agentrigs
+ submit rig
~ / rigs / compforge / devloop

compforge/devloop

A guard-railed, closed-loop workflow for AI coding agents: live state bus + execution-level hard intercepts for Claude Code, Codex, and DeepSeek Harness (GitHub PR / GitLab MR). From step-level to requirement-level; eval-driven, spec-driven

↗ GitHub ★ 4 no license updated today project Codex Claude plugin
share on X
ARCHETYPE
Skill Collector
Ten-plus skills loaded on demand. A procedural-knowledge library.
CONTEXT TAX · EVERY TURN
~4.1k tokens
Moderate · median rig: 2.3k · breakdown
GUARDRAILS
0/5
No committed guardrails · details

Copy this rig

$ git clone --depth 1 https://github.com/compforge/devloop

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 compforge/devloop/code-taste/skills/code-taste .claude/skills/code-taste
$ npx degit compforge/devloop/devloop/skills/gcam .claude/skills/gcam
$ npx degit compforge/devloop/devloop/skills/gcamp .claude/skills/gcamp
$ npx degit compforge/devloop/devloop/skills/gcampr .claude/skills/gcampr
$ npx degit compforge/devloop/devloop/skills/git-ops .claude/skills/git-ops
$ npx degit compforge/devloop/devloop/skills/monitor .claude/skills/monitor
$ npx degit compforge/devloop/devloop/skills/review .claude/skills/review
$ npx degit compforge/devloop/devloop/skills/validate .claude/skills/validate
$ npx degit compforge/devloop/quality/skills/perf .claude/skills/perf
$ npx degit compforge/devloop/quality/skills/trajectory .claude/skills/trajectory

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 (10)

code-tastegcamgcampgcamprgit-opsmonitorreviewvalidateperftrajectory

Similar rigs

gilles-g/localpr
Claude Code plugin: review a local git diff in a pull-request-style page, comment on lines, and let Claude apply the review. Python stdlib only, offline.
★ 2 project Claude Code 1 skills 10d ago
Pragmatist 5.4k tok ·
zhnt/loushang
AI-native agent harness for coding workflows by python: multi-model LLM orchestration, stateful sessions, tool governance, traceable delivery, and provider routing for GPT, Claude, DeepSeek, Qwen, Kimi, GLM, and MiniMax.
★ 1,631 project Codex 2 skills 11d ago
Minimalist 1.8k tok ·
StringKe/std-agent
One .stdai/ source of truth, fanned out to 22 AI coding tools: Claude Code, Codex, Cursor, Copilot, Gemini CLI, Windsurf/Devin, Amp, Warp and more. Native formats, Agent Skills, MCP, context budgets, drift detection.
★ 8 project Claude CodeCodex 2 skills 21d ago
Minimalist 709 tok ·
nkrvivek/traderkit
Packaged Claude-Code-as-trading-terminal setup with risk gates
★ 3 project Claude Code 2 skills 1mo ago
Minimalist 718 tok ·
copied ✓