mandrel 2.37.0 → 2.38.0

package/.agents/workflows/git-deliver.md

@@ -13,7 +13,7 @@ The **single source of truth** for getting outstanding working-tree changes
 out the door when they do not belong to a planned Story (typo fixes, doc
 tweaks, dependency bumps, operator housekeeping, benchmark result commits
 from mandrel-bench's `/benchmark` Step 4). It is the ad-hoc counterpart to
-the heavyweight `/deliver` pipeline: one command that **detects the git
+the heavyweight `/mandrel-deliver` pipeline: one command that **detects the git
 setup** and escalates to the correct terminal step. Flags pin any level
 explicitly; the interactive choice prompt fires **only** when the detected
 state is genuinely ambiguous, so the common path stays non-interactive and
@@ -133,7 +133,7 @@ directly, honoring these contracts:
 Stop at the resolved level and print a one-block summary naming the branch,
 subject, and (pr level) PR URL + auto-merge state.
 
-Do **not** poll CI — that is the `/deliver` Phase 7 job and is overkill for
+Do **not** poll CI — that is the `/mandrel-deliver` Phase 7 job and is overkill for
 ad-hoc changes. The local feature branch left behind at the pr level is
 reaped by the next run's Boot sweep — see
 [`.agents/rules/git-conventions.md` § Local checkout hygiene](../rules/git-conventions.md).
@@ -151,14 +151,14 @@ reaped by the next run's Boot sweep — see
   does not rewrite history.
 - **Always** prefer `--auto --squash --delete-branch` at the pr level unless
   the operator opts out, so `main`'s history stays uniform across the
-  `/git-deliver` and `/deliver` surfaces.
+  `/git-deliver` and `/mandrel-deliver` surfaces.
 
 ---
 
 ## ⚠️ Parallel Story Execution
 
 Do **not** use this workflow from inside a parallel story-execution context
-(`/deliver #<storyId>`, `/deliver` wave dispatch). `git add -A` sweeps any
+(`/mandrel-deliver #<storyId>`, `/mandrel-deliver` wave dispatch). `git add -A` sweeps any
 untracked files in the working tree, which in a shared working directory may
 belong to another agent. In those contexts stage explicit paths only and
 confirm `git branch --show-current` reports the expected `story-<id>` branch

package/.agents/workflows/helpers/_merge-conflict-template.md

@@ -1,7 +1,7 @@
 # Merge Conflict Resolution — Shared Procedure
 
 Canonical, workflow-agnostic procedure for resolving merge / rebase conflicts.
-Referenced by `deliver.md` and `helpers/deliver-story.md`.
+Referenced by `mandrel-deliver.md` and `helpers/deliver-story.md`.
 
 ## Procedure
 

package/.agents/workflows/helpers/audit-lens-core.md

@@ -30,7 +30,7 @@ constraint for that lens only.
 Each lens carries its own `{{changedFiles}}` fence — the substitution anchor
 consumed by `.agents/scripts/lib/audit-suite/` — and reads it as follows:
 
-- When this lens is invoked from `/deliver` close lenses (or a plan-run audit),
+- When this lens is invoked from `/mandrel-deliver` close lenses (or a plan-run audit),
   the fence is populated with the Story (or plan-run) change-set file list.
   **Restrict analysis to those files** (and their direct dependencies when the
   lens explicitly calls for cross-file reasoning).

package/.agents/workflows/helpers/code-review.md

@@ -1,13 +1,13 @@
 ---
 description: >-
   Perform a comprehensive code review of a Story change set against main
-  before `/deliver` opens or merges the Story PR
+  before `/mandrel-deliver` opens or merges the Story PR
 ---
 
 # Code Review (helper)
 
 > **Helper module.** Not a slash command. Invoked automatically from
-> `/deliver` via `single-story-close.js`. To run a review directly, invoke
+> `/mandrel-deliver` via `single-story-close.js`. To run a review directly, invoke
 > the parent workflow — operators do not call this helper by hand.
 
 This helper performs a comprehensive code review of a change set before it
@@ -36,7 +36,7 @@ child.
 
 ## Argument contract
 
-The caller passes the following arguments (`/deliver` passes
+The caller passes the following arguments (`/mandrel-deliver` passes
 `scope: story`):
 
 | Argument    | Type                                  | Required | Meaning                                                                                          |
@@ -61,7 +61,7 @@ It is an **input-only** signal: it changes *how thorough* the review is, never
 the findings envelope (`{ status, severity, posted, report, halted,
 blockerReason }`) nor the posted `verification-results` structured-comment body. An
 absent or malformed `depth` is treated as `standard`, so a Story that skipped
-`/plan` still gets a passing review with no new failure mode.
+`/mandrel-plan` still gets a passing review with no new failure mode.
 
 How each tier changes the review protocol:
 

package/.agents/workflows/helpers/deliver-light.md

@@ -1,6 +1,6 @@
 ---
 description:
-  The unplanned prompt path shared by /deliver and /plan Gate #1. Judges a
+  The unplanned prompt path shared by /mandrel-deliver and /mandrel-plan Gate #1. Judges a
   prompt's predicted footprint, authors a receipt Story, then lands it through
   the same single-story-init / single-story-close engine — every close gate
   unchanged.
@@ -9,8 +9,8 @@ description:
 # Unplanned delivery (the prompt path)
 
 > **A path, not a command.** There is no `/deliver-light` to type. This file is
-> reached two ways — `/deliver "<prompt>"` (an operator describing small work)
-> and `/plan` Gate #1 (a seed the suggestion says fits the light ceilings, once
+> reached two ways — `/mandrel-deliver "<prompt>"` (an operator describing small work)
+> and `/mandrel-plan` Gate #1 (a seed the suggestion says fits the light ceilings, once
 > the operator confirms). Read
 > [`deliver-digest.md`](deliver-digest.md) once first — the engine invariants,
 > gates, and terminal-envelope contract below are its.
@@ -25,7 +25,7 @@ It never relaxes a close gate, never bypasses the PR to `main`, and never lands
 over-scope work silently.
 
 Two callers, one gate: whichever door you arrived through, the suitability gate
-below is the decision. A `/plan` Gate #1 suggestion is a *suggestion* — it is
+below is the decision. A `/mandrel-plan` Gate #1 suggestion is a *suggestion* — it is
 read against seed-time signals (`DELIVER_LIGHT_SUGGESTION_CEILINGS`: artifacts,
 risk hits, sensitive-path classes), while the gate here is read against the
 predicted work's *effort and risk* (`STORY_SHAPE_CEILINGS`: change kinds,
@@ -39,7 +39,7 @@ across three files is trivial work with a high count; a 200-line rewrite of one
 module is a single change. The axes are therefore effort and risk: distinct
 change **kinds** (N instances of one mechanical edit is one kind at N sites), a
 coarse **magnitude** bucket, and **uncertainty** — is the shape determined by
-the request, or does it still need the design decisions `/plan` exists to
+the request, or does it still need the design decisions `/mandrel-plan` exists to
 resolve?
 
 Because the predicted footprint is a *declaration* — a guess, and a gameable one
@@ -65,7 +65,7 @@ answer).
    **and** a ledgered model verdict with a recorded reason. Both must agree on
    `lite`.
 2. **Over-scope stops — it never hard-fails.** An over-ceiling prompt STOPS and
-   asks the operator to escalate to `/plan` or proceed light. **Both answers
+   asks the operator to escalate to `/mandrel-plan` or proceed light. **Both answers
    are executable** — `--operator-proceed-light` records the second one
    (§ Recording a proceed-light answer). Under `--yes` it fails closed to an
    **`escalated` terminal envelope** that ends the session (§ Escalation is
@@ -97,9 +97,9 @@ answer).
    - **`proceed-light`** — the receipt Story is authored; read `storyId` and
      `nextCommands`. Continue to step 2.
    - **`ask-operator`** — predicted scope exceeds the light ceilings. STOP and
-     ask the operator to escalate to `/plan` or proceed light. Do not proceed
+     ask the operator to escalate to `/mandrel-plan` or proceed light. Do not proceed
      on your own. This is a **question, not a terminal** — wait for the answer,
-     then act on it: *escalate* leaves for `/plan`, *proceed light* re-runs the
+     then act on it: *escalate* leaves for `/mandrel-plan`, *proceed light* re-runs the
      same command with `--operator-proceed-light "<their reason>"`
      (§ Recording a proceed-light answer).
    - **over-scope under `--yes`** — no `action` to branch on: the gate emits an
@@ -107,14 +107,14 @@ answer).
      terminal governs; you are finished.
 
    `--amends '#<id>'` is the canonical light case — shape-checked identically; a
-   heavy amendment escalates to `/plan` like any other over-scope prompt.
+   heavy amendment escalates to `/mandrel-plan` like any other over-scope prompt.
 
-   **Entered from `/plan` Gate #1?** Fill `--creates` / `--refactors` /
+   **Entered from `/mandrel-plan` Gate #1?** Fill `--creates` / `--refactors` /
    `--acceptance` / `--reason` from the plan-context envelope's codebase
    snapshot and `complexitySignals` rather than re-deriving them from the seed
    text — Gate #1 has already done that work, and re-deriving throws away the
    better signal. An `ask-operator` verdict here means the two ceiling sets
-   disagreed: **return to [`../plan.md`](../plan.md) step 2 (Author) in the same
+   disagreed: **return to [`../mandrel-plan.md`](../mandrel-plan.md) step 2 (Author) in the same
    session**, carrying the interrogation you already paid for. That bounce-back
    is not an escalation and does not need a fresh session (§ Why the two
    directions differ).
@@ -127,7 +127,7 @@ answer).
    ```
 
    Capture `workCwd`; `remoteVerified: false` → flip `agent::blocked` and stop.
-   This is [`/deliver`](../deliver.md)'s worktree/branch/lease/label engine,
+   This is [`/mandrel-deliver`](../mandrel-deliver.md)'s worktree/branch/lease/label engine,
    invoked, not reimplemented.
 
 3. **Implement + self-eval.** `cd` into `workCwd`, implement the change, run
@@ -155,13 +155,13 @@ answer).
 
    Exit `3` (`blocked: true`) means the diff exceeds a light ceiling or touches a
    sensitive-path class. STOP, flip `agent::blocked`, and **recycle the receipt**
-   through the envelope's `nextCommand` (`/plan <storyId>`) — tickets mode
+   through the envelope's `nextCommand` (`/mandrel-plan <storyId>`) — tickets mode
    rewrites it into properly-planned Stories and closes it as superseded. Do not
    land, and do not leave the receipt open with no successor: it already carries
    the branch, the worktree, and the implementation, all of which are evidence
    the plan should read.
 
-5. **Close and land (same engine).** Exactly [`/deliver`](../deliver.md)'s close:
+5. **Close and land (same engine).** Exactly [`/mandrel-deliver`](../mandrel-deliver.md)'s close:
 
    ```bash
    node .agents/scripts/single-story-close.js --story <storyId> --cwd <main-repo>
@@ -208,19 +208,19 @@ diff backstop, which re-checks the actual change set against ground truth.
 
 Over-scope under `--yes` emits a schema-validated `story-deliver-terminal`
 envelope with **`status: "escalated"`**, `storyId: null`, and a `nextCommand`
-naming the `/plan` invocation that owns the work.
+naming the `/mandrel-plan` invocation that owns the work.
 
 **That envelope IS this session's terminal output.** Relay it and stop. There is
 no remaining step, no degraded fallback, and no smaller version of the work to
 attempt.
 
-**Invoking `/plan` in this same session is forbidden.** Hand the operator the
-`nextCommand`; `/plan` runs in a **fresh** session.
+**Invoking `/mandrel-plan` in this same session is forbidden.** Hand the operator the
+`nextCommand`; `/mandrel-plan` runs in a **fresh** session.
 
 This is not style — it is the empirical finding that motivated the envelope.
 A mandrel-bench 2.13.0 light-arm run read the escalation and continued anyway:
-it invoked `/plan` in-session and delivered. The in-session plan authored **one**
-Story against the scenario's 3–5 contract, where a fresh `/plan` session on the
+it invoked `/mandrel-plan` in-session and delivered. The in-session plan authored **one**
+Story against the scenario's 3–5 contract, where a fresh `/mandrel-plan` session on the
 identical seed authored **four**. Planning inside a session already framed as
 small work under-decomposes, so walking past the escalation silently produced
 the very outcome the guard exists to prevent. The gate's decision was right both
@@ -233,29 +233,29 @@ in a shape the schema pins, so a later run finds nothing to trip over.
 
 ## Why the two directions differ {#why-the-two-directions-differ}
 
-Traffic runs both ways between this path and `/plan`, and the two directions
+Traffic runs both ways between this path and `/mandrel-plan`, and the two directions
 have **deliberately different session rules**. It reads like an inconsistency;
 it is not. The rule:
 
 > **The direction whose guard is model judgment must break the session. The
 > direction whose guard is mechanical need not.**
 
-**Light → `/plan` must be a fresh session.** What is being protected is
+**Light → `/mandrel-plan` must be a fresh session.** What is being protected is
 *authoring judgment*, and the empirical finding above is that a session already
 framed as small work under-decomposes — one Story against a 3–5 contract where
 a fresh session on the identical seed authored four. The frame is the hazard,
 so only a new session removes it.
 
-**`/plan` → light may stay in-session.** Gate #1 fires **before** authoring, so
+**`/mandrel-plan` → light may stay in-session.** Gate #1 fires **before** authoring, so
 there is no authoring to corrupt, and the frame at that point is "plan this
 seed" — the neutral one, not the small one. Everything on the receiving side is
 mechanical: `STORY_SHAPE_CEILINGS`, the ledgered verdict, the diff backstop.
 None of them degrade because the context is large, so nothing is gained by
 paying for a fresh session.
 
-Do not "fix" this into symmetry in either direction. Making `/plan` → light
+Do not "fix" this into symmetry in either direction. Making `/mandrel-plan` → light
 require a fresh session throws away a paid-for interrogation for no guard.
-Letting light → `/plan` run in-session reintroduces the exact failure the
+Letting light → `/mandrel-plan` run in-session reintroduces the exact failure the
 `escalated` envelope exists to prevent.
 
 ## Constraints
@@ -272,9 +272,9 @@ Letting light → `/plan` run in-session reintroduces the exact failure the
 
 ## See also
 
-- [`/deliver`](../deliver.md) — the delivery entry point; routes here on a
+- [`/mandrel-deliver`](../mandrel-deliver.md) — the delivery entry point; routes here on a
   free-text prompt.
-- [`/plan`](../plan.md) — routes here from Gate #1 on a confirmed suggestion,
+- [`/mandrel-plan`](../mandrel-plan.md) — routes here from Gate #1 on a confirmed suggestion,
   and owns the work an over-scope prompt escalates to.
 - [`deliver-story.md`](deliver-story.md) — the one Story delivery engine every
   path shares.

package/.agents/workflows/helpers/deliver-reference.md

@@ -1,21 +1,21 @@
 ---
 description:
-  On-demand reference appendix for /deliver — the sequencing edge cases,
+  On-demand reference appendix for /mandrel-deliver — the sequencing edge cases,
   role-scoped dispatch mechanics, lite-route inline execution, checklist
   threading, and the per-run epilogue. Read it when the matching lever is in
   play; the lean spine in deliver.md links here.
 ---
 
-# /deliver — reference appendix (on-demand)
+# /mandrel-deliver — reference appendix (on-demand)
 
-Reference-only detail split out of [`deliver.md`](../deliver.md) so the
+Reference-only detail split out of [`mandrel-deliver.md`](../mandrel-deliver.md) so the
 always-resident spine stays lean. Nothing here is a new MUST —
 it is the mechanics an operator consults when the matching lever is engaged.
 
 ## Ranges (`4922 - 4926`) {#ranges}
 
 A contiguous span is how an operator reads a plan run, so the dash range is a
-first-class id shape rather than prose to interpret — `/deliver 4922 - 4926`
+first-class id shape rather than prose to interpret — `/mandrel-deliver 4922 - 4926`
 means exactly the five ids in it.
 
 **Pass the span through; never expand it by hand.** Every id-list flag on the
@@ -49,6 +49,14 @@ issue state rather than against anything you hand it. That is why there is no
 batch label to pass and why a blocker that landed in an unrelated run is simply
 seen as done.
 
+**The non-zero exit codes.** **2** — `cycleError`: the graph is
+self-referential; fix `depends_on`, do not retry. **3** — `wedged`: nothing
+dispatchable and nothing in flight, with the undone Stories and their unmet
+blockers named; land a blocker or add it to `--ids`. **4** — `blocked`: a Story
+carries `agent::blocked` with `blockedReason`, the protocol's HITL pause
+([`instructions.md` § 1.J](../../instructions.md)). Blocked outranks a wedge,
+but not a cycle.
+
 **Resuming an exit-4 `blocked`.** Read the friction comment with
 `gh issue view <id> --comments`, and resume only once the operator has
 unblocked it:
@@ -184,7 +192,7 @@ exposes agent dispatch, spawn each ready Story as its own
 `CLAUDE.md` @-closure) carrying the load-bearing delivery MUSTs standalone. The
 sub-agent executes [`deliver-story.md`](deliver-story.md) Steps 0–2.5
 (init → implement → acceptance self-eval → **push**) and stops there; **you**
-own Step 3, serialized — see `/deliver` § Closing what the workers hand back.
+own Step 3, serialized — see `/mandrel-deliver` § Closing what the workers hand back.
 Thread into its prompt: `storyId`; `docsDigestPath` (the per-run docs digest, null when
 `project.docsContextFiles` is unset); `checklistPath` (the footprint-matched
 write-time audit checklist, produced at dispatch, below); and the
@@ -225,7 +233,7 @@ terminal envelope are identical either way — only the isolation differs.
 
 ## Intent phrases (what replaced the flag table)
 
-`/deliver` has no operator-facing flags. The scripts still take every flag they
+`/mandrel-deliver` has no operator-facing flags. The scripts still take every flag they
 always did — the workflow fills them in from what the operator said, the same
 derive-then-announce contract `/git-deliver` uses for its terminal level.
 
@@ -252,7 +260,7 @@ Two rules keep this honest:
 operator expresses; it is a runner asserting *nobody is at the keyboard*, and
 it changes fail-closed behavior (it is what turns the unplanned path's
 over-scope stop into an `escalated` terminal envelope, and what auto-proceeds
-`/plan`'s gates). Cron, `/loop`, and headless dispatch set it. An attended run
+`/mandrel-plan`'s gates). Cron, `/loop`, and headless dispatch set it. An attended run
 never does, however the operator phrases their impatience.
 
 ## Operator-merge implies no-wait

package/.agents/workflows/helpers/deliver-story-reference.md

@@ -33,7 +33,7 @@ Epic-scoped dispatch manifest to serialise two operators driving the same
 Story, so this lease is the only guard against a concurrent
 `single-story-init` clobbering an in-flight run.
 
-**Fail-closed.** Unlike `/deliver`, the standalone path
+**Fail-closed.** Unlike `/mandrel-deliver`, the standalone path
 has **no Epic-scoped lifecycle ledger** to read a per-owner
 `story.heartbeat` from, so there is no live-heartbeat source to decide
 whether a foreign claim is stale. Rather than silently reclaim every
@@ -131,7 +131,7 @@ The v2 engine's trait table:
 | Ceremony      | Per-Story, routed off the derived change level via `ceremony-routing.js` |
 
 **Ceremony-lite Stories still land through this engine unchanged.** A
-lite-routed Story collapses only the _advisory_ plan/deliver
+lite-routed Story collapses only the _advisory_ plan/mandrel-deliver
 ceremony — the fresh-critic / Tech-Spec authoring a one-artifact scope does
 not earn. It does **not** get a cheaper landing: the close-validation gates
 (lint / test / format / coverage / CRAP / maintainability), the PR to `main`,
@@ -231,7 +231,7 @@ demand. See [`.agents/instructions.md` § 3](../../instructions.md).
 write and self-check as you author. When absent, lens-aware coverage still
 runs maker-blind at Story-scope review inside the close subprocess. The
 dispatch step produces `checklistPath` from the Story's predicted footprint
-before it spawns the worker — see [`/deliver`](../deliver.md).
+before it spawns the worker — see [`/mandrel-deliver`](../mandrel-deliver.md).
 
 **Pre-eval full-suite discipline (spine step 1.3).** Repo-invariant guards —
 drift-guard and schema tests living outside the Story's scoped greps — are
@@ -542,7 +542,7 @@ The `single-story-close.js` script, in order:
    `gh pr merge <prNumber> --auto --squash --delete-branch`. Once CI's
    required checks turn green, GitHub squash-merges the PR and deletes
    the source branch — the operator does not need to babysit the merge
-   button. Mirrors the `/deliver` finalize path. Failure is
+   button. Mirrors the `/mandrel-deliver` finalize path. Failure is
    non-fatal: the operator retains the manual merge surface in the
    GitHub UI. Pass `--no-auto-merge` to opt out when the PR needs a
    pre-merge eyeball.
@@ -909,6 +909,11 @@ up").
 
 ## Idempotence and the standing constraints
 
+**Why a no-envelope hand-off must never be re-dispatched.** Only Step 3 mints a
+terminal envelope, so a sub-agent returning without one is the normal shape. The
+branch already exists, and re-running Step 0 underneath live work is how one
+Story ends up with two closes — resume per the spine's § Recovery instead.
+
 Every script in the chain no-ops safely on re-run: `single-story-init.js`
 re-prints `workCwd` for an already-initialized Story; `single-story-close.js`
 and `single-story-confirm-merge.js` short-circuit on a closed or `agent::done`

package/.agents/workflows/helpers/deliver-story.md

@@ -9,7 +9,7 @@ mandatoryReads: [deliver-digest.md]
 
 > **Lean spine.** Happy path + gate list; edge-case, recovery and reference
 > detail lives in [`deliver-story-reference.md`](deliver-story-reference.md)
-> ("reference" below). Invoked by [`/deliver`](../deliver.md).
+> ("reference" below). Invoked by [`/mandrel-deliver`](../mandrel-deliver.md).
 > **Read [`deliver-digest.md`](deliver-digest.md) once, first** — the one
 > bundled read every delivery needs. Steps cite it as "digest § N".
 
@@ -34,14 +34,13 @@ that dispatched the work**, never to a spawned worker.
 - **Inline dispatch** (a one-Story run — digest § 1): one session is both
   roles and walks Steps 0→7, no hand-off.
 - **Sub-agent dispatch**: the `story-worker` stops at Step 2.5 with the branch
-  pushed and returns a hand-off; the dispatching `/deliver` session runs Step 3
+  pushed and returns a hand-off; the dispatching `/mandrel-deliver` session runs Step 3
   **in its own turn** and **serializes the tail — one close at a time across
   the run**, even though implementation ran in parallel (reference § Step 3).
 
-**A worker returning no terminal envelope is expected, not a failure.** Only
-Step 3 mints one, so a hand-off is the normal sub-agent return. Never
-re-dispatch the Story on it — the branch exists, and re-running Step 0 under
-live work is how one Story gets two closes. Resume per § Recovery instead.
+**A worker returning no terminal envelope is expected, not a failure** — only
+Step 3 mints one. Never re-dispatch the Story on it; resume per § Recovery
+(reference § Idempotence and the standing constraints).
 
 ## Step 0 — Initialize (`single-story-init.js`)
 
@@ -162,5 +161,5 @@ not process. Drive `agent::*` through
 
 ## See also
 
-[`deliver-digest.md`](deliver-digest.md), [`/deliver`](../deliver.md),
+[`deliver-digest.md`](deliver-digest.md), [`/mandrel-deliver`](../mandrel-deliver.md),
 [`deliver-story-reference.md`](deliver-story-reference.md).

package/.agents/workflows/helpers/diagnose.md

@@ -9,7 +9,7 @@ description: >-
 
 > **Helper, not a slash command.** Files under `workflows/helpers/` are not
 > projected into the mandrel plugin command tree. The same `lib/checks/` registry runs
-> automatically as preflight inside `/deliver`, `single-story-close`, and
+> automatically as preflight inside `/mandrel-deliver`, `single-story-close`, and
 > `npm test` — this viewer exists only for ad-hoc inspection. Invoke the
 > backing script directly: `node .agents/scripts/diagnose.js [args]`.
 
@@ -18,7 +18,7 @@ description: >-
 `diagnose.js` runs the checks registry assembled under
 `.agents/scripts/lib/checks/` in read-only mode and surfaces every
 finding declared on the requested scope. It is the operator-facing read
-of the same registry that preflight guards (`/deliver`,
+of the same registry that preflight guards (`/mandrel-deliver`,
 `single-story-close`), the retro hook, and `npm test` consult — but with
 `autoFix: false` always, no remote GitHub writes, and no commits.
 

package/.agents/workflows/helpers/parallel-tooling.md

@@ -58,7 +58,7 @@ the same shape as Rule 1 but at the sub-agent layer.
 
 - **Tool primitives:** `Agent` (one call per independent unit, all in one
   turn).
-- **When:** wave-level Story fan-out from `/deliver`, per-dimension
+- **When:** wave-level Story fan-out from `/mandrel-deliver`, per-dimension
   audit dispatch, any "for each X in Xs run /Y X" loop where the Xs do not
   share write paths.
 - **Anti-pattern:** serial `Agent` calls (`Agent` → wait → `Agent` → wait)

package/.agents/workflows/helpers/plan-reference.md

@@ -1,6 +1,6 @@
-# /plan — on-demand reference appendix
+# /mandrel-plan — on-demand reference appendix
 
-> **Applies when:** you are executing [`/plan`](../plan.md) and hit one of the
+> **Applies when:** you are executing [`/mandrel-plan`](../mandrel-plan.md) and hit one of the
 > situations below — input-mode derivation, the Gate #1 light handoff,
 > shape-derived complexity routing, tickets-mode supersede authoring, critic
 > dispatch detail, a failed persist, or source-id resolution. The spine stays
@@ -8,7 +8,7 @@
 
 ## Deriving the input mode
 
-`/plan` has no operator-facing flags; the CLIs below still take every flag they
+`/mandrel-plan` has no operator-facing flags; the CLIs below still take every flag they
 always did. Read the invocation, **announce what you derived**, then fill in
 the flag — the same derive-then-announce contract `/git-deliver` uses for its
 terminal level.
@@ -94,7 +94,7 @@ not re-deriving which assumptions were really the agent's to make.
 
 ## Gate #1 → the light path (in-session handoff)
 
-On a confirmed `deliverLightSuggestion`, `/plan` routes into
+On a confirmed `deliverLightSuggestion`, `/mandrel-plan` routes into
 [`deliver-light.md`](deliver-light.md) **without ending the session**. Two
 things make that safe, and both are worth understanding before changing it:
 
@@ -110,7 +110,7 @@ things make that safe, and both are worth understanding before changing it:
    span). Two different checks on purpose, so a confirm is not a bypass.
 
 **When the light gate answers `ask-operator`**, the two ceiling sets disagreed.
-Resume `/plan` at step 2 (Author) **in this same session** — the interrogation
+Resume `/mandrel-plan` at step 2 (Author) **in this same session** — the interrogation
 is still valid and re-paying for it buys nothing. This bounce-back is not an
 escalation.
 
@@ -138,7 +138,7 @@ in `audit-rules.json`. There is no configuration key to set: a project with no
 rendered frontend resolves falsey and the offer never fires.
 
 When it does fire, **name [`/prototype`](../prototype.md) and stop there.**
-`/plan` must never invoke it — operator invocation is the entire design, because
+`/mandrel-plan` must never invoke it — operator invocation is the entire design, because
 the value is a human looking at a layout before its UI acceptance criteria are
 frozen.
 
@@ -182,7 +182,7 @@ decision:
 
 **The label is a hint; deliver re-derives.** Persist labels a
 lite cohort's Stories with **`route::lite`** as a *human-visible hint only* —
-`/deliver` computes the route from each fetched Story body via the same shape
+`/mandrel-deliver` computes the route from each fetched Story body via the same shape
 function at dispatch, so neither a lost label nor an unread marker can
 misroute delivery: a lite-shaped Story derives `lite` even with the label
 absent, and a sensitive-footprint Story routes `full` and keeps its fresh
@@ -421,7 +421,7 @@ The order is: create unlabelled → upsert `story-plan-state` on
 every Story → upsert `plan-summary` on the primary → flip every Story to
 `agent::ready`.
 
-This is what lets `/deliver` trust the label: a Story carrying
+This is what lets `/mandrel-deliver` trust the label: a Story carrying
 `agent::ready` always has its persist receipt on the ticket, so nothing can
 pick it up mid-write and read a half-persisted plan.
 
@@ -436,7 +436,7 @@ So if a transient GitHub failure strands the run at Story `k` of `N`:
 
 | | Behaviour |
 | --- | --- |
-| The `1..k-1` Stories | Live, but **not** `agent::ready` — invisible to `/deliver`, not half-delivered. |
+| The `1..k-1` Stories | Live, but **not** `agent::ready` — invisible to `/mandrel-deliver`, not half-delivered. |
 | Re-running persist | Adopts them by fingerprint, creates only the missing ones, then flips the whole cohort ready. |
 | Editing `stories.json` first | Changing a slug or title changes the fingerprint — the old issue is orphaned rather than adopted. Close it by hand. |
 

package/.agents/workflows/helpers/qa-core.md

@@ -115,7 +115,7 @@ is no per-workflow finding schema.
 Route the ledger through the shared classify/route/dedup/promote core. The
 outcome is that **every ledger item carries a class, a route decision, and an
 operator-confirmed disposition**, with each `file` item promoted via
-`promote-finding.js` into `/plan` — verified by the cluster's fingerprint
+`promote-finding.js` into `/mandrel-plan` — verified by the cluster's fingerprint
 footer landing in each seed body. For each untriaged item:
 
 1. **Classify** via
@@ -140,7 +140,7 @@ footer landing in each seed body. For each untriaged item:
    against it.
 3. **Decide the disposition** with the operator (`file` / `defer` / `dismiss`)
    and record it back onto the ledger item.
-4. **Promote the `file`-dispositioned findings through `/plan`** via
+4. **Promote the `file`-dispositioned findings through `/mandrel-plan`** via
    [`promote-finding.js`](../../scripts/lib/findings/promote-finding.js) — the
    same cluster/size/route/file path `audit-to-stories` consumes. Never
    hand-roll the clustering, sizing, or promotion in prose:
@@ -149,8 +149,8 @@ footer landing in each seed body. For each untriaged item:
    import { promoteFindings } from '../scripts/lib/findings/promote-finding.js';
    const { promotions } = await promoteFindings(ledgerItems, {
      searchIssues, // GitHub provider, open + closed
-     createStory, // tight cluster (≤2 surfaces): seed → /plan --seed-file
-     createPlanSeed, // broad cluster (>2 surfaces): same /plan --seed-file path (may N>1)
+     createStory, // tight cluster (≤2 surfaces): seed → /mandrel-plan --seed-file
+     createPlanSeed, // broad cluster (>2 surfaces): same /mandrel-plan --seed-file path (may N>1)
    });
    ```
 
@@ -159,16 +159,16 @@ footer landing in each seed body. For each untriaged item:
    `createPlanSeed` — neither opens an Epic; both render a **redacted** plan
    seed (redaction already ran at capture), **stamp the cluster's
    `fingerprintFooter(sha)` verbatim into the seed body**, and chain
-   `/plan --seed-file <seed>`. Prefer one Story; split only under the
+   `/mandrel-plan --seed-file <seed>`. Prefer one Story; split only under the
    default-single policy. A `file` disposition **never** opens a raw GitHub
-   Issue; only `defer` and `dismiss` skip the `/plan` handoff.
+   Issue; only `defer` and `dismiss` skip the `/mandrel-plan` handoff.
 
 ## The HITL write gate
 
 Capture stays read-only precisely so every state change lands in Triage,
-deliberately and confirmed. Any ticket-filing, seed write, `/plan` invocation,
+deliberately and confirmed. Any ticket-filing, seed write, `/mandrel-plan` invocation,
 or label mutation is a **write** — present the artifact, confirm each one with
 the operator, and wait before it happens. The agent never files tickets,
 promotes findings, or mutates a label autonomously. The plan→deliver hard stop
-is preserved: each `/plan` chain pauses at its own HITL gates and never
+is preserved: each `/mandrel-plan` chain pauses at its own HITL gates and never
 auto-delivers.

package/.agents/workflows/helpers/worktree-lifecycle.md

@@ -14,7 +14,7 @@ into the wrong commit. Each Story runs in its own `git worktree` at
 isolated per-Story. The main checkout stays quiet.
 
 This document is the operator and reviewer reference. See
-[`/deliver`](../deliver.md) and [`helpers/deliver-story`](deliver-story.md)
+[`/mandrel-deliver`](../mandrel-deliver.md) and [`helpers/deliver-story`](deliver-story.md)
 for the broader execution flow.
 
 ## Configuration
@@ -50,7 +50,7 @@ root, and shell-metacharacter injection in `root`.
 | **Sweep**       | Operator-driven (`WorktreeManager.sweepStaleLocks`)                           | Stale `*.lock` files under `.git/` (older than 5 min) are removed before GC.                                                                                |
 | **GC**          | Operator-driven (`WorktreeManager.gc`)                                        | Orphan `.worktrees/story-*` whose Stories are closed are reaped if clean.                                                                                   |
 | **Force-drain** | Operator-driven (`drain-pending-cleanup.js`)                                  | Retries `.worktrees/.pending-cleanup.json` (`git worktree remove` then `fs.rm`); Windows-only escalation enumerates user-mode handle holders and `taskkill`s them before re-trying. |
-| **Ensure**      | `single-story-init.js` (entry for `/deliver`)                                 | `git worktree add .worktrees/story-<id>/` on the `story-<id>` branch.                                                                                       |
+| **Ensure**      | `single-story-init.js` (entry for `/mandrel-deliver`)                                 | `git worktree add .worktrees/story-<id>/` on the `story-<id>` branch.                                                                                       |
 | **Run**         | During Story execution                                                        | Agent runs inside the worktree; HEAD/reflog activity is isolated.                                                                                           |
 | **Reap**        | After successful Story merge (in `single-story-close`)                        | `git worktree remove` — refuses to delete dirty trees or unmerged branches.                                                                                 |
 
@@ -85,13 +85,13 @@ epic-runner. The lifecycle surfaces that do run automatically are:
 
 | Entry point                       | Script / caller                                                      | What it cleans                                                                                                          |
 | --------------------------------- | -------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------ |
-| Story init (`/deliver <storyId>`) | `single-story-init.js` boot sweep (`sweepMergedStoryBranches`)        | Merged/closed `story-*` branches (local + origin) from prior runs; it then creates only its own worktree.                 |
-| Story close (`/deliver` close)    | `single-story-close.js` worktree-reap phase (`WorktreeManager.reap`)  | The per-Story worktree; on a Windows EBUSY-class lock the entry is deferred into `.worktrees/.pending-cleanup.json`.       |
+| Story init (`/mandrel-deliver <storyId>`) | `single-story-init.js` boot sweep (`sweepMergedStoryBranches`)        | Merged/closed `story-*` branches (local + origin) from prior runs; it then creates only its own worktree.                 |
+| Story close (`/mandrel-deliver` close)    | `single-story-close.js` worktree-reap phase (`WorktreeManager.reap`)  | The per-Story worktree; on a Windows EBUSY-class lock the entry is deferred into `.worktrees/.pending-cleanup.json`.       |
 | Drain pending-cleanup (operator)  | `drain-pending-cleanup.js` (run directly — see below)                 | The pending-cleanup ledger, with optional Windows handle-holder escalation. This is the only path that drains the ledger. |
 
 Operator takeaway: if worktrees or stale locks accumulate, run
 `node .agents/scripts/drain-pending-cleanup.js` — nothing in the
-`/plan` → `/deliver` loop force-sweeps or GCs on your behalf.
+`/mandrel-plan` → `/mandrel-deliver` loop force-sweeps or GCs on your behalf.
 
 ## Draining the pending-cleanup ledger
 
@@ -297,6 +297,6 @@ Human reviewers should **keep using the main checkout** — not a worktree:
   `git worktree remove --force <path>`. Confirm there is no uncommitted work
   first.
 - **Disable temporarily**: flip `enabled: false` in `.agentrc.json`. The next
-  `/deliver` skips worktree creation entirely.
+  `/mandrel-deliver` skips worktree creation entirely.
 - **Inspect live worktrees**: `git worktree list --porcelain` on the main
   checkout. Each block shows `worktree <path>` / `branch refs/heads/story-<id>`.