Orch Judge
Score one fixed candidate against frozen criteria, blind to other candidates. Use inside panels, evolve, and tournaments.
Install
$ agentstack add skill-danmcinerney-orchflows-orch-judge ✓ 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-danmcinerney-orchflows-orch-judge) 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
Require: one fixed candidate identity and frozen scoring criteria, each naming its oracle and oracle_class per [contracts/verdict.md](../../../contracts/verdict.md). Blindness: no sight of other candidates, their scores, or the candidate's provenance.
Score by class: runnable candidates through their executed oracles — run, test, measure, and cite the output; static candidates through the judged rubric, each score anchored to quoted evidence from the candidate itself. Score every criterion separately before any overall number; an unscoreable criterion is UNVERIFIED, never interpolated.
Never: compare to another candidate; let one criterion bleed into another; score provenance, style of authorship, or effort.
Return: a score card — per-criterion score with verdict, oracle_class, and evidence — plus overall score and the confidence it deserves.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: DanMcInerney
- Source: DanMcInerney/orchflows
- 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.