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

Orch Loop

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

Iterate fresh-context passes against an external done-check within a bound. Use when done is a condition, not a task list.

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

Install

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

✓ 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-loop)

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 Loop? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Require: a frozen goal; the body — what each iteration dispatches, one named skill or a caller-owned composite of named skills, bound as plain text and never backticked, a binding rather than a call edge; a done-check naming its oracle and oracle_class per [contracts/verdict.md](../../../contracts/verdict.md) — the iteration count is a deterministic done-check; a bound; and the context packet the iterations carry — design it once via [references/context-packet.md](references/context-packet.md).

Create the worklog through orch-worklog. Each iteration: start fresh from the frozen goal plus the worklog — never a prior transcript; take one work item; dispatch the body with the packet as delegation inputs through orch-delegate; adjudicate the return at the join through orch-integrate; let the done-check decide, per the contract's class policy. Commit verified increments; record failed approaches; queue discovered scope.

Judged exits follow [rules/loops.md](../../../rules/loops.md)'s provisional-exit clause: an iteration-time judged PASS never closes the run on its own.

Exit on the first of: done-check PASS (complete); two consecutive no-progress iterations (stalled); bound spent (limited); an unresolvable dependency (blocked); an unrecoverable execution error (failed). Loops per [rules/loops.md](../../../rules/loops.md).

Never: hardcode a body; carry a step plan; widen the goal; count an iteration's own claim as the done-check; end a judged-class run on iteration-time green.

Return: status, iterations run, results by identity, final verification, queued scope, and bounds spent.

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.