AgentConfigScore — AI skill for Claude Code
Tamper-resistant regression gate for AI coding-agent instructions—AGENTS.md, CLAUDE.md, Cursor, Copilot, Gemini, and more.
How to install AgentConfigScore
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open LE0-Lin/AgentConfigScore and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What AgentConfigScore does
Tamper-resistant regression gate for AI coding-agent instructions—AGENTS.md, CLAUDE.md, Cursor, Copilot, Gemini, and more.
Alternatives in AI
- CLI Continues — resume any AI coding session in another tool — Claude Code, Copilot, Gemini, Codex, Cursor 1.5k ★
- Snip — CLI proxy that reduces LLM token usage by 60-90% 425 ★
- Kindly Web Search MCP Server — Kindly Web Search MCP Server: Web search + robust content retrieval for AI coding tools (Claude Code, Codex, C 377 ★
README
AgentConfigScore
Codecov for AI coding-agent instructions.
Stop pull requests from quietly making AGENTS.md, CLAUDE.md, Cursor, Copilot and Gemini instructions worse.
AgentConfigScore is a deterministic regression gate for coding-agent configuration. It compares a change with its baseline and answers one CI-friendly question:
**Did this change make our agent instructions worse?**
It is regression-first rather than perfection-first: an existing repository can start at 72/100 and adopt the gate immediately. A pull request that stays at 72 can pass; one that drops to 65 can fail.
| What usually goes wrong | What the gate does |
|---|---|
| A pull request weakens its own quality threshold | Uses the baseline branch's policy to judge the change |
| A new instruction contradicts or duplicates existing guidance | Reports deterministic, line-addressable findings |
| An exception becomes a permanent silent ignore | Requires a reason and expiry, then preserves an audit trail |
| A scanner update becomes noisy on real projects | Replays a pinned, manually reviewed real-repository benchmark |
Get running
python -m pip install "git+https://githubRelated Skills
AgentBridge
Migrate AI coding agent config between 12 agents — Claude Code, Codex, Copilot, Cursor, Gemini, Crush, Grok, o
Agentsync
One source of truth for all your AI coding agent rule files. Sync AGENTS.md, CLAUDE.md, .cursorrules, copilot-
Omnigento
Keep AI coding-agent instructions consistent across Cursor, Claude, Copilot, Codex, and AGENTS.md. One canonic
AI Context Kit
Lint, measure, and manage context files for AI coding agents. Cursor rules, CLAUDE.md, AGENTS.md, Copilot inst
Scavi
Context linter for AI coding agents. Detects stale, conflicting, and incorrect instructions across AGENTS.md,
Agent Rules Lint
Lint AGENTS.md, CLAUDE.md, Cursor rules, and Copilot instructions for safer AI coding agents
Related Agents
Prompt Polisher
Analyzes AI prompt files (.claude/agents/.md, .claude/skills//.md, .agents/skills//.md, CLAUDE.md, AGENTS.md,
Developer Overview
code-container (container) creates isolated Docker environments for AI coding harnesses (Claude Code, OpenCode
