cavecrew
Planning-phase discipline for fix runs — plan mode first, TDD red-before-green, edge cases named up front, memory recall.
Skill by Aimino-Tech
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/aimino-tech-cavecrew
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: testing, writing
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/cavecrew
What's inside
- Skill name
cavecrew- Description
- Planning-phase discipline for fix runs — plan mode first, TDD red-before-green, edge cases named up front, memory recall. Use before writing any fix code.
- License
- AGPL-3.0
- Instructions
- 36 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Cavecrew — planning phase You are the planning crew. No edits before the plan exists. ## 1. Plan mode first Switch to plan mode in omp first. Produce the plan (objective, steps, files, tests) and stop. No edits before the plan exists — code changes without a pinned plan are rejected. ## 2. TDD: failing test first, then the fix Write the failing test first. Show red before, green after: run the test to prove it fails on the base, implement the fix, re-run to prove it passes. No fix without its red-then-green evidence. ## 3. Edge cases before coding Think through edge cases before coding. Name each material case and how it is checked (which test, which assertion, which command). Unnamed edge cases do not get fixed by accident. ## 4. Project memory Recall the repo's recorded facts first when project memory is available: prior repairs, repo patterns, known failures. Memory trouble never blocks the run — proceed with the plan and note the gap. ## 5. Deterministic signals only Prefer deterministic, tool-based signals (tests, coverage, lint, build) over judgement calls. No LLM-as-reviewer: the plan is verified by commands with exit codes, not by asking a model whether it looks right. Human review stays minimal because the signals are mechanical.
From Aimino-Tech/syntaro-mcp, AGPL-3.0.
More from Aimino-Tech/syntaro-mcp
- 0.521score
automation-testing
Aimino-Tech
Automation testing skill using Python + PyTest + Playwright for Web/API, with self-healing selectors, RCA, and vision-based automation.
SkillBFreshness: BClaude Code +9 - 0.521score
ponytail
Aimino-Tech
Deterministic verification tail for fix runs — tests, coverage, lint, build as mechanical PASS/FAIL gates.
SkillBFreshness: BClaude Code +9 - 0.518score
syntaro
Aimino-Tech
SYNTARO.
SkillBFreshness: BClaude Code +9 - 0.516score
caveman
Aimino-Tech
Terse final verification pass for fix runs — mechanical checks only, minimal words, minimal human review.
SkillBFreshness: BClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Sep 18, 2026 (1 month ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- AGPL-3.0
- Repository
- github.com/Aimino-Tech/syntaro-mcp
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from Aimino-Tech
- 0.521score
automation-testing
Aimino-Tech
Automation testing skill using Python + PyTest + Playwright for Web/API, with self-healing selectors, RCA, and vision-based automation.
SkillBFreshness: BClaude Code +9 - 0.521score
ponytail
Aimino-Tech
Deterministic verification tail for fix runs — tests, coverage, lint, build as mechanical PASS/FAIL gates.
SkillBFreshness: BClaude Code +9 - 0.518score
syntaro
Aimino-Tech
SYNTARO.
SkillBFreshness: BClaude Code +9 - 0.516score
caveman
Aimino-Tech
Terse final verification pass for fix runs — mechanical checks only, minimal words, minimal human review.
SkillBFreshness: BClaude Code +9 - 0.500score
Office Oxide MCP
Aimino-Tech
Rust-native MCP server for Office document processing
ConnectorCFreshness: CLocal★ 162↓ 18/wkClaude Code +5 - 0.453score
Fast HTML MCP
Aimino-Tech
Lightning-fast HTML generation from AI agents with 15 tools, 22 components, and 25 templates.
ConnectorCFreshness: CLocal↓ 10/wkClaude Code +5
Cite this page
cavecrew skill. Agent Mart. https://agentmart.dev/skills/aimino-tech-cavecrew (last updated 2026-10-24)