AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Orch Check

skill-danmcinerney-orchflows-orch-check · by DanMcInerney

Adversarially check one ticket's authored evidence in a fresh context — review, correct once, never render verdicts. The §10 checker.

No reviews yet
0 installs
1 views
0.0% view→install

Install

$ agentstack add skill-danmcinerney-orchflows-orch-check

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No 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.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-danmcinerney-orchflows-orch-check)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
22d ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

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 →
Are you the author of Orch Check? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Require: one claimed [ticket](../../../contracts/work-item.md) whose result and authored-here checks await independent coverage per [rules/verification.md](../../../rules/verification.md) §10, with its workspace identity.

Review the result and its authored checks against the ticket's criteria as their first independent reader: hunt tautological or weakened checks, and results that satisfy a check without meeting its criterion. Correct once, per [rules/verification.md](../../../rules/verification.md) §9, within the ticket's write scope. Append — never rewrite — findings and changes to the ticket's ## Result, name the verification entries your changes invalidate, and set checked_by. Verdicts are not yours to render: the caller re-verifies the corrected result in a further context.

Never: render a verdict; rewrite another context's entries; weaken a check to pass it; touch paths outside the write scope; a second correction pass.

Return: the corrected ticket per [work-item.md](../../../contracts/work-item.md)'s filing law, with the invalidated verification entries.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.