@nurix/etna 0.19.10 → 0.19.11

package/data/harness-index.json

@@ -1,5 +1,5 @@
 {
-    "fingerprint": "3745f4d420c5",
+    "fingerprint": "68a0c87df160",
     "harnesses": {
         "code": {
             "plugin": "code",

package/data/harnesses/discussion/CLAUDE.md

@@ -13,7 +13,7 @@ Strictly separated — never mix them:
 | Layer | Lives in |
 | --- | --- |
 | **Method** (timeless) | this file + `.claude/rules/method.md` (how sessions run) + `.claude/rules/artifacts.md` (what gets written) |
-| **State** (current) | `metadata/` — `TOPICS.md` (topic index) + `SESSIONS.md` (session ledger) + `lessons/` (operator layer) + `ops/` (maintenance run-logs) |
+| **State** (current) | `metadata/` — `TOPICS.md` (topic index) + `SESSIONS.md` (session ledger) + `lessons/` (operator layer) + `ops/` (maintenance run-logs) + `writing-styles/` (style registry: `reading.md` default for operator-facing docs) |
 | **Record** (append-only) | each topic's `README.md` + artifacts |
 
 **The operator layer**: `metadata/lessons/` — read `DIGEST.md` at session start alongside the routing files; it is **prior, not canon** (its reading-protocol block governs). Everything else under `lessons/` (append-only `log/`, `forecasts.md`) loads on demand only. The `lessons-maintenance` agent (instruction set: `metadata/lessons/distillation.md`) runs **only during user sessions** — spawn it in the background when the `metadata/ops/` cursor falls a session behind.

package/data/harnesses/discussion/agents/discussion-baseline.md

@@ -29,7 +29,7 @@ Decide once, up front, from two reads:
 
 1. **Git.** If `.git/` is absent: `git init`. Ensure the root `.gitignore` exists with the minimal set (below). The workspace **must** end this run as a git repository — the session-close auto-commit depends on it.
 2. **Seed `metadata/`.** Create `metadata/TOPICS.md`, `metadata/SESSIONS.md`, and `metadata/method-changelog.md` from the templates below — create only what's missing; **never overwrite an existing file**. Stamp `harness-version:` in `TOPICS.md` frontmatter from `.claude/harness.json`.
-3. **Seed the operator layer.** Create `metadata/lessons/` (`distillation.md`, `dimensions.md`, `DIGEST.md`, `forecasts.md`, empty `log/` with a `.gitkeep`) and `metadata/ops/lessons-miner.md` from the templates below — create only what's missing. These ship **empty**: every install accumulates its own operator's lessons via the `lessons-maintenance` agent; no personal content ever ships with the harness.
+3. **Seed the operator layer.** Create `metadata/lessons/` (`distillation.md`, `dimensions.md`, `DIGEST.md`, `forecasts.md`, empty `log/` with a `.gitkeep`) and `metadata/ops/lessons-miner.md` from the templates below — create only what's missing. These ship **empty**: every install accumulates its own operator's lessons via the `lessons-maintenance` agent; no personal content ever ships with the harness. Also seed the style registry `metadata/writing-styles/` (`README.md` + `reading.md` from the templates below, create-only) — the shipped `reading.md` is a generic default the operator refines in place.
 4. **Adopt existing content.** If topic-shaped folders already exist (a folder with a `README.md` that isn't harness machinery), fold them forward: add a `TOPICS.md` entry per topic (state phrase from its README's TL;DR/open threads), and create a `metadata.md` map for any topic lacking one (one line per file — name + what it is, from each file's H1/banner; bulk directories one line total). Adoption is registration, not rewriting — READMEs stay untouched.
 5. **Commit.** One commit: `🔧 baseline: discussion harness v<version>`.
 6. **Hand off.** Report created vs skipped vs adopted, then point at the next actions: start the first topic (say what you're thinking about), or resume via `metadata/TOPICS.md`.
@@ -45,7 +45,7 @@ Declarative, not a migration ladder — converge to the **current** shape; detec
 | Method changelog inside `CLAUDE.md` | `metadata/method-changelog.md` (copy the entries out; the CLI owns `CLAUDE.md` — flag, don't edit it) |
 | Instrument folders at the root | flag for the user to relocate outside the workspace (never move data yourself) |
 
-Only fold what is present. Also seed any missing operator-layer files (`metadata/lessons/` + `metadata/ops/` — same templates below, create-only; introduced in v0.2.0). Then re-stamp `harness-version:`, commit `🔧 baseline: reconciled to discussion harness v<version>`, and report every move.
+Only fold what is present. Also seed any missing operator-layer files (`metadata/lessons/` + `metadata/ops/` — same templates below, create-only; introduced in v0.2.0) and any missing style-registry files (`metadata/writing-styles/` — templates below, create-only; introduced in v0.4.0). Then re-stamp `harness-version:`, commit `🔧 baseline: reconciled to discussion harness v<version>`, and report every move.
 
 ## Rules
 
@@ -231,3 +231,28 @@ Grammar: workspace record = last-processed git commit; transcripts = per-file pr
 
 ## Runs
 ````
+
+`metadata/writing-styles/README.md`:
+
+````markdown
+# writing-styles — the operator's style registry
+
+> **Operator-owned state.** One file per writing register, named for it: `reading.md` (documents presented to the operator — the default), `blog.md`, `email.md`, … A style file is instructions to the writer: register, voice, form, length. The artifact rules' two-audience doctrine is the floor; a style refines on top of it. Style named but file missing → draft it from the operator's instructions in the moment, file it here marked `Not yet ratified`, apply it, surface it for ratification. Machine-facing writing (raw dumps, referential twins) is never styled from here.
+````
+
+`metadata/writing-styles/reading.md`:
+
+````markdown
+# reading — documents presented to the operator (default style)
+
+> Applies to anything the operator will read — readable editions, syntheses filed for reaction, reports. This default ships with the harness; refine in place, dated.
+
+- **Self-contained:** every referenced item's substance expanded inline where used; summarize in place when expansion would bloat; the reader never chases a link or an ID to understand a sentence.
+- **No reference soup:** no lane IDs, item codes, or `file:line` anchors in body prose — at most one pointer line to the machine twin.
+- **Present tense, declarative** — the document states what is, not a narration of what was done.
+- **Each point stands alone** — readable selectively, in any order, with its full meaning intact.
+- **Verdict first**, then support. Full sentences, plain words; no mid-document abbreviations or codenames.
+- **Numbered handles only where the operator disposes by number**; stable across editions.
+- **Tables for short enumerable facts only**; the argument lives in the prose.
+- **Verbosity welcome when it buys self-containment**; cut by dropping what doesn't change the reader's next move.
+````

package/data/harnesses/discussion/harness.json

@@ -1,11 +1,11 @@
 {
   "harness": "discussion",
   "name": "discussion",
-  "version": "0.2.1",
+  "version": "0.4.0",
   "files": [
     ".prettierrc.json",
     ".prettierignore",
     ".vscode/settings.json"
   ],
-  "digest": "14700b32c049"
+  "digest": "670ff91f4b1b"
 }

package/data/harnesses/discussion/rules/artifacts.md

@@ -12,6 +12,8 @@ What gets written in a topic folder. How sessions run is [method.md](method.md).
 
 A ratified class-3 doc **is** the goal-track canon — never double-book it under canon.
 
+**The two audiences**: every artifact serves exactly one reader — the **operator** (human) or the **agent** (main line, sub-agents, downstream syntheses). Operator-facing artifacts (syntheses, goal track, canon, auxiliaries the user reads) are **self-contained**: written in full verbosity, the substance of every cited item expanded inline in prose — summarized in place where full expansion would bloat — never lane IDs, item codes, or link trails the reader must chase. Agent-facing artifacts (raw dumps, and the referential twin of any operator doc) stay maximally cross-referenced: stable IDs, links, the citation grammar. When one document must serve both, it **forks**: the readable edition keeps the canonical name and slot; the referential twin lives in the topic's `machine/` subfolder and remains the citation-of-record (verification, adjudication, and downstream citing run against the twin). Each opens with a one-line pointer to the other; ratification stamps land on the readable edition and are mirrored onto the twin; the twins are the same content in two registers, never allowed to drift — a substantive change lands in both or is a break. Numbered handles the user disposes by (open questions, register items) survive in the readable edition — they are dialogue handles, not citations. The register itself is governed by the workspace style registry `metadata/writing-styles/`: one operator-owned file per register, `reading.md` the default for documents presented to the operator, others (`blog.md`, `email.md`, …) when the operator names one; a named-but-missing style is drafted from the operator's instructions in the moment, filed there unratified, and applied. Grandfathering applies: existing referential artifacts stand; fork on next touch or user request.
+
 **Banner**: class 1/2/3 artifacts and auxiliaries open with an H1 + `>` blockquote banner: **class · derivation (links + scale) · method · ISO date · ratification status**. Status applies to 2/3/auxiliaries only — raw dumps are immutable, never ratified. Exempt: canon (its own `**Status:**` line / orientation paragraph) and clips (two-line header).
 
 **Status vocabulary**: `**DRAFT — not yet ratified**` / `Not yet user-ratified` · `(ratified YYYY-MM-DD)` — at doc, section, or extract granularity · `**Superseded note (YYYY-MM-DD):** … kept as record` · `deferred — blocked on <gate>` vs the exclusion grades.

package/data/harnesses/discussion/rules/method.md

@@ -5,7 +5,7 @@ How sessions run in this workspace. What gets written is [artifacts.md](artifact
 ## Workspace layout
 
 - **Topic folders** — one folder = one long-running topic. Kebab-case noun phrase naming the **inquiry, not the deliverable** (`pricing-research`, not `pricing-report`). Every topic has a `README.md` (the record), a `metadata.md` (the map), and a `TOPICS.md` entry.
-- **`metadata/`** — all workspace state: `TOPICS.md` (topic index), `SESSIONS.md` (session ledger), `method-changelog.md` (workspace-local method notes; the harness itself versions via `.claude/harness.json`), `lessons/` (the operator layer: append-only log + always-loaded digest + forecasts), `ops/` (maintenance-agent run-logs). State lives here and nowhere else.
+- **`metadata/`** — all workspace state: `TOPICS.md` (topic index), `SESSIONS.md` (session ledger), `method-changelog.md` (workspace-local method notes; the harness itself versions via `.claude/harness.json`), `lessons/` (the operator layer: append-only log + always-loaded digest + forecasts), `ops/` (maintenance-agent run-logs), `writing-styles/` (the operator's style registry — one file per register, `reading.md` the default for operator-facing documents). State lives here and nowhere else.
 - **External instruments** — code/data a topic depends on (scraper, corpus, pipeline) lives **outside the workspace**, never at the root: this folder holds only topics and the harness. Record the dependency on the depending topic's README (external path + ratification status); exclusions are recorded on the excluder's side.
 - **Git** — the workspace **is a git repository** (the `discussion-baseline` agent initializes one). The SessionEnd hook auto-commits each session's changes as one `📝 session close` batch — never per-file commits. Milestone commits by hand are still welcome: `✨` content, `🔧` workspace/method. Root `.gitignore` stays minimal.
 - **Grandfathering** — when the method changes, never reshuffle existing artifacts to match. New artifacts follow current rules; old layouts stay, flagged where confusing.
@@ -66,6 +66,10 @@ Method lives in the rules (timeless); state lives in `metadata/` (current); topi
 
 One entry per session, appended at the bottom. An entry is the session's **summary**, rewritten in place when the session resumes — never a resume-log. Format: `## YYYY-MM-DD — <goal headline>` + bullets: `**Goal:**` (the user's stated aim; update it if it shifts mid-session) · `**Touched:**` · `**Filed:**` (linked) · `**Close state:**` (where it stopped, what it awaits). Entries point into topics; content never lives here.
 
+### `writing-styles/` — the style registry
+
+One operator-owned file per writing register (`reading.md` — the default for documents presented to the operator; `blog.md`, `email.md`, … as the operator introduces them). A style file is instructions to the writer — register, voice, form; the artifact rules' two-audience doctrine is the floor it refines. Style named but file missing → draft it from the operator's instructions in the moment, file it marked unratified, apply it. Machine-facing writing is never styled from here.
+
 ### `lessons/` + `ops/` — the operator layer
 
 - `metadata/lessons/` is two-tier: an append-only occurrence **`log/`** (one dated file per maintenance run, never edited, never loaded by default) distilled into **`DIGEST.md`** — the operator profile read at session start (**prior, not canon**; its reading-protocol block governs). Beside them: `forecasts.md` (the operator's falsifiable claims, captured in the moment; resolutions mined for calibration) and `distillation.md` (the maintenance instruction set + admission bar).

package/package.json

@@ -1,6 +1,6 @@
 {
     "name": "@nurix/etna",
-    "version": "0.19.10",
+    "version": "0.19.11",
     "description": "Bootstrap a project with a Nurix harness — copies the harness's CLAUDE.md, skills, agents, rules, and hooks directly into the project from a bundled payload (no marketplace fetch, no network).",
     "type": "module",
     "bin": {