plan-feature SKILL.md skillA
plan-feature from vintasoftware/vinta-ai-workflows is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add vintasoftware/vinta-ai-workflows/plan-feature@git:20261026.4783298Pins git:20261026.4783298 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- vintasoftware/vinta-ai-workflows
- Path
skills/vinta-derive-skills/resources/foundation-skills/plan-feature/SKILL.md- Versions recorded
- 5
- Latest version
- git:20261026.4783298, committed Oct 26, 2026
- First version recorded
- Oct 18, 2026
- Size
- 128,070 bytes
- Repository stars
- 12
- License
- MIT
Author a phased implementation plan for a new feature following the repo's `ai-plans/` conventions — including the dependency graph that lets independent phases be implemented in parallel. Use when the user asks to "plan", "design", "scope", or "break down" a feature, write an implementation plan / IMPLEMENTATION_PLAN.md, or turn a spec/idea into a phased roadmap. Always interrogates the requester before drafting. Validates the emitted workflow with `vinta-ai-maestro validate` when maestro is…
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Plan Feature
Plans live in `ai-plans/` as `YYYY-MM-DD-FEATURE_NAME_IMPLEMENTATION_PLAN.md` (uppercase + underscores). `..._SPEC.md` sibling exists → **read first**. Plan translates spec into phased delivery, doesn't re-derive requirements. No spec? Point at [create-spec](../create-spec/SKILL.md) first; plan without spec = plausible-sounding but unverified. Spec/plan pair share `YYYY-MM-DD-FEATURE_NAME` prefix.
Every plan ships **two** files: the markdown above, and its executable sibling `ai-plans/{TODAY}-<feature-kebab>.workflow.json` — same date prefix, the same phase graph in the form an orchestrator runs. See "Emit the executable workflow". Written every time; never gated on a question.
Once both are written, the workflow is validated ("Validate the workflow with vinta-ai-maestro", when it is installed) and the plan goes to the human for review ("Review the plan with the human"). A review on maestro's page adds a third file, `ai-plans/{TODAY}-<feature-kebab>.review.json`, which holds the comments and the conversation.
## Step 0 — Interrogate before drafting (NON-NEGOTIABLE)
…Read the whole file at its exact version.
How to install
mdr add vintasoftware/vinta-ai-workflows/plan-feature@sha256:3a5e3a498dec2aebThe line at the top of this page pins the label git:20261026.4783298, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_ery62hkz563fehu5)
1 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 5 versions of this file, between Oct 18, 2026 and Oct 26, 2026, about one every 2 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261026.4783298 latest | 2026-10-26 | 4783298 | 128,070 B | A | view · diff |
| git:20261019.a28d535 | 2026-10-19 | a28d535 | 126,701 B | A | view · diff |
| git:20261019.377a7aa | 2026-10-19 | 377a7aa | 125,887 B | A | view · diff |
| git:20261018.3738792 | 2026-10-18 | 3738792 | 124,777 B | A | view · diff |
| git:20261018.1795500 | 2026-10-18 | 1795500 | 124,486 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (128070 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
vintasoftware/vinta-ai-workflows · 12 stars · license MIT · pushed 2026-11-04 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_ery62hkz563fehu5 GET https://markdownregistry.com/api/v1/resolve?ref=vintasoftware/vinta-ai-workflows/plan-feature GET https://markdownregistry.com/api/v1/blob/3a5e3a498dec2aebd113826122a97d6d588fbd16bb3d2c62f8ec54c2862e585f
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.
More from vintasoftware/vinta-ai-workflows
Every file in vintasoftware/vinta-ai-workflows