francoisgn/belayline-agentic-harness
Belayline: versioned, open harness for building software with coding agents (Claude Code, Codex, Cursor, Gemini CLI, Copilot, Aider): intent and TDD, issues → lots → PRs, adversarial reviews, pluggable compliance, stewards, FinOps and a flo
field: Data & analytics workflow: PR / code reviewDebuggingDocsTesting & TDDGit & commits runs claude in CI
stack: Python
ARCHETYPE
Skill Collector
Ten-plus skills loaded on demand. A procedural-knowledge library.
Copy this rig
$ git clone --depth 1 https://github.com/francoisgn/belayline-agentic-harness 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 francoisgn/belayline-agentic-harness/plugins/harness/skills/compliance-review .claude/skills/compliance-review $ npx degit francoisgn/belayline-agentic-harness/plugins/harness/skills/feedback-triage .claude/skills/feedback-triage $ npx degit francoisgn/belayline-agentic-harness/plugins/harness/skills/harness-update .claude/skills/harness-update $ npx degit francoisgn/belayline-agentic-harness/plugins/harness/skills/intent .claude/skills/intent $ npx degit francoisgn/belayline-agentic-harness/plugins/harness/skills/lesson-propose .claude/skills/lesson-propose $ npx degit francoisgn/belayline-agentic-harness/plugins/harness/skills/lessons-check .claude/skills/lessons-check $ npx degit francoisgn/belayline-agentic-harness/plugins/harness/skills/local-check .claude/skills/local-check $ npx degit francoisgn/belayline-agentic-harness/plugins/harness/skills/lot-finish .claude/skills/lot-finish $ npx degit francoisgn/belayline-agentic-harness/plugins/harness/skills/lot-start .claude/skills/lot-start $ npx degit francoisgn/belayline-agentic-harness/plugins/harness/skills/readme-update .claude/skills/readme-update $ npx degit francoisgn/belayline-agentic-harness/plugins/harness/skills/review-round .claude/skills/review-round $ npx degit francoisgn/belayline-agentic-harness/plugins/harness/skills/status-report .claude/skills/status-report
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 16.2k rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(./.env.*)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(git push --force:*)",
"Read(**/*.pem)",
"Read(.env)",
"Read(~/.aws/**)",
"Read(**/*.key)",
"Read(**/.env.*)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Bash(rm -rf *)",
"Bash(sudo *)",
"Bash(sudo:*)",
"Bash(rm -rf /)",
"Bash(git push -f:*)",
"Read(.env.*)",
"Bash(git reset --hard*)",
"Bash(rm -rf /*)"
],
"ask": [
"Bash(git push:*)",
"Bash(git push *)",
"Bash(gh pr merge *)",
"Bash(git commit:*)",
"Bash(rm *)",
"Bash(gh pr merge:*)",
"Bash(gh pr create *)",
"Bash(git reset --hard:*)",
"Bash(npm publish:*)",
"Bash(git rebase *)"
]
}
} Skills (12)
Similar rigs
Atypical-Consulting/kaldor
Intent/code review guard for Claude Code
Minimalist 84 tok · · Q15
Comp0te/claude-plugins
Claude Code plugins for spec-driven development: plan writing and execution, PR and branch review, Figma-to-spec extraction, and UI verification in the running app.
Pragmatist 298 tok · · Q0
newell-paul/sprint-scout
Plan cycling segment attempts around the wind. A browser-only planner and a showcase of AI-native engineering.
Fort Knox 1.9k tok · · Q51
atlax-tech/harness-armor
Self-improving, tool-first Harness Engineering Agent Skills for Claude Code, Codex, Cursor and TRAE. Build, audit, update and verify AGENTS.md-based repositories.
Pragmatist 908 tok · · Q0