Orc Discover
Codebase discovery for orc planning workflow. Analyzes patterns without user interaction.
Install
$ agentstack add skill-qgolem-orc-orc-discover ✓ 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.
Links to your public security report.[](https://agentstack.voostack.com/security/report/skill-qgolem-orc-orc-discover) 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 Discover
Codebase exploration that runs forked (non-interactive).
Input
- $ARGUMENTS — Plan slug
Template
See [templates/STATE.md](templates/STATE.md) for output format.
Process
Step 0: Validate Slug
Tree the plans directory at depth 1 to see existing plan directories:
tree .claude/plans -L 1 -dCompare the tree output against the provided $ARGUMENTS slug. If the slug matches a directory exactly, proceed with that directory. If it doesn't match exactly but a visible directory is clearly the right one (typo, case variation, truncation), use that directory instead. Use the matched directory path for all subsequent steps.
Step 1: Load Vision
Read .claude/plans/$ARGUMENTS/PROJECT.mdExtract search targets from vision.
Step 2: Pattern Discovery
Use Glob and Grep. Find 2-3 examples of each (emphasized: depth matters):
- Similar existing functionality
- File/test naming conventions
- API/route patterns
- Error handling patterns
Step 3: Convention Analysis
For discovered files, document with file:line references:
- Code style (naming, organization)
- Error handling approach
- Testing patterns
Step 4: Integration Mapping
For each file to modify:
- Current purpose
- What will change
- Dependencies (via
rg "import.*filename") - Risk level (H/M/L)
Step 5: Write STATE.md
Write .claude/plans/$ARGUMENTS/STATE.md using template.
Include these required sections:
- Current Phase — Track progress state
- Decisions Made — Audit trail for architectural choices
- Blockers — Surface impediments early
Constraint
Cannot use AskUserQuestion — forked context is non-interactive.
Completion Criteria
- [ ] Found 2-3 examples of similar patterns
- [ ] Documented all files to modify with risk levels
- [ ] Identified integration points
- [ ] Surfaced risks with mitigations
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.