Repoframe — AI skill for Claude Code
Prepare repositories for AI coding agents: analyze, plan with Claude, verify with evidence.
How to install Repoframe
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open felixsc321-hub/repoframe and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Repoframe does
Prepare repositories for AI coding agents: analyze, plan with Claude, verify with evidence.
Alternatives in AI
- Fact Checker — Verify claims and facts with sources 653 ★
- Claude Hub — by Claude Did This - A webhook service that connects Claude Code to GitHub repositories, enabling AI-powered c 393 ★
- Fable Soul — A judgment layer for AI coding agents - make your AI think, verify, and communicate like a senior engineer 106 ★
README
RepoFrame
Prepare repositories for AI coding agents. **Analyze. Plan. Verify.**
Website: [repoframe.com](https://repoframe.com)
[](https://github.com/felixsc321-hub/repoframe/actions/workflows/ci.yml) [](LICENSE) 
**Early alpha.** The core loop (analyze, plan, verify) works and is tested on Linux and Windows. The Claude API integration (`ClaudeProvider`) is implemented and unit-tested with a fake provider, but **has not been exercised against the live API in this release**. The manual `--prompt-only` / `--from-reply` flow, which uses the same prompts, has been used end to end. RepoFrame is under continuous development, and testing against the live API is on the roadmap.
RepoFrame gives a coding agent clean context before it works, an implementable plan while it works, and objective verification after it finishes. It does not replace Codex, Claude Code or Gemini CLI; it wraps them.
repoframe analyze -> repoframe plan "" -> [your coding agent] -> repoframe verify
local, no AI Claude writes the plan Claude Code, Codex, tests + git diff,
Gemini, or a person evidence over opinion
Built for Claude
Claude is RepoFrame's reference reasoning engine. The `plan` step is where it matters: RepoFrame selects a small, structured slice of the repository, builds the prompt, and asks Claude for a precise plan (steps, files to touch, constraints, acceptance criteria, validation commands). Everything else is deterministic and local.
- With the Claude API: set
ANTHROPIC_API_KEYand runrepoframe plan "". - With a Claude subscription (no API key):
repoframe plan "" --prompt-onlywrites a r
Related Skills
Engineering Verification Skill
A portable protocol that makes AI coding agents investigate, verify and safely change existing repositories li
Codevetter
Verify AI-generated code with execution evidence — deterministic, local-first verification for coding-agent ch
Agentic Engineering Protocol
Verification-driven operating protocol for AI coding agents - Explore/Plan/Implement/Verify/Deliver with adver
Askproof Skill
Verify AI agent output with actionable evidence for non-engineers. Build better prompts by auditing AI claims
AI Loop Skill
Your agent says "done" and it is not. A gated multi-agent circuit for Claude Code: whoever implements does not
Research Toolkit
Reusable commands for structured AI-assisted research workflows. Plan-Construct-Verify (PCV), Council of Agent
Related Agents
Glm Agent
Runs Z.AI GLM on the user's GLM Coding Plan. Three modes - consult (direct API call, 1M context, for inputs to
Sub-Agent Refactor Command
A powerful refactoring orchestrator that uses multiple specialized sub-agents to analyze, plan, implement, and
Akinator PM
Use at plan and verify stations to check batch discipline and completion honesty. Reviews whether batches are