Install
$ agentstack add skill-qgolem-orc-spec ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Orc
Orchestrated planning that keeps interactive steps in the main thread.
Input
- $1 — Feature prompt
- $2 — Plan slug
Execution
You MUST execute ALL skills as ordered in steps below in sequence. Do NOT stop after any single phase.
Step 0: Initialize Todos
Step 1: Create Directory
!mkdir -p .claude/plans/$2/phases
Step 2: Vision
Step 3: Discovery (forked)
Step 4: Research (parallel agents)
Step 5: Clarification (interactive x3)
Step 6: Plan Generation (interactive)
Step 7: Report Completion
Output:
Plan created: .claude/plans/$2/
├── PROJECT.md — Vision and success criteria
├── research/ — Domain ecosystem research
├── STATE.md — Codebase context
├── ROADMAP.md — Phase tracking
└── phases/ — Individual phase plans
Next: /orc-swarm [phase N description]
Critical Rules
- Execute ALL phases — Do not stop after Phase 1, 2, or 3
- Sequential execution — Each phase depends on the previous
- Verify outputs — Check each .md file was created before proceeding
- Don't skip clarification — Discovery often surfaces questions that change the plan
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: qGolem
- Source: qGolem/orc
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.