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

Rpi Plan

skill-microsoft-hve-core-rpi-plan · by microsoft

Create implementation-ready planning artifacts and validation evidence for RPI tasks.

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

Install

$ agentstack add skill-microsoft-hve-core-rpi-plan

✓ 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-microsoft-hve-core-rpi-plan)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
1mo 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 Rpi Plan? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

RPI Plan

Use [references/planning.md](references/planning.md) for the planning template and protocol detail.

Follow the shared conventions in copilot-tracking.instructions.md.

Goal

Convert validated research into an implementation-ready plan, supporting details, and a dated planning log with explicit validation evidence.

Derive {{task_slug}} from the primary task or target with lower-kebab-case, and use the current date in YYYY-MM-DD for the dated folders and files.

What to do

  1. Confirm the task scope and the current research state. Prefer a completed /rpi-research artifact when available.
  2. Follow the four phases in order: Context Assessment, Planning, Plan Validation, Completion.
  3. If research is missing or incomplete, create or extend .copilot-tracking/research/{{YYYY-MM-DD}}/{{task_slug}}-research.md. When deeper gaps remain, prefer the Researcher Subagent at .github/agents/hve-core/subagents/researcher-subagent.agent.md via runSubagent or task, writing subagent evidence under .copilot-tracking/research/subagents/{{YYYY-MM-DD}}/-research.md.
  4. Create or update the dated planning artifacts for this phase:
  • .copilot-tracking/plans/{{YYYY-MM-DD}}/{{task_slug}}-plan.instructions.md
  • .copilot-tracking/details/{{YYYY-MM-DD}}/{{task_slug}}-details.md
  • .copilot-tracking/plans/logs/{{YYYY-MM-DD}}/{{task_slug}}-log.md
  • .copilot-tracking/research/{{YYYY-MM-DD}}/{{task_slug}}-research.md

Derive .copilot-tracking/changes/{{YYYY-MM-DD}}/{{task_slug}}-changes.md as the downstream implementation handoff path, but do not create or update it during planning.

  1. Add ` to generated .copilot-tracking/** markdown artifacts. The implementation plan also includes applyTo: '.copilot-tracking/changes/{{YYYY-MM-DD}}/{{task_slug}}-changes.md'` frontmatter.
  2. Prefer the Plan Validator at .github/agents/hve-core/subagents/plan-validator.agent.md via runSubagent or task, providing the research path, plan path, details path, planning log path, and a concise user-requirements summary. If neither dispatch tool is available, perform the equivalent validation inline and record the findings in the Planning Log Validator Findings section instead of dead-stopping on tooling alone.
  3. Fix Critical and High findings in the planning artifacts, update the Planning Log Discrepancy Log and Validator Findings section, and rerun validation until only non-blocking findings remain.
  4. Re-enter dated artifacts in place, keep completed work, refresh line references, and rerun validation after material edits.
  5. Complete the run by summarizing the implementation plan artifacts created and any scope items deferred for future planning, drawing the deferred items from the planning log.

Success criteria

  • The dated planning artifact set exists under .copilot-tracking/plans/, .copilot-tracking/details/, .copilot-tracking/plans/logs/, and .copilot-tracking/research/.
  • The Plan Validator result is captured and any Critical and High findings are resolved before handoff.
  • The plan includes a final validation phase for full project validation and fix iteration.
  • The completion summary names the implementation plan files created and any scope items deferred for future planning.
  • For normal progression, the completion summary may include an implementation handoff to /rpi-implement and the dated artifact set for the next phase.
  • For planning-only, comparison, audit, analysis, or explicitly no-handoff invocations, return validated planning artifacts and next-step guidance without presenting /rpi-implement as an immediate handoff.

Constraints

  • Do not implement code in this phase.
  • Write only to .copilot-tracking/plans/, .copilot-tracking/plans/logs/, .copilot-tracking/details/, and .copilot-tracking/research/ in this phase, except for workflow tracking files explicitly required by the current execution.
  • Keep the output evidence-oriented; use subagents for research and validation instead of repeating planning logic in the skill.

Stop rules

  • Stop if the research artifact is missing or incomplete and deeper research is not available.
  • Stop only for genuine blockers, such as missing task context, an unwritable research path, or unresolved validation findings that materially affect implementation readiness.
  • Stop if the Plan Validator reports Critical and High findings that must be resolved before implementation.

Handoff

After the plan is validated, continue with /rpi-implement only when the caller expects normal progression.

  • Return the plan file path, details file path, planning log path, validation status, and next implementation steps.
  • When the request is planning-only, comparison, audit, analysis, or explicitly no-handoff, return the validated planning artifacts and next-step guidance without presenting /rpi-implement as an immediate handoff.
  • .copilot-tracking/plans/{{YYYY-MM-DD}}/{{task_slug}}-plan.instructions.md
  • .copilot-tracking/details/{{YYYY-MM-DD}}/{{task_slug}}-details.md
  • .copilot-tracking/plans/logs/{{YYYY-MM-DD}}/{{task_slug}}-log.md
  • .copilot-tracking/research/{{YYYY-MM-DD}}/{{task_slug}}-research.md
  • .copilot-tracking/changes/{{YYYY-MM-DD}}/{{task_slug}}-changes.md

> Brought to you by microsoft/hve-core

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.