AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified Apache-2.0 Self-run

Decision Complete Planner

skill-keithhegit-ultra-orchestration-decision-complete-planner · by keithhegit

Turn a structured intake artifact into a decision-complete plan, task graph, dependency map, owned paths, acceptance checks, expected outputs, and retry assumptions. Use when work spans multiple steps, files, or roles and needs explicit orchestration.

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

Install

$ agentstack add skill-keithhegit-ultra-orchestration-decision-complete-planner

✓ 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-keithhegit-ultra-orchestration-decision-complete-planner)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
3mo 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 Decision Complete Planner? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Decision Complete Planner

Produce a plan another agent can execute without filling in key decisions.

In mainline STRICT or STRICT_OPENSPEC runs, planning must produce JSON-ready artifacts. Markdown summaries may explain the plan, but they do not replace the machine-checkable TaskManifest and WorkPackage objects.

Produce

  • Short summary
  • Ordered implementation phases
  • JSON TaskManifest entries
  • JSON WorkPackage entries
  • Parallel vs serial execution boundaries
  • Acceptance checks per package
  • Retry budget assumptions for each non-trivial work package
  • Current OpenSpec change and slice status when STRICT_OPENSPEC applies

Use canonical field names from [../ultra-orchestrator/references/contracts.md](../ultra-orchestrator/references/contracts.md).

Rules

  • Prefer behavior-level decomposition over file-by-file decomposition.
  • Mark shared write scope explicitly.
  • Treat shared write scope as a write-lock conflict, not a soft warning.
  • Keep non-goals visible.
  • If a design choice is still unresolved, surface it instead of hiding it in prose.
  • For development tasks, prefer one bounded OpenSpec change and one current

slice before dispatch.

  • Do not send work to dispatch if artifact validation cannot be planned.

Hand off

Send the plan to $spec-review for completeness, then to $dispatch-and-track.

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.