Is the Code Intelligence skill free?

Yes. The skill itself is free from antonbabenko/agent-plugins. SkillProof publishes the install command and an independent test verdict at no cost.

What is the Code Intelligence SkillProof Score?

9.6/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 9/10, docs & honesty 5/5.

How do I install Code Intelligence?

Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.

Can I use Code Intelligence with Cursor, Copilot, Gemini CLI, Codex or other AI tools?

The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.

Code Intelligence

Disciplined LSP-vs-rg-vs-fuzzy search precedence with position-anchoring and forced disclosure of tool substitutions.

by antonbabenko · antonbabenko/agent-plugins

Tested · Works

Install — copy the command Download source ↗

Test report

Verdict: Tested · Works
Score: 9.6/10
Tested: Jul 14, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Aug 10, 2026 · ad4d284

Ran the repo's own 'rename parseConfig' test scenario on a real 3-file Go fixture: a naive blind sed replace (baseline) corrupted a string literal value and an unrelated identifier (parseConfigDeprecatedAlias); following the skill's discipline renamed only the true definition and call site and left the ambiguous comment/string mentions untouched for review - the exact failure mode the skill exists to prevent, reproduced and fixed live.

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

Installs cleanly 5/5
Triggers reliably 5/5
Output vs. baseline 9/10
Docs & honesty 5/5

What Code Intelligence does

Language-agnostic guidance for choosing between a language server (symbol relationships, safe renames), exact-text search (rg, literals/config), and fuzzy/semantic search (conceptual discovery) - including position-anchoring LSP calls, a 3-part degradation gate before falling back to text search, and a mandatory first-line disclosure format for any tool substitution. Triggers when navigating or refactoring code, choosing a search tool, or handling a degraded/unavailable language server.

How to install Code Intelligence

git clone https://github.com/antonbabenko/agent-plugins
cd agent-plugins
mkdir -p ~/.claude/skills
cp -r plugins/code-intelligence/skills/code-intelligence ~/.claude/skills/code-intelligence

Skills live in ~/.claude/skills/ (global) or .claude/skills/ (per-project). Restart Claude Code after installing.

Commands — how to trigger Code Intelligence

/code-intelligence Disciplined LSP-vs-rg-vs-fuzzy search precedence with position-anchoring and forced disclosure of tool substitutions.

It also activates on plain-language prompts like these:

Rename parseConfig to loadConfig everywhere it's used
Find every reference to this function before I refactor it
Trace all call sites of this class across the codebase

Frequently asked questions

Is the Code Intelligence skill free?: Yes. The skill itself is free from antonbabenko/agent-plugins. SkillProof publishes the install command and an independent test verdict at no cost.
Does Code Intelligence work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 14, 2026. Verdict: Tested · Works. Ran the repo's own 'rename parseConfig' test scenario on a real 3-file Go fixture: a naive blind sed replace (baseline) corrupted a string literal value and an unrelated identifier (parseConfigDeprecatedAlias); following the skill's discipline renamed only the true definition and call site and left the ambiguous comment/string mentions untouched for review - the exact failure mode the skill exists to prevent, reproduced and fixed live.
What is the Code Intelligence SkillProof Score?: 9.6/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 9/10, docs & honesty 5/5.
How do I install Code Intelligence?: Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use Code Intelligence with Cursor, Copilot, Gemini CLI, Codex or other AI tools?: The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.