mandrel 2.37.0 → 2.39.0

package/.agents/docs/workflows.md

@@ -16,7 +16,7 @@ compose. This file is only for "which command does X?" lookups.
 Every command file lives at `.agents/workflows/<name>.md` and is projected
 into a flat `.claude/commands/` tree by `npm run sync:commands` (kept
 current at install time and on every `mandrel sync`/`update`) so it shows
-up as a bare `/<name>` slash command (e.g. `/deliver`). The projection
+up as a bare `/<name>` slash command (e.g. `/mandrel-deliver`). The projection
 writes only `.claude/commands/<name>.md` — there is no plugin manifest and no
 marketplace listing. The commands load in every Claude Code environment.
 
@@ -52,16 +52,16 @@ description, edit the workflow file’s front-matter and regenerate.
 | `/audit-security` | Audit dependency CVEs, input-validation gaps, secrets handling, and auth boundaries; emit a structured High/Medium/Low findings report. |
 | `/audit-seo` | Audit SEO fundamentals and Generative Engine Optimization signals (meta, structured data, crawlability); only relevant for web targets. |
 | `/audit-sre` | "Audit production-readiness for a release candidate: SLOs, observability, runbooks, error budgets, and rollback paths." |
-| `/audit-to-stories` | Convert findings produced by the audit-\* workflows into actionable GitHub Stories. Reads temp/audits/audit-\*-results.md, groups findings cross-audit, deduplicates against existing Issues by fingerprint, and either chains into /plan --seed-file or opens standalone Stories. |
+| `/audit-to-stories` | Convert findings produced by the audit-\* workflows into actionable GitHub Stories. Reads temp/audits/audit-\*-results.md, groups findings cross-audit, deduplicates against existing Issues by fingerprint, and either chains into /mandrel-plan --seed-file or opens standalone Stories. |
 | `/audit-ux-ui` | Audit UX/UI consistency and design system adherence |
-| `/deliver` | Unified delivery entry point. Takes Story ids or a plain-language prompt, derives which path the work belongs on, and lands it via the single deliver-story engine — story-<id> → PR → main. |
 | `/git-cleanup` | Tidy the local checkout in four phases: fast-forward `main`, prune stale remote-tracking refs, sweep merged branches (squash-aware), and triage `git stash` entries — each step gated by operator confirmation. |
 | `/git-deliver` | Single ad-hoc delivery command for working-tree changes. Detects the git setup and escalates to the right terminal step — commit only, commit + push, or commit + push + open a PR with native auto-merge — picking the default from observable state and letting flags pin any level explicitly. Replaces the retired git-commit-all, git-push, and git-pr-all trio. |
+| `/mandrel-deliver` | Unified delivery entry point. Takes Story ids or a plain-language prompt, derives which path the work belongs on, and lands it via the single deliver-story engine — story-<id> → PR → main. |
+| `/mandrel-plan` | Unified planning entry point. Interrogate → author → persist. Emits one Story by default; splits into N>1 only under the default-single split policy. |
 | `/mandrel-update` | npm-era upgrade wraparound for a Mandrel consumer. Runs `npx mandrel update` (resolve newest published version → install → re-materialize `.agents/` → migrate → doctor → surface changelog) as the single mechanical step, then walks the operator through the judgment wraparound the CLI deliberately leaves unowned: reconcile `.agentrc.json`, install the stabilized quality-gate surface, refresh the harness permission allowlist, reconcile the consumer's `AGENTS.md` / runbooks against the surfaced changelog, and stage + commit the staged lockfile bump. |
-| `/memory-consolidate` | Attended consolidation pass over this project's agent memory pool — merge duplicates, verify claims against the current tree, prune with operator confirmation, rewrite the index, and stamp the pool so the /plan advisory goes quiet. |
-| `/plan` | Unified planning entry point. Interrogate → author → persist. Emits one Story by default; splits into N>1 only under the default-single split policy. |
+| `/memory-consolidate` | Attended consolidation pass over this project's agent memory pool — merge duplicates, verify claims against the current tree, prune with operator confirmation, rewrite the index, and stamp the pool so the /mandrel-plan advisory goes quiet. |
 | `/prototype` | Operator-invoked UI prototype pass. Discovers the consumer's design-system SSOT first, then — only after the operator confirms — writes exactly one self-contained HTML file under the gitignored workspace-root temp tree, so a layout can be reviewed before its UI acceptance criteria are authored. |
-| `/qa-assist` | Human-led QA assist loop — set up, then ride a rolling multi-observation intake session. The operator reports observations in any order; the agent enriches each (repro + root-cause file:line + coverage verdict for bugs; analysis + options + recommendation for enhancements), asks clarifying questions only when ambiguous, and appends a redacted ledger item — recording, never planning — to a persistent, resumable session under temp/qa/. Only when the operator says they are done does it review the full ledger and hand off to /plan. |
+| `/qa-assist` | Human-led QA assist loop — set up, then ride a rolling multi-observation intake session. The operator reports observations in any order; the agent enriches each (repro + root-cause file:line + coverage verdict for bugs; analysis + options + recommendation for enhancements), asks clarifying questions only when ambiguous, and appends a redacted ledger item — recording, never planning — to a persistent, resumable session under temp/qa/. Only when the operator says they are done does it review the full ledger and hand off to /mandrel-plan. |
 | `/qa-explore` | Agent-led exploratory-QA loop — the agent Plans a surface with an explicit static-vs-drive method choice, drives it (browser MCP or static), and captures ledger items read-only, then Triages — a bounded per-surface session, HITL-gated at every phase transition, routed through the shared dedup/coverage/classification/missing-test/redaction/session core under temp/qa/ |
 | `/qa-run` | Drive Gherkin scenarios through a real browser as an agent-driven QA sweep |
 

package/.agents/instructions.md

@@ -114,7 +114,7 @@ always wins regardless of tier.
 ## 2. FinOps & Token Budgeting (Economic Guardrails)
 
 Mandrel does not enforce live LLM spend; your host owns session quota.
-Fixed framework ceilings (the `/plan` context envelope, plan-time Story
+Fixed framework ceilings (the `/mandrel-plan` context envelope, plan-time Story
 sizing) **fail closed** naming what to trim:
 [`docs/execution-reference.md`](docs/execution-reference.md#finops--token-budgeting-economic-guardrails).
 
@@ -132,7 +132,7 @@ sizing) **fail closed** naming what to trim:
    `acceptance[]` / `verify[]`); prefer targeted retrieval over broad
    reads.
 2. **Plan First.** For non-trivial tasks (3+ steps or architectural
-   decisions), update the Story's `## Spec` via `/plan` before code.
+   decisions), update the Story's `## Spec` via `/mandrel-plan` before code.
 3. **Artifacts over Chat.** Write test/build/debug output to log
    files, not into chat.
 4. **Idempotency.** Scripts must be safe to run repeatedly.
@@ -174,10 +174,10 @@ prompted.
 The v2 ticket model is Story-only: `acceptance[]` / `verify[]` live
 inline plus the folded Tech Spec in `## Spec` (over-budget Specs fail
 closed — split or tighten; never write Specs under `docs/`). Optional
-`depends_on` edges order rare multi-Story runs, resolved by `/deliver`
+`depends_on` edges order rare multi-Story runs, resolved by `/mandrel-deliver`
 from live state; the `plan-run::<id>` label is filter metadata only.
 Commit subjects reference the Story via `(refs #<storyId>)`. There is no
-`type::epic` / `type::task` label; `/deliver` refuses tickets carrying an
+`type::epic` / `type::task` label; `/mandrel-deliver` refuses tickets carrying an
 `Epic: #N` footer.
 
 ---
@@ -192,7 +192,7 @@ anything under it.
 
 ## 7. Complexity-Aware Execution
 
-`/plan` sizes each Story as a **capability slice a frontier model
+`/mandrel-plan` sizes each Story as a **capability slice a frontier model
 delivers and self-verifies in one pass** — a broad footprint is normal
 when the change is cohesive (backstop: `DEFAULT_MODEL_CAPACITY` in
 `ticket-validator-sizing.js`); do not re-slice it into per-module

package/.agents/rules/changelog-style.md

@@ -3,7 +3,7 @@
 This rule governs the shape of per-release entries in the project CHANGELOG
 (typically `docs/CHANGELOG.md` or `CHANGELOG.md`). It applies whenever a
 release entry is authored or edited — most commonly inside Story #N's
-docs sweep before `/deliver` opens the release PR.
+docs sweep before `/mandrel-deliver` opens the release PR.
 
 The contract is **guidance-tier**: no automated gate fails a close when an
 entry drifts off-template. It still binds every author.
@@ -152,12 +152,12 @@ worktree cleanup.
 - **Shared-store worktrees.** Per-story worktrees link a shared
   `node_modules` store, so parallel waves no longer duplicate installs
   or leave residue that blocks reap.
-- **`/deliver` auto-invokes pre-merge gates** (code review, retro)
+- **`/mandrel-deliver` auto-invokes pre-merge gates** (code review, retro)
   inline. `--skip-code-review` is available as an override.
 - **Closure sweep covers Epic Health tickets** in addition to PRD and
   Tech Spec tickets.
 - **Stale-lock sweep** on the shared `.git/` directory runs at
-  `/deliver` start, clearing lock files left behind by interrupted
+  `/mandrel-deliver` start, clearing lock files left behind by interrupted
   operations.
 ```
 

package/.agents/rules/ci-remediation.md

@@ -31,7 +31,7 @@ exactly one of two ways, and no others:
    delivery's scope — a pre-existing flaky test, a runner/infra weakness, a
    framework-level environment gap. Open the issue with the `meta::framework-gap`
    label (see [`git-conventions.md`](git-conventions.md)) carrying **the run
-   link and the failure signature** so a later `/plan` Phase 0 sweep can act on
+   link and the failure signature** so a later `/mandrel-plan` Phase 0 sweep can act on
    it. Remediate this delivery only if the pre-existing defect is genuinely
    blocking it.
 

package/.agents/rules/git-conventions-reference.md

@@ -95,7 +95,7 @@ signature is worth naming:
 **Invariant (stated in the core): the delivering flow owns tidying the local
 checkout — reaping its own merged refs and fast-forwarding the base branch.
 `/git-cleanup` is a recovery tool, not a routine chore.** The outcome every
-delivering flow (`/deliver`, `/git-deliver`) guarantees, with the mechanics
+delivering flow (`/mandrel-deliver`, `/git-deliver`) guarantees, with the mechanics
 owned by `boot-sweep.js` / `git-cleanup.js`:
 
 - **`main` is fast-forwarded** by the flow itself in its cleanup phase, so the
@@ -104,7 +104,7 @@ owned by `boot-sweep.js` / `git-cleanup.js`:
 - **Merged local refs are reaped** at the next workflow boot's protected sweep
   (`boot-sweep.js`) — every local branch whose PR is already merged, skipping
   any candidate with unpushed work, a dirty worktree, or a still-open parent
-  ticket. `/plan` and `/git-deliver` widen the sweep's `--include` scope beyond
+  ticket. `/mandrel-plan` and `/git-deliver` widen the sweep's `--include` scope beyond
   the default `story-*` to their own branch namespaces at their boot call site.
 - **Content-merged branches are report-only.** A branch detected only via the
   weaker content-equivalence signal (`detectedBy: 'content-merged'` — content
@@ -149,13 +149,13 @@ different hazards:
 - **Recognition signature**: close aborts naming stray files in the main
   checkout that intersect the Story's diff. **Resolution**: relocate those
   edits under the worktree, restore the main checkout
-  (`git -C <main-repo> checkout -- <files>`), then re-run `/deliver <storyId>`.
+  (`git -C <main-repo> checkout -- <files>`), then re-run `/mandrel-deliver <storyId>`.
   Never `git reset --hard` or `git checkout --force` to clear the way.
 
 ## Meta Labels (Retrospective Signal Routing)
 
 Two `meta::*` labels route retrospective signals into durable substrates so
-the `/plan` Phase 0 fetcher (see
+the `/mandrel-plan` Phase 0 fetcher (see
 [`prior-feedback-fetcher.js`](../scripts/lib/feedback-loop/prior-feedback-fetcher.js))
 can surface open feedback issues to the planner. Both labels live in
 [`label-constants.js`](../scripts/lib/label-constants.js) under the

package/.agents/schemas/agentrc.schema.json

@@ -298,7 +298,7 @@
     },
     "planning": {
       "type": "object",
-      "description": "Inputs to `/plan`: risk escalation heuristics, ceremony-lite routing, and the cross-Story conflict-finding severity gates.",
+      "description": "Inputs to `/mandrel-plan`: risk escalation heuristics, ceremony-lite routing, and the cross-Story conflict-finding severity gates.",
       "properties": {
         "riskHeuristics": {
           "oneOf": [
@@ -440,7 +440,7 @@
     },
     "delivery": {
       "type": "object",
-      "description": "Everything `/deliver` and `single-story-close` consume: execution timeouts, worktree isolation, runner concurrency, docs freshness, signals, quality gates, merge/CI watch, review ceremony, and the feedback loop.",
+      "description": "Everything `/mandrel-deliver` and `single-story-close` consume: execution timeouts, worktree isolation, runner concurrency, docs freshness, signals, quality gates, merge/CI watch, review ceremony, and the feedback loop.",
       "properties": {
         "execution": {
           "type": "object",
@@ -521,12 +521,12 @@
         },
         "deliverRunner": {
           "type": "object",
-          "description": "Bounded-concurrency knob for the /deliver fan-out.",
+          "description": "Bounded-concurrency knob for the /mandrel-deliver fan-out.",
           "properties": {
             "concurrencyCap": {
               "type": "integer",
               "minimum": 1,
-              "description": "Maximum ready Stories dispatched by /deliver at once. Default 3. Moderate by design — keeps host-quota consumption predictable while allowing a small ready-set fan-out. Set 1 for strictly sequential delivery; raise further on hosts with adequate parallel-agent quota. See deliver.md for the sequencing model and throughput tradeoff.",
+              "description": "Maximum ready Stories dispatched by /mandrel-deliver at once. Default 3. Moderate by design — keeps host-quota consumption predictable while allowing a small ready-set fan-out. Set 1 for strictly sequential delivery; raise further on hosts with adequate parallel-agent quota. See deliver.md for the sequencing model and throughput tradeoff.",
               "default": 3
             },
             "footprintGuard": {
@@ -1628,7 +1628,7 @@
             },
             "navigability": {
               "type": "object",
-              "description": "Navigability lens + journey-suite config (Epic #4131, F2/F3/F1/F4). Read by audit-suite/selector.js (route globs) and /deliver's per-Story ceremony (journey suite). Opt-in: absent or empty routeGlobs degrades to a silent no-op.",
+              "description": "Navigability lens + journey-suite config (Epic #4131, F2/F3/F1/F4). Read by audit-suite/selector.js (route globs) and /mandrel-deliver's per-Story ceremony (journey suite). Opt-in: absent or empty routeGlobs degrades to a silent no-op.",
               "properties": {
                 "routeGlobs": {
                   "type": "array",
@@ -1648,7 +1648,7 @@
                 },
                 "journeySuite": {
                   "type": "string",
-                  "description": "Path or command for the per-persona journey suite /deliver's per-Story ceremony runs."
+                  "description": "Path or command for the per-persona journey suite /mandrel-deliver's per-Story ceremony runs."
                 }
               },
               "additionalProperties": false
@@ -1692,7 +1692,7 @@
         },
         "codeReview": {
           "type": "object",
-          "description": "Review-provider chain plus bounded-retry knobs for the /deliver code-review ceremony.",
+          "description": "Review-provider chain plus bounded-retry knobs for the /mandrel-deliver code-review ceremony.",
           "properties": {
             "providers": {
               "type": "array",
@@ -1780,7 +1780,7 @@
             "maxFixAttempts": {
               "type": "integer",
               "minimum": 0,
-              "description": "Maximum auto-fix retry attempts per finding in /deliver Phase 5 (code-review). 0 disables auto-fix. Default 3.",
+              "description": "Maximum auto-fix retry attempts per finding in /mandrel-deliver Phase 5 (code-review). 0 disables auto-fix. Default 3.",
               "default": 3
             },
             "maxFixScopeFiles": {
@@ -1792,7 +1792,7 @@
             "autoFixSeverity": {
               "type": "string",
               "enum": ["high", "medium"],
-              "description": "Severity threshold for on-branch remediation in /deliver Phase 5 (code-review). `medium` (default) routes 🔴/🟠/🟡 findings into the host-LLM focused-fix routing (Mediums batched per lens: one commit per lens, a single validation + rescan at the end) while 🟢 suggestions still graduate to follow-up issues; `high` reproduces the pre-4399 Critical/High-only routing. Hard cutover — no back-compat flag.",
+              "description": "Severity threshold for on-branch remediation in /mandrel-deliver Phase 5 (code-review). `medium` (default) routes 🔴/🟠/🟡 findings into the host-LLM focused-fix routing (Mediums batched per lens: one commit per lens, a single validation + rescan at the end) while 🟢 suggestions still graduate to follow-up issues; `high` reproduces the pre-4399 Critical/High-only routing. Hard cutover — no back-compat flag.",
               "default": "medium"
             }
           },
@@ -1921,7 +1921,9 @@
             },
             "advisoryAllowlist": {
               "type": "array",
-              "items": { "type": "string" },
+              "items": {
+                "type": "string"
+              },
               "description": "Story #5096. Check-run names exempt from blockOnAdvisoryFailure — a red run whose name matches exactly never blocks arming. Matching is exact; an unnamed run can never match and always blocks.",
               "default": []
             }
@@ -1985,7 +1987,7 @@
         },
         "environments": {
           "type": "object",
-          "description": "Deployment targets the QA harness can run against (Epic #4326). A map keyed by environment name (e.g. `local`, `staging`), each carrying its own `baseUrl`, its own per-environment sign-in seam (the same url-template/skill union as the top-level seam), and an optional `allowWrites` gate. resolveQaEnvironment selects one environment per invocation by name or by raw-URL origin match against `baseUrl`; `allowWrites` defaults to true only for the `local` environment. Replaces the retired top-level single `signInSeam`.",
+          "description": "Deployment targets the QA harness can run against (Epic #4326). A map keyed by environment name (e.g. `local`, `staging`), each carrying its own `baseUrl`, an optional per-environment sign-in seam, and an optional `allowWrites` gate. `signInSeam` is the union `{ urlTemplate }` (a dev impersonation route) or `{ skill }` (a skill id such as `stack/qa/acme-sso`, resolved against `.agents/skills/` then the consumer-writable `.agents/local/skills/` zone, and rejected loudly by resolveQaEnvironment when it resolves under neither); omit it entirely for a target with no sign-in seam. resolveQaEnvironment selects one environment per invocation by name or by raw-URL origin match against `baseUrl`; `allowWrites` defaults to true only for the `local` environment. Replaces the retired top-level single `signInSeam`.",
           "default": {
             "local": {
               "baseUrl": "http://localhost:3000",
@@ -1995,9 +1997,6 @@
             },
             "staging": {
               "baseUrl": "https://staging.example.test",
-              "signInSeam": {
-                "skill": "stack/qa/sign-in"
-              },
               "allowWrites": false
             }
           },
@@ -2048,7 +2047,7 @@
                 "type": "boolean"
               }
             },
-            "required": ["baseUrl", "signInSeam"],
+            "required": ["baseUrl"],
             "additionalProperties": false
           }
         },
@@ -2059,7 +2058,7 @@
               "credentialRef": "QA_ADMIN_CREDENTIAL"
             },
             "member": {
-              "signInSkill": "stack/qa/sign-in-member"
+              "credentialRef": "QA_MEMBER_CREDENTIAL"
             }
           },
           "oneOf": [

package/.agents/schemas/story-deliver-terminal.schema.json

@@ -21,7 +21,7 @@
     },
     "status": {
       "type": "string",
-      "description": "landed — the PR merged, the Story is agent::done, and the post-land tail was attempted. pending — a bounded wait expired with the PR still in flight; NO label was mutated and no merge.unlanded event was emitted, so the run is resumable via nextCommand. blocked — a classified hard block; the Story carries agent::blocked and blocked.blockClass names the class. failed — a phase crashed; phase names which one. escalated — the /deliver-light suitability gate refused an over-scope prompt under --yes; nothing was created and the session ENDS here, nextCommand naming the /plan invocation that owns the work instead.",
+      "description": "landed — the PR merged, the Story is agent::done, and the post-land tail was attempted. pending — a bounded wait expired with the PR still in flight; NO label was mutated and no merge.unlanded event was emitted, so the run is resumable via nextCommand. blocked — a classified hard block; the Story carries agent::blocked and blocked.blockClass names the class. failed — a phase crashed; phase names which one. escalated — the /deliver-light suitability gate refused an over-scope prompt under --yes; nothing was created and the session ENDS here, nextCommand naming the /mandrel-plan invocation that owns the work instead.",
       "enum": ["landed", "pending", "blocked", "failed", "escalated"]
     },
     "phase": {
@@ -173,7 +173,7 @@
     },
     "nextCommand": {
       "type": ["string", "null"],
-      "description": "The single command that advances this work from where it stopped, or null when status === \"landed\" and nothing remains. Shares its vocabulary with deliver-recover.js so recovery and normal resumption speak one language. For status escalated it is the /plan invocation the operator runs in a FRESH session — the one case where the command is a slash command rather than a script, because the work needs planning, not resumption.",
+      "description": "The single command that advances this work from where it stopped, or null when status === \"landed\" and nothing remains. Shares its vocabulary with deliver-recover.js so recovery and normal resumption speak one language. For status escalated it is the /mandrel-plan invocation the operator runs in a FRESH session — the one case where the command is a slash command rather than a script, because the work needs planning, not resumption.",
       "minLength": 1
     },
     "elapsedSeconds": { "type": "number", "minimum": 0 },

package/.agents/schemas/validation-evidence.schema.json

@@ -2,7 +2,7 @@
   "$schema": "https://json-schema.org/draft/2020-12/schema",
   "$id": "validation-evidence",
   "title": "Validation Evidence",
-  "description": "Per-scope record of which validation gates have passed against which commit SHA. Written by lib/validation-evidence.js under the per-Epic temp tree at temp/run-<id>/validation-evidence.json (Epic-scoped) or temp/run-<id>/stories/story-<storyId>/validation-evidence.json (Story-scoped). Standalone Stories (no parent Epic) use a storyId-anchored keyspace at temp/standalone/stories/story-<storyId>/validation-evidence.json. All paths are gitignored via temp/. Consumed by close-validation, epic-code-review, the acceptance self-eval critic, and /deliver Phase 3 (close-validation) to skip identical re-runs against an already-validated tree. The `storyId` field carries the scope id and equals the epic id for Epic-scoped records.",
+  "description": "Per-scope record of which validation gates have passed against which commit SHA. Written by lib/validation-evidence.js under the per-Epic temp tree at temp/run-<id>/validation-evidence.json (Epic-scoped) or temp/run-<id>/stories/story-<storyId>/validation-evidence.json (Story-scoped). Standalone Stories (no parent Epic) use a storyId-anchored keyspace at temp/standalone/stories/story-<storyId>/validation-evidence.json. All paths are gitignored via temp/. Consumed by close-validation, epic-code-review, the acceptance self-eval critic, and /mandrel-deliver Phase 3 (close-validation) to skip identical re-runs against an already-validated tree. The `storyId` field carries the scope id and equals the epic id for Epic-scoped records.",
   "type": "object",
   "required": ["storyId", "schemaVersion", "records"],
   "properties": {

package/.agents/scripts/acceptance-eval.js

@@ -20,7 +20,7 @@
  *      and the resolved, undisableable round cap
  *      (`delivery.acceptanceEval.maxRounds`, clamped to `[1, ceiling]`).
  *   3. Emit one per-criterion `acceptance-eval` signal into the retro /
- *      feedback substrate so the retro and `/plan` Phase 0 feedback
+ *      feedback substrate so the retro and `/mandrel-plan` Phase 0 feedback
  *      fetch can see which acceptance items needed rework and the round
  *      count.
  *   4. Print a single JSON envelope and exit:

package/.agents/scripts/apply-quality-bootstrap.js

@@ -20,7 +20,7 @@
  *
  * Story #5007 retired the second step. `migrateBaselinesLayout` relocated
  * per-Epic ratchet snapshots into `temp/epic/<id>/baselines/` on the contract
- * that `/deliver` reaps that namespace on merge — a mechanism the Story-only
+ * that `/mandrel-deliver` reaps that namespace on merge — a mechanism the Story-only
  * v2 model deleted, so the migration moved dead data into a namespace no code
  * path writes, reads, or reaps. Its one residual hygiene value (getting the
  * committed `baselines/epic/` tree out of version control) survives as

package/.agents/scripts/audit-to-stories.js

@@ -13,7 +13,7 @@
  *     stdout when --json is set).
  *
  *   --emit-plan-seed --plan <plan.json> --out <path>
- *     Read the plan envelope from disk, render the `/plan --seed`
+ *     Read the plan envelope from disk, render the `/mandrel-plan --seed`
  *     seed markdown, persist to --out.
  *
  *   --emit-stories --plan <plan.json>
@@ -844,7 +844,7 @@ runAsCli(import.meta.url, main, {
     flags: [
       ['--scan', 'Print the grouped, deduplicated plan as JSON.'],
       ['--auto', 'Run the full scan → file pipeline and print the summary.'],
-      ['--emit-plan-seed', 'Emit a /plan --seed-file document.'],
+      ['--emit-plan-seed', 'Emit a /mandrel-plan --seed-file document.'],
       ['--emit-stories', 'Emit the Story drafts as JSON.'],
       [
         '--wire-edges',

package/.agents/scripts/check-doc-links.js

@@ -19,7 +19,7 @@
 //
 //   3. No active doc mentions any retired slash command. The retired-command
 //      blocklist is seeded with `agents-bootstrap-github`,
-//      `single-story-plan` (renamed to `/plan`), and `mandrel`
+//      `single-story-plan` (renamed to `/mandrel-plan`), and `mandrel`
 //      (retired in favor of the generated `.agents/docs/workflows.md`
 //      catalog) and takes precedence over the workflow-resolution check —
 //      a retired token is always a non-zero exit even if a stale workflow
@@ -61,6 +61,18 @@ export const RETIRED_COMMANDS = new Set([
   'git-merge-pr',
 ]);
 
+// Command spellings a *historical* record may still name, keyed by the file
+// allowed to name them. A decisions log that cannot quote the name a command
+// had is a broken record: an ADR describes the world as it was, so freezing
+// its prose is the point. Scoped per-file and per-token rather than
+// allowlisted globally — everywhere else these are simply wrong, and a typo
+// like `/mandrl-plan` must still fail here. Story #5126 renamed `/plan` →
+// `/mandrel-plan` and `/deliver` → `/mandrel-deliver`; the ADRs that decided
+// the Story-only model still name them as they were called then.
+export const SUPERSEDED_COMMAND_SPELLINGS = new Map([
+  ['docs/decisions.md', new Set(['plan', 'deliver'])],
+]);
+
 // Tokens that look like `/foo` in prose but are not slash commands. Tokens
 // are stored WITHOUT the leading slash. The list focuses on common URL path
 // fragments and on-disk path roots that appear in tutorial prose. The
@@ -379,6 +391,20 @@ export function extractSlashTokens(masked) {
 
 // --- Per-file check --------------------------------------------------------
 
+/**
+ * The slash tokens `relFile` may name without resolving to a workflow: the
+ * global allowlist, plus any superseded spelling this particular file is
+ * allowed to quote.
+ *
+ * @param {string} relFile Repo-relative path of the file being checked.
+ * @returns {Set<string>} Tokens to skip, stored without the leading slash.
+ */
+function slashAllowlistFor(relFile) {
+  const superseded = SUPERSEDED_COMMAND_SPELLINGS.get(relFile);
+  if (!superseded) return SLASH_ALLOWLIST;
+  return new Set([...SLASH_ALLOWLIST, ...superseded]);
+}
+
 export function checkFile(absPath, repoRoot) {
   const violations = [];
   const source = fs.readFileSync(absPath, 'utf8');
@@ -454,14 +480,16 @@ export function checkFile(absPath, repoRoot) {
     }
   }
 
-  // 3. Slash-command resolution. Skip retired hits (already reported) and
-  //    allowlisted tokens. A command is valid if it resolves to a top-level
+  // 3. Slash-command resolution. Skip retired hits (already reported),
+  //    allowlisted tokens, and a superseded spelling in the one file allowed
+  //    to quote it (SUPERSEDED_COMMAND_SPELLINGS). A command is valid if it resolves to a top-level
   //    workflow file OR to a helpers/ module (helpers are not projected into
   //    the `.claude/commands/` tree but are still legitimate named workflows
   //    that parent workflows invoke by prose reference).
+  const slashAllowlist = slashAllowlistFor(relFile);
   for (const { token, line } of slashTokens) {
     if (RETIRED_COMMANDS.has(token)) continue;
-    if (SLASH_ALLOWLIST.has(token)) continue;
+    if (slashAllowlist.has(token)) continue;
     // Namespaced loop commands (`/loops:<name>`, Story #4289) resolve to a
     // loop unit under `.agents/workflows/loops/<name>.md`. Split on the `:`
     // and resolve the namespaced path rather than a flat `loops:<name>.md`.

package/.agents/scripts/check-test-temp-hygiene.js

@@ -422,7 +422,7 @@ export function findReservedIdStreamFiles(tempDir) {
  * the **repository-root** temp tree (Story #4892).
  *
  * Resolution matters more than it looks: every writer anchors a relative
- * `tempRoot` to the *main checkout* (so a Story worktree and its `/deliver`
+ * `tempRoot` to the *main checkout* (so a Story worktree and its `/mandrel-deliver`
  * host converge on one ledger), so a guard that scanned `cwd` would scan an
  * empty worktree tree and pass vacuously on the very tree it is meant to
  * protect. `resolveRoot` is the injection seam for tests.

package/.agents/scripts/check-workflow-cli-lint.js

@@ -136,7 +136,7 @@ export function toParagraphs(lines) {
  *      heading (inclusive) — i.e. the section is *about* that script, so the
  *      table is restating its surface.
  *
- * A slash command's own argument table (`/plan`, `/deliver`) has no script
+ * A slash command's own argument table (`/mandrel-plan`, `/mandrel-deliver`) has no script
  * behind it — nothing owns those flags but the workflow prose itself — so
  * condition 2 leaves it alone by design.
  *

package/.agents/scripts/deliver-light.js

@@ -5,7 +5,7 @@
  *
  * A **thin entry point, not a second delivery engine.** It runs the
  * suitability gate, authors a minimal receipt `type::story`, and then hands off
- * to the SAME engine scripts `/deliver` uses:
+ * to the SAME engine scripts `/mandrel-deliver` uses:
  *
  *   suitability gate  →  inline receipt Story  →  single-story-init.js
  *     →  (agent implements + self-evals)  →  diff backstop
@@ -38,9 +38,9 @@
  * envelope with status `escalated` and **ends the session**. Before that it was
  * an ordinary gate envelope plus exit 2 — a warning a caller could walk past,
  * and one mandrel-bench 2.13.0 light-arm run did exactly that: it read the
- * escalation, invoked `/plan` in the same session, and delivered. In-session
+ * escalation, invoked `/mandrel-plan` in the same session, and delivered. In-session
  * planning under-decomposed (ONE Story against the scenario's 3-5 contract,
- * where a fresh `/plan` session on the identical seed authored four), so
+ * where a fresh `/mandrel-plan` session on the identical seed authored four), so
  * escalation silently produced the outcome the guard exists to prevent.
  * {@link module:lib/orchestration/story-deliver-terminal.buildEscalationTerminal}
  * carries the guarantees the schema then enforces.
@@ -88,7 +88,7 @@ Usage:
   deliver-light.js --backstop --story <id>
 
 The thin /deliver-light entry point: suitability gate → inline receipt Story →
-the same single-story-init.js / single-story-close.js engine /deliver uses.
+the same single-story-init.js / single-story-close.js engine /mandrel-deliver uses.
 
 The gate judges EFFORT and RISK, not artifact counts: N instances of one
 mechanical edit is one kind at N sites. It rejects only clearly-epic work; the
@@ -102,9 +102,9 @@ Gate options:
   --kinds <csv>      Distinct KINDS of change (default: one per assumption, so
                      N same-shaped edits count once).
   --magnitude <m>    Coarse effort bucket: trivial | moderate | substantial
-                     (default moderate; substantial routes to /plan).
+                     (default moderate; substantial routes to /mandrel-plan).
   --uncertainty <u>  determined (the request fixes the shape) | needs-design
-                     (default determined; needs-design routes to /plan).
+                     (default determined; needs-design routes to /mandrel-plan).
   --route <r>        Ledgered model verdict route: lite | full.
   --reason <text>    Recorded reason for a lite verdict (required for lite).
   --amends <#id>     Mark this as an amendment of an existing issue.
@@ -125,7 +125,7 @@ Backstop options:
                      change's IMPLEMENTATION half by magnitude (changed lines +
                      file sprawl); test/doc/baseline companions are exempt from
                      the counts but still matched for sensitive paths. A block
-                     emits a nextCommand recycling the receipt through /plan.
+                     emits a nextCommand recycling the receipt through /mandrel-plan.
   --story <id>       Story issue number whose story-<id> branch to diff.
 
   --pretty           Pretty-print the JSON envelope.
@@ -280,7 +280,7 @@ export async function createLightReceipt({
 }
 
 /**
- * The engine hand-off — the SAME scripts `/deliver` uses. Named here as
+ * The engine hand-off — the SAME scripts `/mandrel-deliver` uses. Named here as
  * commands, never reimplemented: this is the whole of deliver-light's
  * relationship to worktree/branch/lease/PR/merge mechanics.
  *
@@ -397,7 +397,7 @@ export async function runGateMode(values, deps = {}) {
   if (values.yes === true && hasOperatorOverride(values)) {
     process.stderr.write(HELP);
     throw new Error(
-      '[deliver-light] --operator-proceed-light is attended-only and cannot be combined with --yes: an unattended run has no operator whose answer this is, and over-scope must fail closed to /plan',
+      '[deliver-light] --operator-proceed-light is attended-only and cannot be combined with --yes: an unattended run has no operator whose answer this is, and over-scope must fail closed to /mandrel-plan',
     );
   }
 
@@ -423,7 +423,7 @@ export async function runGateMode(values, deps = {}) {
     });
     emitTerminalFn(envelope);
     Logger.warn(
-      `[deliver-light] ESCALATED to /plan — this session ENDS here; run ${envelope.nextCommand} in a FRESH session: ${gate.outcome.reasons.join('; ')}`,
+      `[deliver-light] ESCALATED to /mandrel-plan — this session ENDS here; run ${envelope.nextCommand} in a FRESH session: ${gate.outcome.reasons.join('; ')}`,
     );
     return exitCodeForTerminal(envelope);
   }

package/.agents/scripts/deliver-recover.js

@@ -12,7 +12,7 @@
  * is the thing they cannot act on.
  *
  * The strand this exists for above all others is the **merged-but-label-stale**
- * Story: a `/deliver` re-run refuses it outright, because
+ * Story: a `/mandrel-deliver` re-run refuses it outright, because
  * `single-story-init.js` hard-errors on an already-closed Story. Before this
  * surface, that Story had no automated way back.
  *

package/.agents/scripts/drain-pending-cleanup.js

@@ -8,7 +8,7 @@
  * any still-stuck entries by enumerating the processes holding handles
  * inside the worktree path and terminating them.
  *
- * Invoked by `/deliver` and `/plan`
+ * Invoked by `/mandrel-deliver` and `/mandrel-plan`
  * (via `drainPendingCleanupAtBoot` → `worktree-sweep.js`), and
  * `story-close` so the pending-cleanup ledger drains automatically
  * across the sprint lifecycle. Operators can also run it standalone:

package/.agents/scripts/evidence-gate.js

@@ -3,7 +3,7 @@
 /**
  * evidence-gate.js — evidence-aware wrapper around a single shell gate.
  *
- * Tech Spec #819 §"Evidence record (Story 7)" — `/deliver` Phase 3
+ * Tech Spec #819 §"Evidence record (Story 7)" — `/mandrel-deliver` Phase 3
  * (close-validation) runs `npm run lint` and `npm test` against the Epic
  * branch before opening the PR.
  * If the same gate has already passed against the current `git rev-parse