fumo-Lin/cognitive-sparring-partner
A pre-development cognitive harness for AI Coding projects. Clarify ideas, pressure-test assumptions, narrow MVP scope, and decide whether to proceed before Claude Code starts building.
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
Copy this rig
# review before running: this installs third-party code
$ npx degit fumo-Lin/cognitive-sparring-partner/.claude ./rig-cognitive-sparring-partner # inspect, then merge into .claude/ MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.
$ npx degit fumo-Lin/cognitive-sparring-partner/.claude/skills/csp-clarify .claude/skills/csp-clarify $ npx degit fumo-Lin/cognitive-sparring-partner/.claude/skills/csp-drift-check .claude/skills/csp-drift-check $ npx degit fumo-Lin/cognitive-sparring-partner/.claude/skills/csp-mvp-gate .claude/skills/csp-mvp-gate $ npx degit fumo-Lin/cognitive-sparring-partner/.claude/skills/csp-predev-decision .claude/skills/csp-predev-decision $ npx degit fumo-Lin/cognitive-sparring-partner/.claude/skills/csp-pressure-test .claude/skills/csp-pressure-test $ npx degit fumo-Lin/cognitive-sparring-partner/.claude/skills/csp .claude/skills/csp
$ curl -fsSL --create-dirs -o .claude/agents/decision-coach.md https://raw.githubusercontent.com/fumo-Lin/cognitive-sparring-partner/main/.claude/agents/decision-coach.md $ curl -fsSL --create-dirs -o .claude/agents/idea-clarifier.md https://raw.githubusercontent.com/fumo-Lin/cognitive-sparring-partner/main/.claude/agents/idea-clarifier.md $ curl -fsSL --create-dirs -o .claude/agents/mvp-scope-guardian.md https://raw.githubusercontent.com/fumo-Lin/cognitive-sparring-partner/main/.claude/agents/mvp-scope-guardian.md $ curl -fsSL --create-dirs -o .claude/agents/red-team-critic.md https://raw.githubusercontent.com/fumo-Lin/cognitive-sparring-partner/main/.claude/agents/red-team-critic.md
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 7,204 rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(rm -rf *)",
"Read(**/*.pem)",
"Bash(rm -rf /)",
"Bash(git push --force:*)",
"Bash(sudo *)",
"Read(.env)",
"Bash(rm -rf /*)",
"Read(./.env.*)",
"Read(~/.aws/**)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Read(**/*.key)",
"Read(**/.env.*)",
"Bash(sudo:*)",
"Bash(git reset --hard*)",
"Bash(git reset --hard:*)",
"Read(.env.*)"
],
"ask": [
"Bash(git push:*)",
"Bash(git push *)",
"Bash(git commit:*)",
"Bash(rm *)",
"Bash(rm:*)",
"Bash(git rebase *)",
"Bash(wget *)",
"Bash(npm publish:*)",
"Bash(git commit *)",
"Bash(gh pr merge *)"
]
}
} Skills (6)
Subagents (4)
| decision-coach model: opus | 决策教练 - 帮助用户做出前置决策，记录权衡 |
| idea-clarifier model: opus | 想法澄清师 - 帮助用户把模糊想法变成清晰的问题陈述 |
| mvp-scope-guardian model: opus | MVP 守门人 - 严格控制 MVP 范围，拒绝范围蔓延 |
| red-team-critic model: opus | 红队批评家 - 挑战假设，识别盲点和风险 |
Similar rigs
anomalyco/opencode
The open source coding agent.
Pragmatist 4.2k tok ·
DietrichGebert/ponytail
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
Pragmatist 1.6k tok ·
Shubhamsaboo/awesome-llm-apps
100+ AI Agents, Agent Skills and RAG Apps - Free and Open Source.
Pragmatist 4.2k tok ·
garrytan/gstack
Use Garry Tan's exact Claude Code setup: 23 opinionated tools that serve as CEO, Designer, Eng Manager, Release Manager, Doc Engineer, and QA
Pragmatist 8.8k tok ·