@entelligentsia/forgecli 1.0.21 → 1.0.36

package/dist/forge-payload/.base-pack/commands/new-sprint.md

@@ -3,14 +3,14 @@ name: new-sprint
 description: Elicit and structure requirements for a new sprint
 ---
 
-# /{{PREFIX}}:new-sprint
+# /forge:new-sprint
 
 Read the new-sprint workflow and follow it.
 
 ## Locate the Forge plugin
 
 ```
-FORGE_ROOT: !`echo "${CLAUDE_PLUGIN_ROOT}"`
+FORGE_ROOT: !`echo "${CLAUDE_PLUGIN_ROOT:-$(pwd)/.forge}"`
 ```
 
 ## Execute

package/dist/forge-payload/.base-pack/commands/plan-sprint.md

@@ -3,14 +3,14 @@ name: plan-sprint
 description: Decompose sprint requirements into tasks with dependencies
 ---
 
-# /{{PREFIX}}:plan-sprint
+# /forge:plan-sprint
 
 Read the plan-sprint workflow and follow it.
 
 ## Locate the Forge plugin
 
 ```
-FORGE_ROOT: !`echo "${CLAUDE_PLUGIN_ROOT}"`
+FORGE_ROOT: !`echo "${CLAUDE_PLUGIN_ROOT:-$(pwd)/.forge}"`
 ```
 
 ## Execute

package/dist/forge-payload/.base-pack/commands/plan.md

@@ -3,14 +3,14 @@ name: plan
 description: Design and document the implementation plan for a task
 ---
 
-# /{{PREFIX}}:plan
+# /forge:plan
 
 Read the plan workflow and follow it.
 
 ## Locate the Forge plugin
 
 ```
-FORGE_ROOT: !`echo "${CLAUDE_PLUGIN_ROOT}"`
+FORGE_ROOT: !`echo "${CLAUDE_PLUGIN_ROOT:-$(pwd)/.forge}"`
 ```
 
 ## Execute

package/dist/forge-payload/.base-pack/commands/retro.md

@@ -3,14 +3,14 @@ name: retro
 description: Produce sprint retrospective and lessons-learned document
 ---
 
-# /{{PREFIX}}:retro
+# /forge:retro
 
 Read the retro workflow and follow it.
 
 ## Locate the Forge plugin
 
 ```
-FORGE_ROOT: !`echo "${CLAUDE_PLUGIN_ROOT}"`
+FORGE_ROOT: !`echo "${CLAUDE_PLUGIN_ROOT:-$(pwd)/.forge}"`
 ```
 
 ## Execute

package/dist/forge-payload/.base-pack/commands/review-code.md

@@ -3,14 +3,14 @@ name: review-code
 description: Code quality review of a completed task implementation
 ---
 
-# /{{PREFIX}}:review-code
+# /forge:review-code
 
 Read the review-code workflow and follow it.
 
 ## Locate the Forge plugin
 
 ```
-FORGE_ROOT: !`echo "${CLAUDE_PLUGIN_ROOT}"`
+FORGE_ROOT: !`echo "${CLAUDE_PLUGIN_ROOT:-$(pwd)/.forge}"`
 ```
 
 ## Execute

package/dist/forge-payload/.base-pack/commands/review-plan.md

@@ -3,14 +3,14 @@ name: review-plan
 description: Architectural review of a task implementation plan
 ---
 
-# /{{PREFIX}}:review-plan
+# /forge:review-plan
 
 Read the review-plan workflow and follow it.
 
 ## Locate the Forge plugin
 
 ```
-FORGE_ROOT: !`echo "${CLAUDE_PLUGIN_ROOT}"`
+FORGE_ROOT: !`echo "${CLAUDE_PLUGIN_ROOT:-$(pwd)/.forge}"`
 ```
 
 ## Execute

package/dist/forge-payload/.base-pack/commands/run-sprint.md

@@ -3,14 +3,14 @@ name: run-sprint
 description: Execute all tasks in a sprint (sequential or parallel)
 ---
 
-# /{{PREFIX}}:run-sprint
+# /forge:run-sprint
 
 Read the run-sprint workflow and follow it.
 
 ## Locate the Forge plugin
 
 ```
-FORGE_ROOT: !`echo "${CLAUDE_PLUGIN_ROOT}"`
+FORGE_ROOT: !`echo "${CLAUDE_PLUGIN_ROOT:-$(pwd)/.forge}"`
 ```
 
 ## Execute

package/dist/forge-payload/.base-pack/commands/run-task.md

@@ -3,14 +3,14 @@ name: run-task
 description: Orchestrate the full plan→implement→review→approve pipeline for a task
 ---
 
-# /{{PREFIX}}:run-task
+# /forge:run-task
 
 Read the run-task workflow and follow it.
 
 ## Locate the Forge plugin
 
 ```
-FORGE_ROOT: !`echo "${CLAUDE_PLUGIN_ROOT}"`
+FORGE_ROOT: !`echo "${CLAUDE_PLUGIN_ROOT:-$(pwd)/.forge}"`
 ```
 
 ## Execute

package/dist/forge-payload/.base-pack/commands/validate.md

@@ -3,14 +3,14 @@ name: validate
 description: Validate that a task implementation satisfies acceptance criteria
 ---
 
-# /{{PREFIX}}:validate
+# /forge:validate
 
 Read the validate workflow and follow it.
 
 ## Locate the Forge plugin
 
 ```
-FORGE_ROOT: !`echo "${CLAUDE_PLUGIN_ROOT}"`
+FORGE_ROOT: !`echo "${CLAUDE_PLUGIN_ROOT:-$(pwd)/.forge}"`
 ```
 
 ## Execute

package/dist/forge-payload/.base-pack/workflows/_fragments/event-emission-schema.md

@@ -4,6 +4,10 @@
      orchestrator stitches runtime telemetry + judgement into the canonical
      event and emits it. Referenced by meta-orchestrate.md and meta-fix-bug.md.
 
+     Companion: _fragments/event-vocabulary.md owns the `type` token
+     vocabulary (phase→type tables for task/bug/sprint events). This fragment
+     owns WHO emits; that one owns WHAT token.
+
      PLAN-11 / SLICE-2 (2026-05-14): the LLM no longer hand-builds event JSON.
      Runtime facts (model, provider, eventId, timestamps, iteration, tokens)
      are owned by the orchestrator, never the subagent. The subagent only

package/dist/forge-payload/.base-pack/workflows/_fragments/event-vocabulary.md

@@ -0,0 +1,88 @@
+# Fragment: Event Type Vocabulary
+
+<!-- Canonical phase→type vocabulary for store events (forge-engineering#39).
+     This fragment OWNS the `type` token vocabulary; `schemas/event.schema.json`
+     mirrors it. Any vocabulary change lands here first, then in the schema enum
+     (test-first via tools/__tests__/event-schema-variants.test.cjs), then in
+     emitters (forge-cli orchestrators, wfl JS drivers, meta workflows).
+
+     Companion: _fragments/event-emission-schema.md owns WHO emits (orchestrator
+     vs subagent field ownership). This fragment owns WHAT token each phase emits.
+
+     Invariant: every token emitted by any surface MUST appear in the schema
+     enum, and every enum token MUST have a named emitter below. Dead tokens are
+     removed (bug-fixed was retired by forge-engineering#39 — defined, never
+     emitted by anything). -->
+
+## Rules
+
+1. **Emitted tokens ⊆ schema enum.** An emitter never invents a token. If a new
+   phase outcome needs a token, add it here + the schema enum first.
+2. **`type` is optional** on events. An untyped event is valid (task-pipeline
+   events from forge-cli run-task are currently untyped). When a `type` IS set,
+   it must come from the tables below.
+3. **Kebab-case for lifecycle tokens.** Underscore names are reserved for the
+   `friction` and `skill_usage` event families.
+4. **Conditional fields.** Typed events trigger schema conditionals — see the
+   "Requires" column. Driver-emitted skip events have no model/provider; emit
+   the literal `"n/a"` for both (never guess a model string — see
+   `_fragments/event-emission-schema.md` §Why no example record here).
+5. **Skip reasons ride in `notes`.** `reason` is not a declared event property
+   (`additionalProperties: false` rejects it).
+
+## Task pipeline (orchestrate_task / run-task / wfl:run-task)
+
+| Phase | Pass token | Fail token | Requires |
+|---|---|---|---|
+| plan | `task-planned` | `task-planned` | taskId, phase, iteration |
+| review-plan | `plan-approved` | `review-failed` | taskId, phase, iteration |
+| implement | `task-implemented` | `task-implemented` | taskId, phase, iteration |
+| review-code | `review-passed` | `review-failed` | taskId, phase, iteration |
+| validate | `task-validated` | `review-failed` | taskId, phase, iteration |
+| approve | `task-approved` | `review-failed` | taskId, phase, iteration |
+| commit | `task-committed` | `task-committed` | taskId, phase, iteration |
+
+`plan-complete` is a legacy alias accepted by the enum for plan-phase events;
+new emitters use `task-planned`.
+
+## Bug pipeline (fix_bug / fix-bug / wfl:fix-bug)
+
+| Phase | Pass token | Fail token | Requires |
+|---|---|---|---|
+| pre-loop skip | `bug-skipped` | — | bugId (no phase/iteration; model/provider `"n/a"`) |
+| triage | `bug-triaged` | `bug-triaged` | bugId, phase, iteration |
+| plan-fix | `fix-planned` | `fix-planned` | bugId, phase, iteration |
+| review-plan | `fix-review-passed` | `fix-review-failed` | bugId, phase, iteration |
+| implement | `fix-implemented` | `fix-implemented` | bugId, phase, iteration |
+| review-code | `fix-code-review-passed` | `fix-code-review-failed` | bugId, phase, iteration |
+| approve | `fix-approved` | `fix-revision-requested` | bugId, phase, iteration |
+| commit | `bug-committed` | `bug-commit-failed` | bugId, phase, iteration |
+
+Non-review phases emit their single token regardless of outcome (the verdict
+field carries the judgement); review phases (review-plan, review-code, approve)
+select pass/fail on `verdict == "revision"`.
+
+## Sprint grain (run_sprint / run-sprint / wfl:run-sprint)
+
+| Moment | Token | Requires |
+|---|---|---|
+| before wave loop | `sprint-start` | sprintId (taskCount optional) |
+| before each task dispatch | `task-dispatch` | taskId (convention; phase/iteration carried but not schema-enforced) |
+| sprint finished | `sprint-complete` | taskCount, completedTaskIds, verdict |
+| sprint aborted | `sprint-halted` | haltedAtTaskIndex, haltedAtTaskId, lastError |
+
+## Other families
+
+| Token | Emitter | Spec |
+|---|---|---|
+| `friction` | any persona, drained by orchestrator | `_fragments/friction-emit.md` |
+| `skill_usage` | forge-cli skill-curation telemetry | `event.schema.json` skill_usage conditional |
+
+## Out of scope (known follow-ups)
+
+- **Feature events** have no lifecycle tokens; feature-related events are
+  emitted untyped. Defining a feature vocabulary is a future change to this
+  fragment + the enum.
+- **Task-pipeline typed emission in forge-cli** — run-task currently emits
+  untyped events (valid under Rule 2); adopting the task table above is
+  forward work tracked in forge-engineering#39 step 3.

package/dist/forge-payload/.base-pack/workflows/collator_agent.md

@@ -75,12 +75,11 @@ Never set `FORGE_SKIP_WRITE_VALIDATION=1` — operator-only emergency switch.
      }
      ```
      The orchestrator reads this file directly to compose the collation event narrative. Do NOT call `set-summary` to register it — that would mutate the store in violation of Iron Law 1.
-   - Invoke Tomoshibi via Skill tool to refresh KB and workflow links in agent
-     instruction files:
-     ```
-     Use the Skill tool:
-       skill: "forge:refresh-kb-links"
-     ```
+   - KB link refresh (best-effort; skip if unavailable):
+     When running standalone in the Claude Code TUI, invoke via the Skill tool
+     (`skill: "forge:refresh-kb-links"`).
+     When running as a subagent within forge-cli (Pi runtime), the TS orchestrator
+     calls `runRefreshKbLinks` directly after this phase — skip this step.
 ```
 
 <!-- See _fragments/generation-instructions.md for Generation Instructions template -->

package/dist/forge-payload/.base-pack/workflows/commit_task.md

@@ -27,6 +27,8 @@ deps:
 - Commit only the artifacts produced for this task; do not sweep unrelated working-tree changes into the commit. The commit boundary mirrors the task boundary.
 - Read `.forge/personas/engineer.md` first; print the persona identity line (emoji, name, tagline) to stdout before any other tool use.
 - All store I/O via `forge_store` (or `node .forge/tools/store-cli.cjs`). Never edit `.forge/store/*.json` directly.
+- **Never run `git add`/`git commit`/`git reset` yourself** — `commit-task.cjs` owns staging, boundary checks, committing, and the terminal transition (#40). Your judgement input is the message.
+- **Commit writes NO summary** (`commit` ∉ `VALID_SUMMARY_PHASES` — any `set-summary` is rejected); the tool's terminal `update-status` is this phase's only store write.
 
 ## Store-Write Verification
 
@@ -36,48 +38,49 @@ deps:
 
 ```
 
-0a. Pre-flight Gate Check:
-   - **Entity-mode resolution:** read the kickoff arguments. `--task {id}` → `entity_kind = "task"`, `record_id = {id}`. `--bug {id}` → `entity_kind = "bug"`, `record_id = {id}`. All store-cli calls below substitute `{entity_kind}` and `{record_id}` for the literal "task"/{taskId} placeholders.
-   - Run: `node .forge/tools/preflight-gate.cjs --phase commit --{entity_kind} {record_id}`
-   - Exit 1 (gate failed) → print stderr and HALT. Do not proceed; do not attempt to produce the artifact.
-   - Exit 2 (misconfiguration) → print stderr and HALT.
-   - Exit 0 → continue.
+0. Entity-mode resolution:
+   - Read the kickoff arguments. `--task {id}` → `entity_kind = "task"`, `record_id = {id}`. `--bug {id}` → `entity_kind = "bug"`, `record_id = {id}`.
 
-0b. Pipeline Step Guard (user-invoked state check):
-   - If `--force` is present in the invocation arguments, skip this step entirely.
-   - If `entity_kind == "bug"`, skip this step entirely (bug state is managed by meta-fix-bug.md).
-   - Read current task state:
-     `node .forge/tools/store-cli.cjs read task {record_id} --json`
-   - Extract the `status` field from the JSON output.
-   - Allowed states for this phase: `approved`.
-   - If the current status is NOT in the allowed set:
-     Print the following and HALT (do not proceed):
-     `× Task {record_id} is in state '{status}' — /forge:approve must complete first. To run the full pipeline: /forge:run-task {record_id}`
+1. Inspect ONCE (message material only — #40 batched-inspection rule):
+   - One `git diff --stat`; at most ONE combined `git diff` if the message needs detail.
+     Never per-file diffs, never repeated `git status` — each extra turn re-pays full context.
+   - Staging is NOT your decision — the tool derives it from the store record.
 
-1. Load Context:
-   - Read the record manifest (task or bug, per entity_kind).
-   - Read ARCHITECT_APPROVAL.md by kind — never construct the path:
-     `forge_artifact({ command:"read", entity:"{entity_kind}", entityId:"{record_id}", artifact:"architect-approval" })`
+2. Craft the commit message:
+   - Follow project conventions; include the record ID ({taskId} / {bugId}) in the subject.
+   - `Co-authored-by:` trailer from the host runtime: Claude Code →
+     `Co-authored-by: Claude <noreply@anthropic.com>`; pi / Ollama / other →
+     `Co-authored-by: {modelId} <noreply@{provider}.ai>` from the session's `provider` and
+     `modelId`; if unresolvable, omit rather than guess. Never hardcode
+     `Claude Opus 4.6 <noreply@anthropic.com>` (forge#82 regression).
+   - Git's configured `user.name`/`user.email` own authorship; never `--author`.
 
-2. Staging:
-   - Stage all record-related artifacts and the code changes:
-     - Task mode: PLAN.md, PROGRESS.md, REVIEW files, ARCHITECT_APPROVAL.md, and the implementation diff under the task directory plus modified source files.
-     - Bug mode: BUG_FIX_PLAN.md (Path B only — absent on Path A), TRIAGE.md, PROGRESS.md, REVIEW files, ARCHITECT_APPROVAL.md, the regression test, and the implementation diff.
-   - Verify no unrelated files are staged.
+3. Commit via the tool — ONE call:
+   - If the `forge_commit` named tool is available (forgecli): call it —
+     `forge_commit({ entity:"{entity_kind}", id:"{record_id}", message:"<message>", trailer:"<line>" })`.
+     Never pass the message through a bash string when the typed tool exists.
+   - Otherwise (Claude Code): `node .forge/tools/commit-task.cjs --{entity_kind} {record_id} --message "<message>" [--trailer "<Co-authored-by line>"]`
+   - The tool owns the choreography: preflight gate (`preflight-gate.cjs --phase commit`
+     internally), status precondition (task `approved` / bug `in-progress` — wrong-state runs
+     halt with `× {record_id} is in state '{status}' …; /forge:approve must complete first`),
+     staging (artifact dir + `summaries.implementation.files_changed` provenance),
+     commit-boundary guard (aborts on a pre-staged index), `git commit`, terminal transition
+     (task → `committed`; bug → `fixed`, the ONLY post-triage `bug.status` write).
+   - On `no files_changed provenance` warning: ONE `git status --porcelain`, then re-run the
+     tool with `--also <path>` per source file. Never manual `git add`.
+   - Success → JSON with `ok:true`. `committed:true` carries `sha` + `staged`;
+     `committed:false, reason:"nothing-to-commit"` is ALSO success (fix already at HEAD /
+     staging set clean — the tool still sealed the record's terminal status). Do not
+     "fix" a no-op by staging things yourself.
+   - Failure (exit 1 / ok:false) → print stderr and HALT — no manual staging, no
+     `git reset`, no `--force` retry (operator-gated). Tool file missing → HALT;
+     instruct `/forge:update` + `/forge:rebuild tools`.
+   - NEVER commit before the tool reports `ok: true` — the premature-commit/reset/redo loop
+     is forbidden.
 
-3. Commit:
-   - Create a commit with a message following project conventions.
-   - Include the record ID in the commit message: task ID for task mode, bug ID for bug mode.
-   - Append a `Co-authored-by:` trailer crediting the AI assistant that actually ran the session. Resolve the identity from the host runtime: on Claude Code use `Co-authored-by: Claude <noreply@anthropic.com>`; on pi / Ollama / any other runtime use `Co-authored-by: {modelId} <noreply@{provider}.ai>` derived from the session's `provider` and `modelId` (e.g. `Co-authored-by: glm-5.1:cloud <noreply@ollama.ai>`); if neither is resolvable, omit the trailer rather than guess. Do NOT hardcode `Claude Opus 4.6 <noreply@anthropic.com>` — that literal is rejected as a regression of forge#82 (commits authored under the wrong model).
-   - Let git's configured `user.name` / `user.email` own the commit author; never pass `--author` to override it.
-
-4. Store Finalization:
-   - Transitions:
-     - **Task mode** — `approved → committed` (terminal): `node .forge/tools/store-cli.cjs update-status task {taskId} status committed`
-     - **Bug mode** — `in-progress → fixed` (terminal): `node .forge/tools/store-cli.cjs update-status bug {bugId} status fixed`. This is the ONLY phase in the bug pipeline that writes `bug.status` post-triage (see `meta-fix-bug.md § Iron Laws #2`). Do NOT write `approved` or `verified` — those values are vestigial enum members slated for removal.
-
-5. Finalize:
-   - **Do NOT emit a phase event yourself.** The orchestrator owns event emission — it composes the canonical event from runtime telemetry (model, provider, tokens, wall times) plus the SUMMARY you write in the next step. Subagents that call `store-cli emit` for phase events hallucinate runtime facts (see Plan 11 / Slice 2). Write the SUMMARY and return.
+4. Finalize:
+   - No summary, no `set-summary` (see Iron Laws). **Do NOT emit a phase event yourself** —
+     the orchestrator owns event emission. Return the tool's JSON result as your phase output.
 ```
 
 <!-- See _fragments/generation-instructions.md for Generation Instructions template -->

package/dist/forge-payload/.base-pack/workflows/implement_plan.md

@@ -83,13 +83,13 @@ deps:
          `node .forge/tools/store-cli.cjs update-status task {taskId} status implementing`
          `node .forge/tools/store-cli.cjs update-status task {taskId} status implemented`
      - **Bug mode** — NO status write. The bug remains `in-progress` until the commit phase transitions it to `fixed`. Writing `bug.status` here violates `meta-fix-bug.md § Iron Laws #2`.
-   - **Do NOT emit a phase event yourself.** The orchestrator owns event emission — it composes the canonical event from runtime telemetry (model, provider, tokens, wall times) plus the SUMMARY you write in the next step. Subagents that call `store-cli emit` for phase events hallucinate runtime facts (see Plan 11 / Slice 2). Write the SUMMARY and return.
+   - **Do NOT emit a phase event yourself.** The orchestrator owns event emission — it composes the canonical event from runtime telemetry plus the SUMMARY you write next. Subagents that call `store-cli emit` for phase events hallucinate runtime facts (Plan 11 / Slice 2). Write the SUMMARY and return.
 
 7. Emit Summary Sidecar:
    - Write `IMPLEMENTATION-SUMMARY.json` via `forge_artifact`:
      `forge_artifact({ command:"write", entity:"{entity_kind}", entityId:"{record_id}", artifact:"implementation-summary", content:"<JSON>" })`
-     JSON shape: `{"objective":"<one sentence>", "key_changes":["<up to 12 bullets>"], "verdict":"n/a", "written_at":"<ISO 8601>", "artifact_ref":"PROGRESS.md"}`
-     The tool validates required fields automatically — fix and retry if it rejects.
+     JSON shape: `{"objective":"<one sentence>", "key_changes":["<up to 12 bullets>"], "files_changed":["<path>"], "verdict":"n/a", "written_at":"<ISO 8601>", "artifact_ref":"PROGRESS.md"}`
+   - `files_changed`: every repo path this phase changed (one `git status --porcelain`); `commit-task.cjs` stages from it.
    - Then link sidecar to store (task mode):
      `forge_store({ command:"set-summary", args:["{taskId}", "implementation"] })`
      Or (bug mode):

package/dist/forge-payload/.base-pack/workflows/migrate_structural.md

@@ -279,7 +279,7 @@ node .forge/tools/substitute-placeholders.cjs \
 ```
 
 This overwrites `.forge/personas/`, `.forge/skills/`, `.forge/workflows/`,
-`.forge/templates/`, and `.claude/commands/<prefix>/` with the freshly substituted
+`.forge/templates/`, and `.claude/commands/forge/` with the freshly substituted
 base-pack.
 
 If `substitute-placeholders.cjs` exits non-zero: halt, report the error to the

package/dist/forge-payload/.base-pack/workflows-js/wfl-fix-bug.js

@@ -66,6 +66,22 @@ const SKIP_STATUS = ['blocked', 'escalated', 'fixed', 'abandoned']
 // non-review phase (the approve workflow self-escalates if it rejects).
 const REVIEW_ROLES = ['review-plan', 'review-code']
 
+// Bug-phase `type` tokens — verbatim port of the canonical table in
+// .forge/workflows/_fragments/event-vocabulary.md § Bug pipeline
+// (forge-engineering#39). The COMPLETE event carries the pass token (or the
+// fail token when a review phase's verdict is "revision"); the START event is
+// always untyped. Keyed by phase ROLE (matches PHASES_A/PHASES_B role names;
+// triage is keyed separately since it runs outside the phase loop).
+const BUG_TYPE_TOKENS = {
+  'triage':      { pass: 'bug-triaged',            fail: 'bug-triaged' },
+  'plan':        { pass: 'fix-planned',            fail: 'fix-planned' },
+  'review-plan': { pass: 'fix-review-passed',      fail: 'fix-review-failed' },
+  'implement':   { pass: 'fix-implemented',        fail: 'fix-implemented' },
+  'review-code': { pass: 'fix-code-review-passed', fail: 'fix-code-review-failed' },
+  'approve':     { pass: 'fix-approved',           fail: 'fix-revision-requested' },
+  'commit':      { pass: 'bug-committed',          fail: 'bug-commit-failed' },
+}
+
 // Per-phase model tier — verbatim port of fix_bug.md § Role-to-Tier Mapping.
 // Passed as the `model` opt to agent(); the host resolves the tier name to a model.
 const ROLE_TIER = {
@@ -160,6 +176,16 @@ function revisionTarget(phases, reviewIdx) {
 // The subagent owns ALL shell-dependent side-effects for this phase.
 function runBugPhase(bugId, phase, iter) {
   const sprintId = 'bugs'   // virtual sprint dir for all emit/sidecar/progress
+  // forge-engineering#39: explicit type-token guidance per
+  // .forge/workflows/_fragments/event-vocabulary.md § Bug pipeline. Without
+  // it, subagents guessed and leaked the action value into `type`
+  // ("start"/"complete" — schema-rejected store residue in events/bugs/).
+  const typeTokens = BUG_TYPE_TOKENS[phase.role]
+  const typeTokenLine = typeTokens
+    ? (REVIEW_ROLES.includes(phase.role)
+        ? 'set type="' + typeTokens.pass + '" when your verdict is Approved, type="' + typeTokens.fail + '" when it is Revision Required.'
+        : 'set type="' + typeTokens.pass + '".')
+    : 'omit the "type" field entirely (untyped events are valid; this role has no table entry).'
   return agent(
     [
       `You are running a SINGLE pipeline phase for Forge bug ${bugId} (sprint bugs).`,
@@ -175,11 +201,14 @@ function runBugPhase(bugId, phase, iter) {
       '   3a. BEFORE running the phase workflow: note the start timestamp (startTimestamp = new Date().toISOString()).',
       '   Emit a start event via `node .forge/tools/store-cli.cjs emit bugs \'{event-json}\'`',
       '   with action="start", role="' + phase.role + '", iteration=' + iter + ', startTimestamp and endTimestamp both equal to startTimestamp (0-duration placeholder).',
+      '   The start event MUST NOT include a "type" field.',
       '   3b. AFTER the phase workflow completes: note the end timestamp (endTimestamp = new Date().toISOString()).',
       '   Compute durationMinutes = (new Date(endTimestamp) - new Date(startTimestamp)) / 60000.',
       '   Emit a complete event via `node .forge/tools/store-cli.cjs emit bugs \'{event-json}\'`',
-      '   conforming to `.forge/schemas/event.schema.json` (role, action="complete", phase, iteration=' + iter + ',',
+      '   conforming to `.forge/schemas/event.schema.json` (role, action="complete", phase, iteration=' + iter + ', bugId,',
       '   startTimestamp, endTimestamp, durationMinutes, plus your own model/provider/token usage — do NOT invent placeholder model strings).',
+      '   COMPLETE-event type (per .forge/workflows/_fragments/event-vocabulary.md): ' + typeTokenLine,
+      '   NEVER copy the action value ("start"/"complete") into "type" — those tokens are schema-rejected and the event would be dropped.',
       '   If `/cost` data is available, also write the token sidecar via the `--sidecar` form. Best-effort; skip silently if unavailable.',
       '   Then drain any `.forge/cache/FRICTION-*.jsonl` friction records you produced and emit them as type "friction".',
       phase.role && REVIEW_ROLES.includes(phase.role)
@@ -230,14 +259,18 @@ const resolved = await agent(
 
 if (!resolved) throw new Error(`Could not resolve bug record for ${bugId}`)
 
-// Pre-loop status guard — fix_bug.md: skip at pre-loop with one bug_skipped event.
+// Pre-loop status guard — fix_bug.md: skip at pre-loop with one bug-skipped event.
+// Token + payload per _fragments/event-vocabulary.md (forge-engineering#39):
+// bug-skipped requires bugId but no phase/iteration; driver-emitted skips carry
+// model/provider "n/a"; the skip reason rides in "notes" (declared property).
 if (SKIP_STATUS.includes(resolved.bugStatus)) {
   log(`⚠ ${bugId} — status is ${resolved.bugStatus}, skipping run.`)
-  // Emit bug_skipped event (not a silent return — Iron Law 3).
+  // Emit bug-skipped event (not a silent return — Iron Law 3).
   await agent(
     [
-      `Emit a bug_skipped event for ${bugId}..`,
-      `Run \`node .forge/tools/store-cli.cjs emit bugs '{"type":"bug_skipped","sprintId":"bugs","bugId":"${bugId}","role":"orchestrator","action":"skipped","reason":"status=${resolved.bugStatus}","startTimestamp":"'$(date -u +%Y-%m-%dT%H:%M:%S.%3NZ)'","endTimestamp":"'$(date -u +%Y-%m-%dT%H:%M:%S.%3NZ)'","durationMinutes":0}'\`.`,
+      `Emit a bug-skipped event for ${bugId}.`,
+      `Run \`node .forge/tools/store-cli.cjs emit bugs '{"eventId":"<uuid-v4>","type":"bug-skipped","sprintId":"bugs","bugId":"${bugId}","role":"orchestrator","action":"skipped","notes":"status=${resolved.bugStatus}","startTimestamp":"'$(date -u +%Y-%m-%dT%H:%M:%S.%3NZ)'","endTimestamp":"'$(date -u +%Y-%m-%dT%H:%M:%S.%3NZ)'","durationMinutes":0,"model":"n/a","provider":"n/a"}'\`.`,
+      'Replace <uuid-v4> with a UUID v4 string (e.g. crypto.randomUUID()). Do NOT modify any other store records.',
       `Best-effort. Return taskStatus="${resolved.bugStatus}", gatePassed=true, verdict="none", escalated=false, phase="skip", role="orchestrator".`,
     ].join(' '),
     { label: `${bugId}:skip`, phase: 'Skip', schema: BUG_PHASE_RESULT_SCHEMA, model: 'haiku' }
@@ -268,11 +301,14 @@ let triageResult = await agent(
     '   3a. BEFORE running the triage workflow: note the start timestamp (startTimestamp = new Date().toISOString()).',
     '   Emit a start event via `node .forge/tools/store-cli.cjs emit bugs \'{event-json}\'`',
     '   with action="start", role="triage", iteration=1, startTimestamp and endTimestamp both equal to startTimestamp (0-duration placeholder).',
+    '   The start event MUST NOT include a "type" field.',
     '   3b. AFTER the triage workflow completes: note the end timestamp (endTimestamp = new Date().toISOString()).',
     '   Compute durationMinutes = (new Date(endTimestamp) - new Date(startTimestamp)) / 60000.',
     '   Emit a complete event via `node .forge/tools/store-cli.cjs emit bugs \'{event-json}\'`',
-    '   conforming to `.forge/schemas/event.schema.json` (role, action="complete", phase, iteration=1,',
+    '   conforming to `.forge/schemas/event.schema.json` (role, action="complete", phase, iteration=1, bugId,',
     '   startTimestamp, endTimestamp, durationMinutes, plus your own model/provider/token usage — do NOT invent placeholder model strings).',
+    '   COMPLETE-event type (per .forge/workflows/_fragments/event-vocabulary.md): set type="bug-triaged".',
+    '   NEVER copy the action value ("start"/"complete") into "type" — those tokens are schema-rejected and the event would be dropped.',
     '   If `/cost` data is available, also write the token sidecar via the `--sidecar` form. Best-effort; skip silently if unavailable.',
     '4. NON-REVIEW phase: return verdict="none".',
     '5. Read `.forge/store/bugs/' + bugId + '.json` and return its final status as taskStatus, plus a one-line note.',