@mutmutco/cursor-plugin 4.2.6 → 4.3.0

package/skills/mmi-resume/SKILL.md

@@ -1,123 +0,0 @@
----
-name: mmi-resume
-description: Open a session — self-check, repo status, and the next actionable board item in one pass.
----
-
-**Host-native invocation:** Claude `/mmi:mmi-resume` · Codex `$mmi:mmi-resume` · jervcode/Kimi `/skill:mmi-resume` · Kilo `skill` tool. A backticked `/name` in this doc names the matching workflow (this skill or a sibling), not a literal command.
-
-# /mmi-resume — start of session
-
-One flow to re-anchor at the top of a session: is the toolchain sound, what does this repo/worktree look
-like right now, and what is the single next thing worth doing. Read-only — it renders the picture and gets
-out of the way. `/mmi` is the board-only hello-to-work; `/mmi-resume` is the wider session open that folds in
-the toolchain self-check and the current-branch snapshot.
-
-## Step 0 — toolchain self-check
-
-```bash
-mmi-cli doctor --self
-```
-
-`doctor --self` verifies the two things that silently break a session: CLI/plugin version parity against
-the published version, and whether the active `gh` token can resolve this repo. It is fast, but it reads
-npm and GitHub — it is not offline-safe, and it checks neither PATH nor hook wiring (#3485). On a **hard**
-gap it points at the heal path — relay it and run it before working:
-
-```bash
-mmi-cli plugin heal      # only on a hard version/plugin gap; then restart Claude Code / reopen the workspace
-```
-
-A clean self-check is silent-enough — move straight on. Do not block the snapshot on a soft/advisory note.
-
-## Step 1 — repo snapshot
-
-```bash
-mmi-cli status
-```
-
-`status` is the unified current-state read for **this** checkout: branch, **release track** (when the repo is
-registered — `releaseTrack` + branch topology from Hub META), linked worktrees, your open PRs, your claimed
-board items, and whether a local stage is running. It is the "where am I" line — render it, don't re-derive
-it from raw `git`/`gh`. Keep the case-preserving `repo` value it reports; that is the workspace identity the
-next step must use (for example `mutmutco/MMC-ZuberShade`).
-
-**Release-track doctrine (#5244):** direct-track repos (`releaseTrack: direct`, plus MMI-Hub via the
-`isHubControlRepo` special case) have **only** `development` and `main` — no `rc` branch exists. Never hunt
-for, clean up, or run `/rcand` against an `rc` ref on direct-track. When `status` omits `releaseTrack`
-(unregistered repo or registry unavailable), resolve it before any train/rc/hotfix/release or branch-hygiene
-work:
-```bash
-mmi-cli oracle org project get {owner}/{repo} --json
-```
-
-### Step 1a — report deferred host cleanup, never perform it here (#5182)
-
-`/mmi-resume` remains read-only. When `status` names linked worktrees or the workspace has previously
-reported a Windows `deferred-lock`, inventory before recommending new work:
-
-```bash
-git worktree list --porcelain
-git -C <linked-worktree> status --porcelain
-gh pr view <known-pr> --repo <owner/repo> --json state,headRefName,headRefOid,mergeCommit
-```
-
-Do not treat a deleted remote branch, a branch name, or `state: MERGED` alone as deletion permission.
-Classify the residue using the host-owned cleanup contract in the `mmi` skill:
-
-- **cleanup candidate** — PR is merged, its `headRefName` and `headRefOid` exactly match the local branch
-  name/OID, and the registered worktree is clean;
-- **deferred-lock** — that exact proof passed, but a prior Windows lock left the path or registration;
-- **retained-ambiguous** — dirty/untracked, OID mismatch, unknown PR, active owner/context, or unreadable proof.
-
-Render the state and the exact path; never delete during `/mmi-resume`. Cleanup happens only in the owning
-agent/host flow, from outside the worktree, after draining every context that used it. The SOP deliberately
-uses `git branch -D` only after exact merged-PR/head-OID proof because squash delivery can never satisfy
-`git branch -d` ancestry. It retries a Windows lock once, then retains and reports—no process killing,
-blind recursive delete, or MMI lifecycle command.
-
-## Step 2 — the next move
-
-```bash
-mmi-cli oracle next --repo <repo reported by status>
-```
-
-Never the retired flat `mmi-cli next` — Wave 3 (#4316) removed that alias; a `flat 'next' alias was
-removed` exit means follow the printed `oracle next` path (and `mmi-cli plugin heal` when
-`doctor --self` says the plugin is behind). Pass the repository from `status` explicitly; never
-reconstruct it by changing case or punctuation. `next` recommends the single most actionable
-claimable board item (unblocked, priority-ranked) and prints the exact
-`mmi-cli oracle board claim <n>` to take it. Offer it; do not claim on the user's behalf without a go.
-For the full board partition (yours / claimable / taken) run `/mmi`.
-
-## Step 3 — render, then stop
-
-Lead with one line: toolchain OK (or the heal to run), the branch + what's in flight, and the one next
-item with its claim command. Then stop. The user drives — claim, continue, or file when they say so.
-
-## Current-state doors (Hub#4120)
-
-When answering “what is true now”, **ask the CLI**, not committed markdown inventories or weekly janitor prose.
-
-| Ask | Verb |
-| --- | --- |
-| Schedules / harbour lanes | `mmi-cli harbour org schedules` / `--json` |
-| Boxes / IPs | `mmi-cli devops runtime box list` |
-| Registry / projects | `mmi-cli oracle org project list\|get` |
-| Board | `mmi-cli oracle board read` / `mmi-cli oracle next` |
-| Docs index freshness | `mmi-cli oracle docs index --check` |
-
-## Notes
-
-- `/mmi-resume` is read-only session orientation. It never claims, moves, or writes.
-- Board status moves are automatic (claim, PR open, merge). Never suggest a manual status move.
-- Slower, board-partition view → `/mmi`. Readiness-gate view for a new repo/first session → `/onboard`.
-
-## Retro — one check before you finish
-Before your final report, answer one question honestly: did **this skill's own instructions** misfire
-this run — ambiguous wording, a misleading message, or an environment failure it should have warned
-about? (Process only — never the user's code or task; e.g. a self-check that reported a false gap, or a
-snapshot that named the wrong branch.) If yes, file **one** lesson and move on; a clean run is silent
-(hard cap: one per run). It lands on the Hub board (deduped) and is fixed only via a reviewed PR — never
-edit the skill live; the retro is advisory, so if the call fails, note it and continue:
-`mmi-cli learning skill-lesson --skill mmi-resume --title "<what misfired>" --body "<what; evidence; proposed amendment>"`
-(never the retired flat `mmi-cli skill-lesson`).

package/skills/onboard/SKILL.md

@@ -1,72 +0,0 @@
----
-name: onboard
-description: Guided first session — readiness check, repo status, and the first command to run.
----
-
-**Host-native invocation:** Claude `/mmi:onboard` · Codex `$mmi:onboard` · jervcode/Kimi `/skill:onboard` · Kilo `skill` tool. A backticked `/name` in this doc names the matching workflow (this skill or a sibling), not a literal command.
-
-# /onboard — guided first session
-
-For a developer's first session in a repo (or a fresh checkout): confirm the repo is wired into the org,
-show what state it's in, and hand over the one concrete next command. Read-only — it diagnoses and points,
-it does not change anything.
-
-## Step 0 — readiness gate
-
-```bash
-mmi-cli onboard
-```
-
-`onboard` reports the five things a machine needs to be workable and the exact next command to fix the
-first gap:
-
-- **Track** — the repo's branch + origin (is this an org checkout at all).
-- **Board** — is the Project board reachable, and how many items are on it.
-- **Registry** — is the repo registered in the Hub (`PROJECT#<slug>` META).
-- **Secrets** — is a GitHub token available for the vault path.
-- **MMI Hub** — does `mmi-hub status` find the installed CLI and every present host surface at the
-  gated fleet version, with hourly automatic updates healthy.
-
-The **Plugin** row is per machine, not per repo. The Hub's thin Claude/Codex catalogs pin exact npm
-packages; Git no longer transports plugin content, and background marketplace auto-update stays **off**
-so it cannot race Hub maintenance. `mmi-hub` gates a release tag+BOM, converges each present host,
-and records last-run evidence. A red row names `mmi-hub install`, `mmi-hub update`, or
-`mmi-hub autoupdate on`; no marketplace ref or hand-edited auto-update ceremony remains.
-
-A `✗` on any line comes with a `Next command:` — run **that** first. Common ones:
-
-- Hub maintenance missing or stale → `npm install -g @mutmutco/hub` then `mmi-hub install`.
-- Hub API URL not configured → `mmi-cli doctor` (safe tooling wiring only; no repository cleanup).
-- Repo not registered → a master-admin runs `/bootstrap` (or `mmi-cli oracle org project set <owner/repo>`).
-- GitHub auth missing → the dev runs `gh auth login --hostname github.com --git-protocol https --web --scopes "project"`.
-
-## Step 1 — the picture
-
-Once the gates are green:
-
-```bash
-mmi-cli status        # branch, worktrees, your PRs, your claimed items, stage
-mmi-cli oracle next          # the first claimable item + its claim command
-```
-
-## Step 2 — hand over the first move
-
-Close with one grounding line: gates green (or the one gate to fix), and the single first command —
-usually `mmi-cli oracle board claim <n>` for the recommended item, or the readiness fix if a gate is red. Don't
-claim on the user's behalf; let them take the first item when ready.
-
-## Notes
-
-- `/onboard` is the first-session, readiness-first wrapper. Once a repo is known-good, `/mmi-resume` is the
-  faster daily open and `/mmi` is the board.
-- Everything here is read-only. The heavier setup (`/bootstrap`) is master-admin only.
-
-## Retro — one check before you finish
-Before your final report, answer one question honestly: did **this skill's own instructions** misfire
-this run — ambiguous wording, a misleading message, or an environment failure it should have warned
-about? (Process only — never the user's code or task; e.g. a readiness gate that reported green while a
-board read actually failed, or a next command that pointed at the wrong fix.) If yes, file **one** lesson
-and move on; a clean run is silent (hard cap: one per run). It lands on the Hub board (deduped) and is
-fixed only via a reviewed PR — never edit the skill live; the retro is advisory, so if the call fails,
-note it and continue:
-`mmi-cli learning skill-lesson --skill onboard --title "<what misfired>" --body "<what; evidence; proposed amendment>"`