vc-plan-discovery
Discover related plans for the current task: same feature folder full depth, other features active-only, general-plans active. Like vc-context-discovery but for plan artifacts.
pinned to #3bcb2f9updated 2 months ago
Ask your AI client: “install skills/vc-plan-discovery”.
Requires the metahub MCP server installed in your client. Set up MCP.
mh install skills/vc-plan-discoverymetahub onboarded this repo on the author's behalf.
If you own github.com/withkynam/vibecode-pro-max-kit on GitHub, claim the listing to take over publishing. Your claim preserves the existing eval history and badges; only the curator label is replaced with verified-publisher on your next publish.
Stars
1,035
Last commit
2 months ago
Latest release
published
- #agentic
- #ai-agents
- #ai-coding-assistant
- #ai-development
- #ai-workflow
- #anthropic
- #claude
- #claude-code
- #cli-tools
- #code-quality
- #codex
- #coding-agents
- #cursor
- #developer-tools
- #llm
- #openai
- #prompt-engineering
- #typescript
- #vibe-coding
- #vibecoding
About this skill
Pulled from SKILL.md at publish time.
Output style: Follow process/development-protocols/communication-standards.md — answer-first, plain language, no unexplained jargon, TL;DR on long responses.
Automated checks the publisher passed at publish time — structure, docs, safety, and whether the artifact behaves as claimed.3bcb2f9· 2 months ago
Behavioral checks ran but aren't published for this artifact; the static checks above ran at publish time.
Kind-specific
3 passed1 warningSkill: triggers declaredwarn
No `trigger` phrases in SKILL.md frontmatter
Add `trigger:` lines so Claude knows when to activate this skill — e.g. `when building MCP servers` or `for diagram creation`.
Skill: SKILL.md present
found at .claude/skills/vc-plan-discovery/SKILL.md · frontmatter source: SKILL.md
Skill: body content present
479 words · 3,380 chars · 11 sections · 2 code blocks
Skill: allowed-tools scope
no allowed-tools restriction (Claude may use anything)
Release history
1- releasecurrent3bcb2f9warn2 months ago
Contents
Output style: Follow
process/development-protocols/communication-standards.md— answer-first, plain language, no unexplained jargon, TL;DR on long responses.
Invocation
Primary method — run the auto-discovery script. It applies the Scope Rules below
(same-feature full depth; other features active-only; general-plans active always) and
extracts ONLY the leading YAML frontmatter block of each .md file (no whole-file reads):
node .claude/skills/vc-plan-discovery/scripts/discover-plans.mjs [--feature <name>] [--json]
It groups output into Active Plans / Backlog / Completed / Reports / References (each line:
- [name]: description (path)) and prints a trailing Found N active, N backlog, N completed, N reports, N references line. It never throws on a missing root and exits 0
unless given a bad flag. Use --json for a machine-readable object. Prefer this over the
manual scan below — it is deterministic and avoids loading huge files into context.
Per task-folder artefact colocation, the script scans one level into each
{slug}_{date}/ task folder and surfaces co-located _PLAN_/_REPORT_/_REF_ artefacts;
the sibling reports//references/ dirs are deprecated and only hold legacy artefacts.
The manual scan in Scope Rules below is the FALLBACK for when the script fails.
Purpose
Surface all plans relevant to the current task so agents have full plan context — what was tried, what is in progress, what is deferred, and what reports and references exist — before doing any phase work.
Scope Rules
- Same feature folder (from task context or argument): read ALL of
active/,backlog/,completed/, plus any legacy siblingreports/,references/— surface every file with frontmatter - Other feature folders: read
active/only — surface plans whose frontmatterdescriptionorfeaturefield matches the task domain general-plans/active/: always scangeneral-plans/completed/, legacyreports/,references/: scan only when same-feature folder is not identified
Per task-folder artefact colocation, expect every current artefact (plan, spec, reports, references) INSIDE its {slug}_{date}/ task folder — scan one level into each task folder. The sibling reports//references/ dirs are deprecated and only hold legacy artefacts.
Frontmatter Reading
Read frontmatter fields: name, description, type, feature, phase
Route by description field for relevance matching (same approach as vc-context-discovery).
Skip files without frontmatter or with incomplete frontmatter — log as "no frontmatter, skipped".
Output: grouped list by folder — Active Plans / Backlog / Completed / Reports / References — with name + description per file.
When To Invoke
- First action alongside
vc-context-discoveryat the start of every loop step (research / validate / execute / update-process) - Any time an agent needs to know: what plans exist for this feature, what was tried before, what is deferred, what references exist
Output Format
### Active Plans
- [name]: description (path)
### Backlog
- [name]: description (path)
### Completed
- [name]: description (path)
### Reports
- [name]: description (path)
### References
- [name]: description (path)
Found N active, N backlog, N completed, N reports, N references
Reviews
No reviews yet. Be the first.
Related
Verification Before Completion
Evidence before assertions, always
Writing Plans
Turn specs into phased implementation plans
Test-Driven Development
Red → green → refactor discipline for any feature or bugfix
mh install skills/vc-plan-discovery