~ / rigs / MichaelYcJo / AgenticSeal

MichaelYcJo/AgenticSeal

A workflow of agents that frames, builds, inspects and seals a change without asking anyone, and ends in a seal bound to a commit.

↗ GitHub ★ 1 MIT updated 11d ago project Claude Code Claude plugin
stack: Python
share on X
ARCHETYPE
Orchestrator
A bench of specialised subagents. The main agent mostly delegates.
CONTEXT TAX · EVERY TURN
~614 tokens
Featherweight · median rig: 2.3k · breakdown
GUARDRAILS
0/5
No committed guardrails · details
Quality 0/100 Guardrails v2

Copy this rig

# review before running: this installs third-party code
$ npx degit MichaelYcJo/AgenticSeal/agents ./rig-agenticseal/agents
$ npx degit MichaelYcJo/AgenticSeal/skills ./rig-agenticseal/skills

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 MichaelYcJo/AgenticSeal/skills/agent-contract .claude/skills/agent-contract
$ npx degit MichaelYcJo/AgenticSeal/skills/code-review .claude/skills/code-review
$ npx degit MichaelYcJo/AgenticSeal/skills/commit-pr-convention .claude/skills/commit-pr-convention
$ npx degit MichaelYcJo/AgenticSeal/skills/confidence-check .claude/skills/confidence-check
$ npx degit MichaelYcJo/AgenticSeal/skills/config .claude/skills/config
$ npx degit MichaelYcJo/AgenticSeal/skills/core .claude/skills/core
$ npx degit MichaelYcJo/AgenticSeal/skills/feature-planner .claude/skills/feature-planner
$ npx degit MichaelYcJo/AgenticSeal/skills/implement .claude/skills/implement
$ npx degit MichaelYcJo/AgenticSeal/skills/legacy-parity .claude/skills/legacy-parity
$ npx degit MichaelYcJo/AgenticSeal/skills/parity-setup .claude/skills/parity-setup
$ npx degit MichaelYcJo/AgenticSeal/skills/settle .claude/skills/settle
$ npx degit MichaelYcJo/AgenticSeal/skills/start .claude/skills/start
$ npx degit MichaelYcJo/AgenticSeal/skills/update .claude/skills/update
$ npx degit MichaelYcJo/AgenticSeal/skills/verify .claude/skills/verify
$ npx degit MichaelYcJo/AgenticSeal/skills/writing-style .claude/skills/writing-style
$ curl -fsSL --create-dirs -o .claude/agents/crafter.md https://raw.githubusercontent.com/MichaelYcJo/AgenticSeal/main/agents/crafter.md
$ curl -fsSL --create-dirs -o .claude/agents/framer.md https://raw.githubusercontent.com/MichaelYcJo/AgenticSeal/main/agents/framer.md
$ curl -fsSL --create-dirs -o .claude/agents/proofer.md https://raw.githubusercontent.com/MichaelYcJo/AgenticSeal/main/agents/proofer.md
$ curl -fsSL --create-dirs -o .claude/agents/sealer.md https://raw.githubusercontent.com/MichaelYcJo/AgenticSeal/main/agents/sealer.md
$ curl -fsSL --create-dirs -o .claude/agents/tracer.md https://raw.githubusercontent.com/MichaelYcJo/AgenticSeal/main/agents/tracer.md

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 (15)

Subagents (5)

crafter|
framer|
proofer|
sealer
model: opus
|
tracer|

Similar rigs

copied ✓