sherparc/Sherpa
Generic AI-harness generator: scan the codebase, plan owner docs, agents and skills, create them after approval.
ARCHETYPE
Automator
Hooks on every lifecycle event: format, lint, notify, log.
Copy this rig
# review before running: this installs third-party code
$ npx degit sherparc/Sherpa/.claude ./rig-sherpa # 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 sherparc/Sherpa/.claude/skills/architect-review .claude/skills/architect-review $ npx degit sherparc/Sherpa/.claude/skills/e2e-test .claude/skills/e2e-test $ npx degit sherparc/Sherpa/.claude/skills/milestone-step .claude/skills/milestone-step $ npx degit sherparc/Sherpa/.claude/skills/sherparc-sync .claude/skills/sherparc-sync $ npx degit sherparc/Sherpa/.claude/skills/sync-kb .claude/skills/sync-kb
$ curl -fsSL --create-dirs -o .claude/agents/architect.md https://raw.githubusercontent.com/sherparc/Sherpa/main/.claude/agents/architect.md $ curl -fsSL --create-dirs -o .claude/agents/e2e-tester.md https://raw.githubusercontent.com/sherparc/Sherpa/main/.claude/agents/e2e-tester.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 (5)
Subagents (2)
| architect | Use this agent for anything that touches Sherpa's shape: a new command or milestone, a design decision, a change to the model, plan, apply or state formats, a question about how the pieces fit or why |
| e2e-tester | Use this agent to verify end to end that Sherpa does what README, CLAUDE.md and the ADR index claim: it runs the whole CLI lifecycle (doctor → scan → plan → apply → status/check → adopt → apply --remo |
Hooks (4)
| event | matcher | runs |
|---|---|---|
| UserPromptSubmit | * | sh -c 'command -v python3 >/dev/null 2>&1 && exec python3 "$0" || exec python "$0"' "$CLAUDE_PROJECT_DIR/.claude/hooks/sherpa-outcome.py" |
| PostToolUse | Bash|Edit|Write|MultiEdit | sh -c 'command -v python3 >/dev/null 2>&1 && exec python3 "$0" || exec python "$0"' "$CLAUDE_PROJECT_DIR/.claude/hooks/sherpa-outcome.py" |
| PostToolUseFailure | Bash | sh -c 'command -v python3 >/dev/null 2>&1 && exec python3 "$0" || exec python "$0"' "$CLAUDE_PROJECT_DIR/.claude/hooks/sherpa-outcome.py" |
| Stop | * | sh -c 'command -v python3 >/dev/null 2>&1 && exec python3 "$0" || exec python "$0"' "$CLAUDE_PROJECT_DIR/.claude/hooks/sherpa-outcome.py" |
Slash commands (3)
/architect-review/e2e-test/sync-kb
Similar rigs
aravindhsampath/agentic-template
Cookie-cutter project template for an agentic development workflow: Claude Code architect + engineer subagents, Pi-based multi-model code review (Deepseek + Kimi), strict branch hygiene, declarative apply-standard script.
Pragmatist 2.5k tok ·
ameya-vichare/claude-sdd-starter
A platform-agnostic Claude Code setup for engineering teams, using an interactive setup wizard that tailors everything to your project and provides a spec-driven feature development workflow.
Orchestrator 2.3k tok ·
Sabeekhann/cc-token-meter
Private, local Claude Code usage intelligence track tokens, estimated cost, cache efficiency, budgets, projects, and live sessions with zero telemetry.
Orchestrator 7.3k tok ·
itshig/AGENTS-template
Drop-in AGENTS.md template for Claude Code, Cursor, Codex, and other AI agents — with .agents/ for rules, personas, and workflows.
Orchestrator 3.0k tok ·