep -v ".claude/skills/improve/SKILL.md"

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

Delete the temp clone (`rm -rf "$TMP"` / `Remove-Item -Recurse -Force $TMP`). Always run cleanup,

global-skills/install-framework/SKILL.md · 125 lines

How it starts

The opening of the file, as written. The whole thing — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Install Framework

Bootstraps the Claude Code Framework into the current working directory's repo by cloning the framework from GitHub and running its installer in non-interactive mode. Use this in a repo that does NOT yet have the framework. To refine an already-installed framework, use the per-repo /setup instead.

Framework source (clone target): https://github.com/BostonOrange/claude-code-framework.git

Process

1. Prerequisites + OS detection

Confirm git is available (git --version). If missing, stop and tell the user to install git.
Detect the OS to choose the installer:
- Windows → setup.ps1 (run with pwsh or powershell). PowerShell is required.
- macOS / Linux / Git Bash → setup.sh. It requires python3; if python3 is missing, stop and tell the user.

2. Idempotency guard

If the target repo already contains .claude/settings.local.json or .claude/state/setup-applied.md, the framework is likely already installed. Stop and ask the user whether to re-run (which overwrites template files) before continuing. Do not clobber silently.

3. Auto-detect what you can (target repo = current directory)

Project type from marker files:
- package.json with React/Next deps → react, otherwise nodejs
- requirements.txt / pyproject.toml → python
- go.mod → go
- pom.xml / build.gradle → java
- Gemfile → rails
- sfdx-project.json → salesforce
- none of the above → generic
Base branch: git symbolic-ref --short refs/remotes/origin/HEAD (strip origin/); fall back to the current branch, then main.
Short name: the repo directory's basename.

4. Collect remaining answers in chat

Confirm the detected project type, then ask (with sensible defaults) for the values you cannot detect: tracker (ado/jira/linear/github/none), CI/CD (github-actions/gitlab-ci/circleci/none), notification (slack/teams/discord/none), and — only for react/nodejs — design system (untitled-ui/shadcn/custom/none). Keep it minimal; deep configuration is /setup's job.

Read the full file on GitHub · 125 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.

yesterday First seen · 125 lines · 48 tokens per session scan D 43f2d1f40f0e

Subscribe to this mod's changes

install-framework is a skill published in the GitHub repository BostonOrange/claude-code-framework (2 stars, last pushed 1mo ago), licensed MIT. It adds 48 tokens to every session and 1,385 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it D with 2 findings (reads agent configuration directories, recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Git and workflow Languages

systematic-debugging

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

obra/superpowers · 21 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

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 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

install-framework