Skip to content

wherefore: add the slate skill and wire the sibling skills to it - #10

Merged
DustinVK merged 4 commits into
mainfrom
feature/plan
Jul 19, 2026
Merged

wherefore: add the slate skill and wire the sibling skills to it#10
DustinVK merged 4 commits into
mainfrom
feature/plan

Conversation

@DustinVK

@DustinVK DustinVK commented Jul 18, 2026

Copy link
Copy Markdown
Owner

What

Adds a first-class skill for the wherefore/plan/ collection and wires the existing skills around it. The skill was authored as plan; after review the verb was renamed to slate to stop it competing with Claude Code's built-in plan mode for triggering. The collection, the P-NNN scheme, and the frontmatter contract are unchanged: a verb and the collection it writes are allowed to diverge, the same way capture writes log/ and resolve writes questions/.

The slate skill

One verb under /wherefore:slate, four intents detected from the request:

  • open: allocate the next P-NNN, break the work into - [ ] checkboxes, never bulk-generate.
  • advance: todo -> doing -> done (reopening allowed), bump updated on any write, hand off to capture on a human-driven done.
  • drop: status: dropped, requires a dropped_reason or decision_ref, never deletes.
  • read: report plan/ only, grouped by status.

Spikes are supported via an optional answers: Q-NNN key (the semantic opposite of question_ref), so an item investigating a question does not render as blocked.

Sibling wiring

slate stays the sole writer of plan/; the others are read-only or hand off:

  • capture surfaces plan links for approval and hands off (never writes plan/, never auto-closes on inference).
  • ask surfaces spikes alongside open questions.
  • resolve reports unblocked and answered items, skips dropped ones.
  • supersede flags plan items pointing at a retired decision, read-only.

Driver suppression in both directions (capture drives slate advance, slate drives resolve) prevents handoff loops.

Docs and fixes

  • seed scaffolds plan/ and its README on a fresh repo.
  • The frontmatter contract is documented consistently across the slate skill, capture, seed, AGENTS.md, and CLAUDE.md; both firm project rules (no em dashes; never delete under a wherefore/ data dir) now appear in all five skills.
  • Next-ID allocation in capture and slate now reads the authoritative id from frontmatter instead of scanning filenames, which is how two Q-008s were allocated. The newer duplicate was renumbered to Q-011.
  • The main README now documents the skill (skills list, lifecycle note, directory trees).
  • AGENTS.md stays the tool-neutral floor: it documents the plan-item collection and contract, not the skill verb, so nothing there names plan or slate.

Version

Plugin bumped 0.1.3 -> 0.2.0. A new skill is an additive feature, so it is a minor bump; the plan -> slate rename is not a public break because the skill was never in a released version.

Dogfood records

This repo's own wherefore/ captures the work: the capture-does-not-write-plan-items and rename-plan-skill-to-slate decisions, plan items P-004 through P-010, and questions Q-010 (capture/supersede boundary) and Q-011.

Validation

claude plugin validate passes for the plugin and marketplace; JSON manifests parse; the four-intent dry-run ran against an out-of-repo scratch dir; zero em dashes; a whole-repo grep confirms no product reference to the skill as plan.

🤖 Generated with Claude Code

DustinVK and others added 4 commits July 18, 2026 17:31
Add a plan skill under /wherefore:plan for the wherefore/plan/ collection:
one verb with four intents (open, advance, drop, read), spikes via an
optional answers key, and the full P-NNN frontmatter contract. Open breaks
work into checkboxes; advance and read tolerate prose-only bodies.

Wire the siblings around it, read-only or hand-off, so plan stays the sole
writer of plan/:
- capture surfaces plan links for approval and hands off to plan (advance
  to close, open for implied work); it never writes plan/ and never
  auto-closes on inference.
- ask surfaces spikes (answers) alongside open questions.
- resolve reports unblocked and answered items and skips dropped ones.
- supersede flags plan items whose decision_ref points at a retired
  decision, read-only.
Driver suppression both directions (capture drives advance, plan drives
resolve) prevents handoff loops.

seed scaffolds plan/ and its README on a fresh repo. The frontmatter
contract is documented consistently across the plan skill, capture, seed,
AGENTS.md, and CLAUDE.md. Both project rules (no em dashes; never delete
under a wherefore/ data dir) now appear in all five skills.

Fix next-ID allocation in capture and plan to read the authoritative id
from frontmatter instead of scanning filenames, which is how two Q-008s
were allocated; renumber the newer duplicate (ibm-plex) to Q-011.

Dogfood records: the capture-does-not-write-plan-items decision, plan items
P-004 through P-010, and questions Q-010 and Q-011.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Add the plan skill everywhere the README enumerates the plugin: the summary
bullet, the skills list (open/advance/drop/read, owns plan/, hands off to
capture and ask), the AGENTS.md workflow line, a Plan lifecycle note, and both
directory trees.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
The skill verb `plan` competed with Claude Code's built-in plan mode for
triggering. Rename the verb to `slate`; the collection, the P-NNN scheme, the
frontmatter contract, and every settled ruling stay exactly as they were (a verb
and the collection it writes are allowed to diverge, as capture writes log/ and
resolve writes questions/).

- skills/plan/ -> skills/slate/: name, H1, and a description that leads with the
  collection (operating items in wherefore/plan/) with artifact-centered triggers
  and /wherefore:slate.
- Update every sibling cross-reference (capture, ask, resolve, supersede) to slate,
  keeping the driver-suppression symmetry intact.
- seed embed, CLAUDE.md, README.md, and the ROADMAP verb reference updated.
- Dogfood: capture the rename as a decision; update P-004's text to slate.

AGENTS.md is unchanged: it is the tool-neutral floor and names the collection, not
the skill verb.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Adding a fifth skill (slate) is an additive feature, so bump the minor version.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
@DustinVK DustinVK changed the title wherefore: add plan skill and wire the sibling skills to it wherefore: add the slate skill and wire the sibling skills to it Jul 19, 2026
@DustinVK
DustinVK merged commit 2249287 into main Jul 19, 2026
1 check passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant