Orch Build
Materialize or change one library or scoped custom item through the admission tests. Use for any new or amended skill, pack, or contract.
Install
$ agentstack add skill-danmcinerney-orchflows-orch-build ✓ 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-build) 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: the item's intended contract — what it requires, returns, and never does — its target tier, and its scope per [references/scopes.md](references/scopes.md).
Route first: a request the existing machinery already expresses — a stamped spec, an existing skill or composition — returns that routing, never a new item.
Apply the admission tests from [rules/composition.md](../../../rules/composition.md) before writing: expressible from existing contracts, or a justified kernel candidate; no existing skill already owns the judgment; the tier and landing zone are right — data belongs in a pack cell, integration detail in scripts, one-off procedure in the spec or prompt, and always-on rules in the scope's instruction file, never in a skill body. Start a custom workflow from the nearest composition, pinning its open decisions through orch-elicit. Write to the anatomy and budget; for a pack, satisfy every [signature](../../../contracts/pack-signature.md) cell and its sharing constraints; for a contract change, treat any shape change as breaking.
Gate the result's artifact identity through orch-critique with [references/library-lens.md](references/library-lens.md), in a context independent of this one; verify with the validator and tests as oracles where the scope provides them.
Never: create a near-duplicate of an existing skill; exceed the tier's budget to avoid splitting a reference; touch a T0 contract outside a supersession change; land at canonical scope what the request placed at user or project scope.
Return: the item and adapter paths, admission evidence, boundary findings, and oracle output — or the existing routing when no item is minted.
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.