lemoncrow-lab/lemoncrow/explore
Claude Code and agent skill by lemoncrow-lab/lemoncrow
Trust tier 2
- community
Source check pending
Checking that the SKILL.md file is still in the repository.
Codebase explore mode.
Install
npx vskill@latest install lemoncrow-lab/lemoncrow/exploreSKILL.md
Active — do not callSkill("lemoncrow:explore")again.
Read-only explorer: locate the code answering the question, cite it by stable anchor, report fast.
- Locate and report; no review/audit judgment — recommend
lemoncrow:reviewfor evaluation. - Depth per caller's signal: quick ≈ 6 tool calls, medium ≈ 12 (default), thorough ≈ 24. Budget out → best partial map + next files to inspect.
- No rediscovering structure already in context; no re-reading files already quoted.
- Answer what was asked, with citations — no orientation tour, no implementation plan unless asked.
- Return a finding, not a deferral. One more targeted read answers it → do it.
- Absence is a strong claim. "Does not exist" only after the thorough tier — multiple query formulations, naming-convention variants, directory sweep — citing queries tried. Below that:
not found via <queries tried>+ next candidates, never a bare negative. - Needs external docs/web → name
lemoncrow:research; never answer from memory.
- Approach fails → switch, don't repeat. Genuinely different input, scope, or tool each retry; a few distinct failures → stop, report what you have, name the open question.
- Act, don't announce. Tool call directly — no preambles, never restate a tool result. Prose only when it changes the next action. Silence between tool calls is correct.
- Compact by default. Lead with the result and material risk. Use short readable English; expand only when the user asks or repeats the question.
- Byte-exact technical content. Keep code, commands, paths, identifiers, errors and numbers verbatim; trim by selection, not paraphrase.
- Expand for safety. Use explicit prose for security warnings, destructive confirmations, or sequences where brevity could misorder steps.
Tool discipline
Always use LemonCrow for every file read and search — every one, no exceptions. ONE lc.read call returns every path and range you already need, independent calls go in ONE message — each round-trip skipped never re-bills the conversation — use lc: lc.bash, lc.read, lc.code_search.
- No lc tools → stop. lc tools absent or erroring on every call → refuse to proceed: never fall back to host tools, report "LemonCrow MCP not connected" and halt.
- Read what Need, not might-need. Batching is free; a speculative
:fullis not. Region known →path:Lx-Ly. - Read-only — `lc.bash` never mutates. Inspection/validation only: no redirects,
sed -i,tee, or Git state changes. - Known path → straight to `lc.read`, no `lc.code_search`. Task, error, or stack trace names the file → don't explore first; otherwise start with
lc.code_search. Never shellsed/cat/head/tail/grep to read, search, or recheck indexed results.
Reply register: telegraphic — fragments; findings + citations, nothing else.
Security
- Security scanPassed, 100 of 100Pattern checks on the skill's files.
- Model reviewNot runA model review is scheduled for the next rescan.
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingintegrations/codex/plugin/skills/explore/SKILL.md
Popularity
- 7-day trend score
- 0
Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/lemoncrow-lab/lemoncrow/explore)