create-pmos 0.38.6 → 0.38.8

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "create-pmos",
-  "version": "0.38.6",
+  "version": "0.38.8",
   "description": "Scaffold the PMOS portable kit — run the PMOS product-management workflow (initiative → lane-fit spec → contract → build → three gates, with work-type lanes for features, research, maintenance, incidents, and content) entirely inside your own repo, with all state as git-versioned files. Includes `workflow-sweep`, which audits the state every board derives from and separates real defects from work you simply have not done. `create-pmos workspace` also installs + launches the local Terminal Workspace GUI. No database, no network, no telemetry.",
   "license": "MIT",
   "bin": {

package/payload/KIT-VERSION

@@ -1,3 +1,3 @@
-kernel-source: pmos@cb4d5ff
+kernel-source: pmos@6e5901f
 assembled: 2026-10-03
 mode: vendor

package/payload/okf/core/templates/report-rubric-template.md

@@ -0,0 +1,35 @@
+---
+type: Template
+title: Report Rubric Template
+description: The scaffold for judging a report or decision record (D68 report and decision-record lanes) — accuracy and sourcing, audience fit, decision clarity and honest gaps, with a pass threshold and two caps. Copy it as the rubric the lane's review step grades against.
+tags: [template, report, rubric, review, pm-artifacts]
+timestamp: 2026-10-03
+---
+
+# Report Rubric Template
+
+**Situating context:** Authored with [D78](/okf/products/pmos/adr/d78-one-report-shape.md). The review step of the `report` and `decision-record` lanes turned green on any non-empty `reviewed_by`, with no standard to grade against. This rubric is that standard. The [pm-communication skill](/skills/pm-communication.skill) hands it to the reviewer. Copy the block below, set the audience, and keep the weights unless the PM changes them. The copy is an operational instance, not OKF knowledge.
+
+> Usage: the reviewer is not the drafter. Grade the document, not the process that made it. Score each dimension from 0 to 1, multiply by its weight, add them, and compare to the threshold. Record the verdict in `evals.jsonl`. The PM's acceptance is separate and binds.
+
+---
+
+```markdown
+# Rubric: <report or decision record title>
+
+- initiative_id: <id>
+- audience: <leadership | delivery | partner>
+- pass_threshold: 0.80
+
+| # | Dimension | Weight | Full credit |
+|---|---|---|---|
+| D1 | Accuracy and sourcing | 0.30 | Every claim carries a pointer: an initiative id, an acceptance, a note, or a source item. A reviewer can open each pointer and find the claim. Numbers match their source. |
+| D2 | Audience fit | 0.25 | The order and content match the audience. Leadership: the decision or headline first, then the risk, then the evidence. Delivery: scope, state, acceptance and what blocks. Partner: what changed for them and what they must do, with a date. Nothing the audience cannot act on is included. |
+| D3 | Decision clarity | 0.25 | The reader can tell, from the first screen, whether a decision is needed, what it is, the options, the recommendation and the date. A document with no decision says so. A decision record states the choice before the reasoning. |
+| D4 | Honest gaps | 0.20 | Sources that could not be reached are named. Items that could not be verified are marked unverified. A quiet period is reported as quiet. Nothing is filled in to make the report look complete. |
+
+## Caps
+
+- A claim stated as fact with no pointer that the reviewer cannot find in any source: the score is capped at 0.60.
+- A source named that the drafter did not reach: the score is capped at 0.40.
+```

package/payload/okf/core/templates/report-weekly-template.md

@@ -1,35 +1,46 @@
 ---
 type: Template
 title: Weekly Report Template
-description: A regular status report (D68 report lane, light track by default): what moved, against which KR or domain goal, what is blocked, and what needs the reader.
+description: A regular status report (D68 report lane, light track by default) in the one report frame of D78 — Headline, What moved, Risks, Metrics, Needs your call, Sources reached and not reached — for a named audience.
 tags: [template, report, status, pm-artifacts]
-timestamp: 2026-10-01
+timestamp: 2026-10-03
 ---
 
 # Weekly Report Template
 
-**Situating context:** Authored with [D68](/okf/products/pmos/adr/d68-repository-profiles.md) for the pm-artifacts profile, by release R3 of [the PMOS overhaul plan](/planning/research/pm-overhaul-plan.md). Copy the block below into the repository's planning area, fill every `<…>`, and point the initiative record at it (`brief_path` for a brief, `doc_path` for the deliverable). The copy is an operational instance, not OKF knowledge.
+**Situating context:** Authored with [D68](/okf/products/pmos/adr/d68-repository-profiles.md) for the pm-artifacts profile, by release R3 of [the PMOS overhaul plan](/planning/research/pm-overhaul-plan.md). Copy the block below into the repository's planning area, fill every `<…>`, and point the initiative record at it (`brief_path` for a brief, `doc_path` for the deliverable). The copy is an operational instance, not OKF knowledge. The section list is the report frame of [D78](/okf/products/pmos/adr/d78-one-report-shape.md): Headline first, Needs your call and Sources reached and not reached last. A PM's definition file may replace the middle sections (What moved, Risks, Metrics). The [pm-communication skill](/skills/pm-communication.skill) drafts this document for a named audience. Keep the `initiative_id` line: the workflow audit uses it to find the report.
 
 ---
 
 ```markdown
+---
+type: Reference
+title: "Report — <week of YYYY-MM-DD> — <scope: domain | portfolio>"
+initiative_id: <id of the report-lane initiative>
+audience: <leadership | delivery | partner>
+status: draft
+---
+
 # Weekly report — <week of YYYY-MM-DD> — <scope: domain | portfolio>
 
 ## Headline
-<one sentence: the most important change this week>
+<one or two sentences: what the reader most needs to know. Put the decision first if there is one.>
 
-## Moved this week
+## What moved
 | initiative | anchor (KR · domain) | what moved | evidence |
 |---|---|---|---|
 
+## Risks
+| initiative | risk or blocker | what is needed | from whom |
+|---|---|---|---|
+
 ## Metrics
 | metric | last week | this week | target | trend |
 |---|---|---|---|---|
 
-## Blocked or at risk
-| initiative | blocker | what is needed | from whom |
-|---|---|---|---|
+## Needs your call
+<each decision or review waiting on the reader: the question, the options, your recommendation, the date it is needed by>
 
-## Needs you
-<the decisions or reviews waiting on the reader>
+## Sources reached and not reached
+<each source kind: reached, or not reached and why. Say if nothing changed.>
 ```

package/payload/planning/evals/eval-calibration.md

@@ -2,7 +2,7 @@
 type: Reference
 title: "Eval calibration log"
 description: "Append-only record of every PM override of an evaluator verdict."
-generated: {by: process:create-pmos, at: "2026-10-03T00:48:37Z"}
+generated: {by: process:create-pmos, at: "2026-10-03T03:25:22Z"}
 status: stable
 ---
 

package/payload/planning/okrs/health-budgets.md

@@ -2,7 +2,7 @@
 type: Reference
 title: "Health budgets"
 description: "Closed registry of health-budget anchors (D59), edited only by the PM."
-generated: {by: process:create-pmos, at: "2026-10-03T00:48:37Z"}
+generated: {by: process:create-pmos, at: "2026-10-03T03:25:22Z"}
 status: stable
 ---
 

package/payload/skills/pm-communication.skill

@@ -0,0 +1,123 @@
+---
+name: pm-communication
+description: Draft a status report, stakeholder update or decision record for one named audience (leadership, delivery or partner), write it where the initiative's record points, and set doc_path. Use when the PM asks for a status update, a stakeholder update, a decision communication, a report, or to put a scheduled draft under a lane.
+version: 1.0.0
+owner: wawan
+risk: low
+category: communication
+scope: read:okf, read:planning, read:state, write:planning/reports
+---
+
+# pm-communication — Draft the update for the reader
+
+This skill is the producer for the `report` and `decision-record` lanes of the document profile
+([D77](/okf/products/pmos/adr/d77-lane-definitions.md)). It drafts one document for one audience in
+the report frame of [D78](/okf/products/pmos/adr/d78-one-report-shape.md). It writes a file. It sends
+nothing.
+
+> **Format note:** this skill follows [SKILL-FORMAT](/skills/SKILL-FORMAT.md). The text is
+> instructional (class A of [technical-writing-ste](/skills/technical-writing-ste.skill)).
+> The documents it drafts are class B, except the request in *Needs your call*.
+
+## When to use vs. not
+
+- **Use** for a status report, a stakeholder update, a decision record or a decision communication.
+- **Use** to put a scheduled draft under the `report` lane (step 4).
+- **Do not use** for customer-facing copy or release notes. That is the content lane and the
+  [copywriting skill](/skills/copywriting.skill).
+- **Do not use** to decide the lane. That is the [pmos-router](/skills/pmos-router.skill).
+- **Do not use** to gather what the PM wants to say. That is the
+  [requirements-elicitation skill](/skills/requirements-elicitation.skill), which holds the
+  questions for the `report` and `decision-record` lanes. Follow it when step 2 needs answers.
+
+## Rules that always hold
+
+1. The draft is a file in this repository. Never send, post, share, email, publish or upload it. The PM does that (D71).
+2. Every claim carries a pointer: an initiative id, an acceptance, a note, a run or a source item. A claim with no pointer is left out or marked "unverified".
+3. Write nothing that you did not read. Name each source you could not reach. If nothing changed, say so.
+4. Never write `reviewed_by`, a review verdict, an acceptance or a handoff. Those belong to the reviewer and the PM.
+5. A gathered note with `confidence: unconfirmed` is marked unverified in the draft. Never write it as a fact.
+6. Skip threads and pages that are private, personal, confidential or HR. Count them. Do not read them.
+7. Never copy message bodies, attachments, tokens or credentials. Quote at most one short sentence per item.
+
+## Procedure
+
+1. **Find the lane and the record.** Read the initiative record and its `type`. Run
+   `node scripts/workflow-state.js --lanes --json` (in a kit repository the script is
+   `pmos/scripts/workflow-state.js`). Find the lane in `defs`. It must be `report` or
+   `decision-record`. State the lane's `output` and `done` in plain words before you draft.
+   *Done when:* the PM has seen the lane's output and done-rule.
+
+   If the profile has no such lane (the code profile), say so. Offer the content lane with an
+   internal audience, and stop. If the script is missing or the lane is unknown, say so and ask
+   which lane applies.
+
+2. **Name the audience.** The audience is leadership, delivery or partner. Read it from the
+   record, the PM's definition file or the PM's request. If none names it, ask the PM, with a
+   recommended answer, by the requirements-elicitation skill. Do not choose one.
+   *Done when:* the audience is one of the three and the PM has confirmed it.
+
+3. **Gather the facts.** Read what the draft will claim: the initiatives and their acceptances
+   (`node scripts/workflow-state.js`), the runs, the notes in `<state>/requirements/` (`<state>`
+   is `pmos/state/` if it exists, and `planning/` if not), and each source the PM's definition
+   file names that you can reach. For a report, read `<state>/reports/definitions/<cadence>.md`
+   if it exists and follow it where it does not remove a part of the frame. Look facts up. Do
+   not ask the PM for a fact that a file holds.
+   *Done when:* each claim you will make has a pointer, and each source you could not reach is listed.
+
+4. **Adopt a scheduled draft, if the PM names one.** If the PM points at an existing draft (a
+   file under `<state>/reports/`), do not draft a new one. Set the record's `doc_path` to that
+   file (step 6) and go to step 7 on it. Tell the PM that the draft was written by a schedule
+   and was not part of the lane until now.
+   *Done when:* the PM has said whether to adopt or to draft a new one.
+
+5. **Draft in the audience's register.** For a report, copy the
+   [report template](/okf/core/templates/report-weekly-template.md). For a decision record, copy the
+   [decision-record template](/okf/core/templates/decision-record-template.md). Fill every section
+   in the order and register for the audience (see [Registers](#registers)). The Headline comes
+   first. If a decision is needed, the Headline says what it is.
+   Write the file to the record's `doc_path`. If the record has none, write
+   `planning/reports/<initiative-id>-<YYYY-MM-DD>.md`. If the file exists, do not overwrite it:
+   append a section `## Later run HH:MM`. Start with this frontmatter, one key per line:
+   `type: Reference`, `title`, `initiative_id`, `audience`, `status: draft`,
+   `generated: {by: claude-code/pm-communication, at: "<ISO 8601>"}` and
+   `sources: [{resource: "<pointer>", title: "<what it is>"}]`. Do not add `timestamp` or `verified`.
+   *Done when:* the file exists and has all the sections of its template.
+
+6. **Point the record at it.** Set `doc_path` on the initiative record to the file. This is the
+   only key you set. If `doc_path` already names a different file, do not change it: ask the PM.
+   *Done when:* `node scripts/workflow-state.js <id>` shows the draft step done with this file as its basis.
+
+7. **Check the draft against the done-rule.** Read the lane's `done` text. Say which part is
+   met: the document exists (yes), a reviewer has judged it (not yet), the PM has accepted it
+   (not yet), and handed off, where the lane says so (not yet). Then check the draft:
+   the Headline is first; the decision or the absence of one is visible on the first screen;
+   each claim has a pointer; *Sources reached and not reached* is last; nothing in it is
+   outside the audience's register.
+   *Done when:* every check passes or the failing one is named to the PM.
+
+8. **Hand over.** Say where the draft is. Name the review step: the reviewer is not you, and
+   grades against the [report rubric](/okf/core/templates/report-rubric-template.md). State the open
+   questions and the sources not reached. Do not send the draft.
+   *Done when:* the PM knows where the draft is, who must review it, and what is still open.
+
+## Registers
+
+One register per audience. The order is fixed. What a register leaves out is as much a part of it
+as what it includes. A decision comes before its reasoning for every audience.
+
+| Audience | Order | Include | Leave out | Length |
+|---|---|---|---|---|
+| **Leadership** | The decision or headline; the risk; the evidence | The call you need and by when; the effect on a goal or a date; one number that shows it | Task lists, tool names, how the work was done | One screen |
+| **Delivery** | Scope and state; acceptance; what blocks | Initiative ids, acceptance state, blockers with an owner, next step | Strategy, history before this period | As long as the work needs, in tables |
+| **Partner** | What changed for them; what they must do, and by when | The change in their terms, the date, who to ask | Internal ids, internal debate, anything they cannot act on | Short: the action first |
+
+For a decision record, the choice and its owner come first. Then who must act and by when. The
+reasoning and the options considered come last.
+
+## Failure behaviour
+
+- The audience is not named and the PM does not answer: do not draft. Say what is missing.
+- The lane definition cannot be read: say so, and ask which lane applies.
+- No source can be reached: write a short honest draft that says so. Do not fill the gap.
+- `doc_path` names a different file: do not change it. Ask the PM.

package/payload/skills/pmos-router.skill

@@ -64,6 +64,7 @@ router is the bug (fix it via the weekly harness scan).
 | A **text deliverable** (landing page, microcopy, release notes, campaign) | **Content lane** | `type: content`; content brief at `prd_path`, rubric recommended not required (D58); [copywriting skill](/skills/copywriting.skill). Copy for a prototype rides the prototype instead (D60) | Initiative Gate (content brief) |
 | **Upkeep** — refactor/ops/security with no honest KR | **Chore lane, health-anchored** | `type: chore`; one-paragraph intent in `status`; anchor `health:<id>` from [health-budgets](/planning/okrs/health-budgets.md) (D59) — never a faked KR | Initiative Gate (intent + anchor) |
 | "**Gather**, **clarify** or **sharpen** the requirements" — the PM has a vague ask or notes from gathering and no brief yet | **Requirements elicitation** (before the lane's first artifact) | [requirements-elicitation skill](/skills/requirements-elicitation.skill) → `planning/briefs/<id>-requirements.md` at `brief_path`; reads the lane's input from `scripts/lane-defs.js` and the notes `gather-requirements` filed (D71); the PM confirms each note item. It does not choose the lane and does not write the PRD | none (the brief is never a gate) |
+| "**Write a status update**, a **stakeholder update** or a **decision communication**", or put a scheduled report draft under a lane — a report, an update or a decision record for a named audience (leadership, delivery or partner) | **Document profile: the `report` or `decision-record` lane.** **Code profile: the content lane**, with an internal audience (customer-facing copy is a different request) | [pm-communication skill](/skills/pm-communication.skill) → a draft at `doc_path`, in the report frame of D78 (Headline, the middle sections, Needs your call, Sources reached and not reached); it asks for the audience, sets `doc_path`, never sends and never writes the review or the acceptance. The reviewer grades against the [report rubric](/okf/core/templates/report-rubric-template.md) | Initiative Gate (the lane's record); the review and acceptance steps stay open for the reviewer and the PM |
 
 **Every route** still takes the universal steps: anchored initiative row (`create_initiative`),
 branch `initiative/<id>`, and the human Acceptance Gate at the end (D12) — the router never bypasses

package/payload/skills/technical-writing-ste.skill

@@ -39,7 +39,7 @@ Ask what the reader must do with it. Derive the class from the path, not from fe
 | Class | What the reader must do | Where it lives |
 |---|---|---|
 | **A — instructional** | **Act**, correctly, on one reading | `skills/**` · playbooks and runbooks · gate and CI failure strings · UI copy and microcopy · tool descriptions · template usage notes |
-| **B — descriptive** | **Understand**, not obey | `okf/**` concepts and references · explainers · `**/README.md` · design and data-model docs |
+| **B — descriptive** | **Understand**, not obey | `okf/**` concepts and references · explainers · `**/README.md` · design and data-model docs · agent-drafted status reports and stakeholder updates (`planning/reports/**`, `<state>/reports/**`) |
 | **C — argumentative** | **Weigh a judgement under uncertainty** | ADRs and decision records · `planning/prd/**` · briefs · the discoveries log · eval verdicts · PR bodies |
 
 The three classes are the rule. **The paths are your repo's, so write them down once.** In PMOS they
@@ -48,8 +48,10 @@ also cover `build-skills/**` and `okf/core/playbooks/**` (A), `planning/explaine
 cover your CLI output, your error strings and your component copy (A), and your architecture notes
 (B). When a path is not on your list, ask the question in column two and add the answer to the list.
 
-Two boundary rules. **Text the PM wrote is Class C**, whatever it is about. And the profile binds
-**new and modified text only** — never rewrite an existing corpus to satisfy it.
+Three boundary rules. **Text the PM wrote is Class C**, whatever it is about. The profile binds
+**new and modified text only** — never rewrite an existing corpus to satisfy it. And inside an
+agent-drafted status report or update, the request in *Needs your call* is **Class A**: the reader
+must act on it, so write one question, the options, your recommendation and the date.
 
 **Done when:** you can name the class and the row that put it there.
 

package/payload/skills-native/pm-communication/SKILL.md

@@ -0,0 +1,125 @@
+---
+name: pm-communication
+description: Draft a status report, stakeholder update or decision record for one named audience (leadership, delivery or partner), write it where the initiative's record points, and set doc_path. Use when the PM asks for a status update, a stakeholder update, a decision communication, a report, or to put a scheduled draft under a lane.
+license: MIT
+metadata:
+  pmos-version: 1.0.0
+  pmos-owner: wawan
+  pmos-risk: low
+  pmos-category: communication
+  pmos-scope: read:okf, read:planning, read:state, write:planning/reports
+---
+
+# pm-communication — Draft the update for the reader
+
+This skill is the producer for the `report` and `decision-record` lanes of the document profile
+([D77](/okf/products/pmos/adr/d77-lane-definitions.md)). It drafts one document for one audience in
+the report frame of [D78](/okf/products/pmos/adr/d78-one-report-shape.md). It writes a file. It sends
+nothing.
+
+> **Format note:** this skill follows [SKILL-FORMAT](/skills/SKILL-FORMAT.md). The text is
+> instructional (class A of [technical-writing-ste](/skills/technical-writing-ste.skill)).
+> The documents it drafts are class B, except the request in *Needs your call*.
+
+## When to use vs. not
+
+- **Use** for a status report, a stakeholder update, a decision record or a decision communication.
+- **Use** to put a scheduled draft under the `report` lane (step 4).
+- **Do not use** for customer-facing copy or release notes. That is the content lane and the
+  [copywriting skill](/skills/copywriting.skill).
+- **Do not use** to decide the lane. That is the [pmos-router](/skills/pmos-router.skill).
+- **Do not use** to gather what the PM wants to say. That is the
+  [requirements-elicitation skill](/skills/requirements-elicitation.skill), which holds the
+  questions for the `report` and `decision-record` lanes. Follow it when step 2 needs answers.
+
+## Rules that always hold
+
+1. The draft is a file in this repository. Never send, post, share, email, publish or upload it. The PM does that (D71).
+2. Every claim carries a pointer: an initiative id, an acceptance, a note, a run or a source item. A claim with no pointer is left out or marked "unverified".
+3. Write nothing that you did not read. Name each source you could not reach. If nothing changed, say so.
+4. Never write `reviewed_by`, a review verdict, an acceptance or a handoff. Those belong to the reviewer and the PM.
+5. A gathered note with `confidence: unconfirmed` is marked unverified in the draft. Never write it as a fact.
+6. Skip threads and pages that are private, personal, confidential or HR. Count them. Do not read them.
+7. Never copy message bodies, attachments, tokens or credentials. Quote at most one short sentence per item.
+
+## Procedure
+
+1. **Find the lane and the record.** Read the initiative record and its `type`. Run
+   `node scripts/workflow-state.js --lanes --json` (in a kit repository the script is
+   `pmos/scripts/workflow-state.js`). Find the lane in `defs`. It must be `report` or
+   `decision-record`. State the lane's `output` and `done` in plain words before you draft.
+   *Done when:* the PM has seen the lane's output and done-rule.
+
+   If the profile has no such lane (the code profile), say so. Offer the content lane with an
+   internal audience, and stop. If the script is missing or the lane is unknown, say so and ask
+   which lane applies.
+
+2. **Name the audience.** The audience is leadership, delivery or partner. Read it from the
+   record, the PM's definition file or the PM's request. If none names it, ask the PM, with a
+   recommended answer, by the requirements-elicitation skill. Do not choose one.
+   *Done when:* the audience is one of the three and the PM has confirmed it.
+
+3. **Gather the facts.** Read what the draft will claim: the initiatives and their acceptances
+   (`node scripts/workflow-state.js`), the runs, the notes in `<state>/requirements/` (`<state>`
+   is `pmos/state/` if it exists, and `planning/` if not), and each source the PM's definition
+   file names that you can reach. For a report, read `<state>/reports/definitions/<cadence>.md`
+   if it exists and follow it where it does not remove a part of the frame. Look facts up. Do
+   not ask the PM for a fact that a file holds.
+   *Done when:* each claim you will make has a pointer, and each source you could not reach is listed.
+
+4. **Adopt a scheduled draft, if the PM names one.** If the PM points at an existing draft (a
+   file under `<state>/reports/`), do not draft a new one. Set the record's `doc_path` to that
+   file (step 6) and go to step 7 on it. Tell the PM that the draft was written by a schedule
+   and was not part of the lane until now.
+   *Done when:* the PM has said whether to adopt or to draft a new one.
+
+5. **Draft in the audience's register.** For a report, copy the
+   [report template](/okf/core/templates/report-weekly-template.md). For a decision record, copy the
+   [decision-record template](/okf/core/templates/decision-record-template.md). Fill every section
+   in the order and register for the audience (see [Registers](#registers)). The Headline comes
+   first. If a decision is needed, the Headline says what it is.
+   Write the file to the record's `doc_path`. If the record has none, write
+   `planning/reports/<initiative-id>-<YYYY-MM-DD>.md`. If the file exists, do not overwrite it:
+   append a section `## Later run HH:MM`. Start with this frontmatter, one key per line:
+   `type: Reference`, `title`, `initiative_id`, `audience`, `status: draft`,
+   `generated: {by: claude-code/pm-communication, at: "<ISO 8601>"}` and
+   `sources: [{resource: "<pointer>", title: "<what it is>"}]`. Do not add `timestamp` or `verified`.
+   *Done when:* the file exists and has all the sections of its template.
+
+6. **Point the record at it.** Set `doc_path` on the initiative record to the file. This is the
+   only key you set. If `doc_path` already names a different file, do not change it: ask the PM.
+   *Done when:* `node scripts/workflow-state.js <id>` shows the draft step done with this file as its basis.
+
+7. **Check the draft against the done-rule.** Read the lane's `done` text. Say which part is
+   met: the document exists (yes), a reviewer has judged it (not yet), the PM has accepted it
+   (not yet), and handed off, where the lane says so (not yet). Then check the draft:
+   the Headline is first; the decision or the absence of one is visible on the first screen;
+   each claim has a pointer; *Sources reached and not reached* is last; nothing in it is
+   outside the audience's register.
+   *Done when:* every check passes or the failing one is named to the PM.
+
+8. **Hand over.** Say where the draft is. Name the review step: the reviewer is not you, and
+   grades against the [report rubric](/okf/core/templates/report-rubric-template.md). State the open
+   questions and the sources not reached. Do not send the draft.
+   *Done when:* the PM knows where the draft is, who must review it, and what is still open.
+
+## Registers
+
+One register per audience. The order is fixed. What a register leaves out is as much a part of it
+as what it includes. A decision comes before its reasoning for every audience.
+
+| Audience | Order | Include | Leave out | Length |
+|---|---|---|---|---|
+| **Leadership** | The decision or headline; the risk; the evidence | The call you need and by when; the effect on a goal or a date; one number that shows it | Task lists, tool names, how the work was done | One screen |
+| **Delivery** | Scope and state; acceptance; what blocks | Initiative ids, acceptance state, blockers with an owner, next step | Strategy, history before this period | As long as the work needs, in tables |
+| **Partner** | What changed for them; what they must do, and by when | The change in their terms, the date, who to ask | Internal ids, internal debate, anything they cannot act on | Short: the action first |
+
+For a decision record, the choice and its owner come first. Then who must act and by when. The
+reasoning and the options considered come last.
+
+## Failure behaviour
+
+- The audience is not named and the PM does not answer: do not draft. Say what is missing.
+- The lane definition cannot be read: say so, and ask which lane applies.
+- No source can be reached: write a short honest draft that says so. Do not fill the gap.
+- `doc_path` names a different file: do not change it. Ask the PM.

package/payload/skills-native/pmos-router/SKILL.md

@@ -66,6 +66,7 @@ router is the bug (fix it via the weekly harness scan).
 | A **text deliverable** (landing page, microcopy, release notes, campaign) | **Content lane** | `type: content`; content brief at `prd_path`, rubric recommended not required (D58); [copywriting skill](/skills/copywriting.skill). Copy for a prototype rides the prototype instead (D60) | Initiative Gate (content brief) |
 | **Upkeep** — refactor/ops/security with no honest KR | **Chore lane, health-anchored** | `type: chore`; one-paragraph intent in `status`; anchor `health:<id>` from [health-budgets](/planning/okrs/health-budgets.md) (D59) — never a faked KR | Initiative Gate (intent + anchor) |
 | "**Gather**, **clarify** or **sharpen** the requirements" — the PM has a vague ask or notes from gathering and no brief yet | **Requirements elicitation** (before the lane's first artifact) | [requirements-elicitation skill](/skills/requirements-elicitation.skill) → `planning/briefs/<id>-requirements.md` at `brief_path`; reads the lane's input from `scripts/lane-defs.js` and the notes `gather-requirements` filed (D71); the PM confirms each note item. It does not choose the lane and does not write the PRD | none (the brief is never a gate) |
+| "**Write a status update**, a **stakeholder update** or a **decision communication**", or put a scheduled report draft under a lane — a report, an update or a decision record for a named audience (leadership, delivery or partner) | **Document profile: the `report` or `decision-record` lane.** **Code profile: the content lane**, with an internal audience (customer-facing copy is a different request) | [pm-communication skill](/skills/pm-communication.skill) → a draft at `doc_path`, in the report frame of D78 (Headline, the middle sections, Needs your call, Sources reached and not reached); it asks for the audience, sets `doc_path`, never sends and never writes the review or the acceptance. The reviewer grades against the [report rubric](/okf/core/templates/report-rubric-template.md) | Initiative Gate (the lane's record); the review and acceptance steps stay open for the reviewer and the PM |
 
 **Every route** still takes the universal steps: anchored initiative row (`create_initiative`),
 branch `initiative/<id>`, and the human Acceptance Gate at the end (D12) — the router never bypasses

package/payload/skills-native/technical-writing-ste/SKILL.md

@@ -41,7 +41,7 @@ Ask what the reader must do with it. Derive the class from the path, not from fe
 | Class | What the reader must do | Where it lives |
 |---|---|---|
 | **A — instructional** | **Act**, correctly, on one reading | `skills/**` · playbooks and runbooks · gate and CI failure strings · UI copy and microcopy · tool descriptions · template usage notes |
-| **B — descriptive** | **Understand**, not obey | `okf/**` concepts and references · explainers · `**/README.md` · design and data-model docs |
+| **B — descriptive** | **Understand**, not obey | `okf/**` concepts and references · explainers · `**/README.md` · design and data-model docs · agent-drafted status reports and stakeholder updates (`planning/reports/**`, `<state>/reports/**`) |
 | **C — argumentative** | **Weigh a judgement under uncertainty** | ADRs and decision records · `planning/prd/**` · briefs · the discoveries log · eval verdicts · PR bodies |
 
 The three classes are the rule. **The paths are your repo's, so write them down once.** In PMOS they
@@ -50,8 +50,10 @@ also cover `build-skills/**` and `okf/core/playbooks/**` (A), `planning/explaine
 cover your CLI output, your error strings and your component copy (A), and your architecture notes
 (B). When a path is not on your list, ask the question in column two and add the answer to the list.
 
-Two boundary rules. **Text the PM wrote is Class C**, whatever it is about. And the profile binds
-**new and modified text only** — never rewrite an existing corpus to satisfy it.
+Three boundary rules. **Text the PM wrote is Class C**, whatever it is about. The profile binds
+**new and modified text only** — never rewrite an existing corpus to satisfy it. And inside an
+agent-drafted status report or update, the request in *Needs your call* is **Class A**: the reader
+must act on it, so write one question, the options, your recommendation and the date.
 
 **Done when:** you can name the class and the row that put it there.
 

package/payload/state/discoveries.md

@@ -2,7 +2,7 @@
 type: Reference
 title: "Discoveries and friction log"
 description: "Append-only record of what runs discovered and where the process rubbed."
-generated: {by: process:create-pmos, at: "2026-10-03T00:48:37Z"}
+generated: {by: process:create-pmos, at: "2026-10-03T03:25:22Z"}
 status: stable
 ---
 

package/workspace/README.md

@@ -46,6 +46,41 @@ npm run test:ui      # browser checks: terminal geometry, reader scroll, markdow
 ```
 </details>
 
+## Scheduled tasks from the terminal (`schedule-cli`)
+
+`pmos schedule` and `pmos skill` talk to the running workspace server, so the terminal and the workspace share one schedule store and one validator. Every change is saved the moment the command succeeds. A refused value names what is allowed and changes nothing. With no server running the command says so and exits 1.
+
+```
+pmos schedule add --skill gather-requirements --cadence daily --time 07:30 --max-runs 20 --until 2026-12-31
+pmos schedule add --from-session <session-id> --skill-name my-check --output "Summary,Risks" --cadence weekly --day Fri --time 16:00
+pmos schedule add --from-file notes.txt --skill-name my-check --cadence daily      # same, from a text file
+pmos schedule list [--all] · show <id|name> · run · enable · disable · rm
+pmos schedule edit <id|name> --time 08:00 --args "focus on billing" --tier deep --until none
+pmos skill list · show <name> · new --name N --description T [--body-file F] · edit <name> --file F · copy <name>
+```
+
+| To change | Use |
+|---|---|
+| Period | `--cadence daily\|weekly\|bi-weekly\|monthly\|once` with `--time HH:MM`, `--day`, `--day-of-month` or `--date` |
+| Duration | `--until YYYY-MM-DD` (that day still runs) and `--max-runs N`. When either is reached the schedule turns itself off and records why. `none` clears one. |
+| Details and input | `--name`, `--args` (up to 2000 characters, added to each run) |
+| How it runs | `--skill`, `--tier fast\|balanced\|deep`, `--profile` |
+| Structure and output | The skill: `pmos skill edit`. Its `output:` list is the contract. Built-in skills are read-only; `pmos skill copy` makes an editable one. |
+
+`--from-session` and `--from-file` write a new **user** skill from the captured work (the last 6000 characters of a session's terminal text, escape codes removed) and schedule it. Read the skill before its first run: `pmos skill show <name>`. A session's text can hold anything you typed or printed. The command never overwrites a skill and never uses a built-in's name.
+
+**A schedule fires only while the workspace server is running.** A slot missed while it is stopped is skipped, never caught up. A one-off gets a 15-minute grace window. A skill's text is never typed into a session starting with `/`, because Claude Code would read that as a slash command.
+
+## The initiative list and detail: status groups, next steps, conversations, files (`initiative-surface-batch`)
+
+**Group by status.** Above the initiative list, `group by objective | status` switches the grouping, and `active only` (in status mode) shows only live work. The groups, in this order: **Needs you** (returned at acceptance, or open items in the needs queue) · **In progress** (runs logged, nothing merged) · **Planning** (recorded, no run yet) · **Awaiting acceptance** (delivered, not accepted) · **Accepted** · **On hold** · **Closed** · **Cancelled** · **Unknown** (the history could not be read, so the status cannot be derived). "Active" is the first four. The status is **derived** from the ledgers and git, never typed into a record. On hold, closed and cancelled are the PM's: the `on hold` / `close` / `cancel` buttons in the initiative detail append one line to `lifecycle.jsonl`, and `reopen` appends another. An active search shows every match whatever its status.
+
+**Next steps to done.** The initiative detail lists everything between where it is and accepted, in order: the remaining workflow steps (blocked first), open needs items, a returned acceptance, the sessions running on it, then the PM acceptance (D12). The first is marked `next`. Every item names the fact it came from. It is read from the workflow ladder and the ledgers, not written by a model, so it never names a step the engine does not require. A stopped initiative says so and leads with `reopen`; an accepted one says nothing remains.
+
+**Conversations and files in the artifacts.** A session that belongs to an initiative — one you bound, one started on it, or one on its `initiative/<id>` branch — is listed under its artifacts as a conversation. It opens a read-only transcript tab. The transcript is saved when the session ends or is removed, so ending a session no longer erases it. It is kept in this machine's **runtime state directory** (`transcripts/`), not in the repository, and is never sent anywhere; a transcript can contain anything you typed or an agent printed, including a secret. A session on no initiative is not recorded. Below the documents, **files from git** lists what was changed for the initiative: commits on its `initiative/<id>` branch and commits whose subject names it, grouped as code, tests, documents or other, once each, only files that still exist. A failed git read is stated, never shown as an empty list.
+
+**Ending a session from the repository navigation** closes its tab. A refused end, or "asked it to end, not exited yet", leaves the tab open.
+
 ## Layout — four panels (PM-directed design, built by `workspace-four-panel`)
 The three-column layout is retired. The surface is now **four collapsible panels** under a 44px top bar and a 26px status bar, on the oklch token layer, in both themes:
 

package/workspace/bin/pmos.js

@@ -389,6 +389,13 @@ function doctor() {
   else if (cmd === 'ls' || cmd === 'list') code = await ls();
   else if (cmd === 'stop') code = await stop();
   else if (cmd === 'doctor') code = doctor();
+  else if (cmd === 'schedule' || cmd === 'skill') {
+    // Thin client of the running server's own routes (lib/schedule-cli.js): one store, one validator.
+    const live = await discover();
+    const port = live.length ? live[0].port : null;
+    code = await require('../lib/schedule-cli').run(process.argv.slice(2), {
+      say, call: async (m, p, b) => (port ? api(port, m, p, b) : null) });
+  }
   else if (cmd === 'upgrade') {
     // Escape hatch: pull the latest bundled app and force-reinstall over this global copy. Delegates
     // to the scaffolder (which owns the install path) rather than reinstalling itself in place.
@@ -400,9 +407,11 @@ function doctor() {
     if (r.error) { say('✗ could not run ' + npx + ' — ' + r.error.message); code = 1; }
     else code = r.status === null ? 1 : r.status;
   } else if (cmd === 'help' || cmd === '--help' || cmd === '-h') {
-    say('usage: pmos [<path>|status|ls|stop|doctor|upgrade]');
+    say('usage: pmos [<path>|status|ls|stop|doctor|upgrade|schedule|skill]');
     say('  pmos          open the current repo as a workspace (starts the server if needed)');
     say('  pmos <path>   open another repo as a workspace');
+    say('  pmos schedule …  create, edit and run scheduled tasks (pmos schedule --help)');
+    say('  pmos skill …     list, read, create and edit skills');
     say('  pmos upgrade  reinstall the workspace app from the latest published create-pmos');
     code = 0;
   } else if (cmd === 'up' || cmd === 'start' || cmd === 'open') {