Install
$ agentstack add skill-tomzx-agents-create-plan ✓ 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.
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
Create Plan
Produces a structured implementation plan from a specification or requirements document, organized into phases with milestones, dependencies, effort estimates, and a risk register.
Prerequisites
- Apply the shared SDLC conventions in
skills/sdlc/references/shared.md. - If no argument is provided, locate the feature directory under
.sdlc/features/whose frontmatterissuefield references$ISSUE_NUMBER. .sdlc/features/N-/specification.md(must have passed review with findings verdictapproved), or a specification/requirements document provided in context or as a file path ($1).sdlc/features/N-/telemetry.md(optional, if a telemetry plan was produced): include analytics instrumentation as deliverables in the plan.sdlc/features/N-/observability.md(optional, if an observability plan was produced): include logging, metrics, tracing, and alerting as deliverables in the plan- Team size and velocity context (if available)
Steps
- Read the specification or requirements, and the telemetry and observability plans if present.
- Identify all units of work and group them into logical phases.
- Define phase goals (milestones) and their success criteria.
- Map dependencies between phases and external factors.
- Estimate effort for each phase (person-days or story points).
- Identify risks and mitigations.
- Propose a timeline if team capacity is known.
- Write the output to
.sdlc/features/N-/plan.md.
Output Format
Use the template at skills/sdlc/templates/features/plan.md (copied to .sdlc/templates/features/plan.md by /initialize-sdlc-directory; use the project's customized copy if present). Write the result to the artifact path named in the steps above.
Outcome
If $OUTCOME_YAML is set, emit verdict: approved there per skills/sdlc/references/shared.md once the draft plan/ PR is opened. If no PR was opened, omit the file.
Example Usage
Scenario 1: End-to-end feature Spec describes a payment flow. Plan: Phase 1 (DB schema + migrations), Phase 2 (API endpoints), Phase 3 (frontend integration), Phase 4 (testing + hardening), Phase 5 (rollout).
Scenario 2: High-risk external dependency Plan includes a spike in Phase 1 to validate a third-party payment provider integration before committing to Phase 2 scope.
Completion Checklist
Before handing off to review, confirm:
- [ ] Telemetry and observability deliverables pulled into the plan as explicit work items
Self-check the draft against the [review-plan checklist](../review-plan/SKILL.md) and fix what you can, so review finds less to flag.
Next Step
Run /review-plan to audit for completeness, feasibility, and risk coverage before moving on. Once approved, run /publish-plan to commit the plan and share it with the issue author, then continue with /create-tasks-decomposition.
Useful Commands Reference
No CLI commands required. This skill operates on document content provided in context.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: tomzx
- Source: tomzx/agents
- 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.