paperlint 3.1.3 → 4.0.0

package/scripts/test.test.ts

@@ -0,0 +1,78 @@
+/**
+ * `npm test`'s runner: both suites run whatever the first returned, each failure is named, and
+ * the harness arguments reach the harness runner only.
+ */
+import assert from "node:assert/strict";
+import { test } from "vitest";
+import { runSuites, SUITES, type Spawn } from "./test.ts";
+
+/** A spawn that records every call and exits with `status[file]` (`null` for a signal). */
+const fake = (status: Record<string, number | null>) => {
+  const calls: string[][] = [];
+  const spawn: Spawn = (file, args) => {
+    calls.push([file, ...args]);
+    return { status: status[file] ?? null };
+  };
+  return { calls, spawn };
+};
+
+test("a failing vitest does not skip the harnesses, and is named as the failure", () => {
+  const { calls, spawn } = fake({ vitest: 1, vigiles: 0 });
+  const said: string[] = [];
+  assert.equal(
+    runSuites(["--no-skip"], { spawn, err: (s) => said.push(s) }),
+    1,
+  );
+  assert.deepEqual(calls, [
+    ["vitest", "run"],
+    ["vigiles", "test", "--min=1", "--no-skip"],
+  ]);
+  assert.deepEqual(said, [
+    "✗ vitest failed (exit 1) — its own report is above",
+  ]);
+});
+
+test("both passing is 0 and silent; a harness killed by a signal is exit 1, named", () => {
+  const ok = fake({ vitest: 0, vigiles: 0 });
+  assert.equal(runSuites([], { spawn: ok.spawn, err: assert.fail }), 0);
+  const killed = fake({ vitest: 0, vigiles: null });
+  const said: string[] = [];
+  assert.equal(
+    runSuites([], { spawn: killed.spawn, err: (s) => said.push(s) }),
+    1,
+  );
+  assert.deepEqual(said, [
+    "✗ harnesses failed (exit 1) — its own report is above",
+  ]);
+  assert.deepEqual(
+    SUITES.map((s) => s.name),
+    ["vitest", "harnesses"],
+  );
+});
+
+test("every suite runs the SOURCES: the paperlint-source condition is in NODE_OPTIONS, the caller's kept", () => {
+  const seen: (string | undefined)[] = [];
+  const spawn: Spawn = (_file, _args, options) => {
+    seen.push(options.env.NODE_OPTIONS);
+    return { status: 0 };
+  };
+  assert.equal(
+    runSuites([], {
+      spawn,
+      err: assert.fail,
+      env: { NODE_OPTIONS: "--import=./x.ts" },
+    }),
+    0,
+  );
+  assert.deepEqual(seen, [
+    "--conditions=paperlint-source --import=./x.ts",
+    "--conditions=paperlint-source --import=./x.ts",
+  ]);
+  // Without a caller's NODE_OPTIONS there is no stray trailing space.
+  seen.length = 0;
+  runSuites([], { spawn, err: assert.fail, env: {} });
+  assert.deepEqual(seen, [
+    "--conditions=paperlint-source",
+    "--conditions=paperlint-source",
+  ]);
+});

package/scripts/test.ts

@@ -0,0 +1,87 @@
+/**
+ * `npm test`: the unit tests (vitest), then the harnesses (`vigiles test`). BOTH always run.
+ *
+ * Until #52 this was `vitest run && vigiles test --min=1`. Under `npm run coverage` a single
+ * failing vitest test then skipped every harness, and what the run printed last was c8's summary:
+ * lines, branches and functions each some six points below the floor. The one failing test sat
+ * above that, looking like a consequence rather than the cause. Running both suites keeps the
+ * coverage report whole, so a failing test is reported as itself and the coverage figures still
+ * mean what they say.
+ *
+ * Arguments are the harness runner's (`npm test -- --no-skip`), as they were before.
+ *
+ * Both suites run the SOURCES: every child gets `--conditions=paperlint-source`, so `#lib/*` and
+ * `#eslint-rules/*` resolve to `.ts`, not to `dist/`. This runner is the one owner of that
+ * setting. When only `npm run coverage` passed it, a plain `npm test` loaded the rules twice —
+ * `dist/` through `eslint.config.mjs`, `.ts` through the harness — and a harness comparing the two
+ * failed on macOS CI, the one job that runs `npm test` bare.
+ */
+import { spawnSync } from "node:child_process";
+import { isMain } from "../skills/paper-pipeline/scripts/consumer.mjs";
+
+/** The two suites, in order: what a failure is named as, and the command. */
+export interface Suite {
+  readonly name: string;
+  /** The program, then its arguments. */
+  readonly command: readonly [string, ...string[]];
+}
+
+/** What `runSuites` needs from a finished process: its exit status, `null` when a signal ended it. */
+export type Spawn = (
+  file: string,
+  args: readonly string[],
+  options: { stdio: "inherit"; env: NodeJS.ProcessEnv },
+) => { readonly status: number | null };
+
+/** The condition that points package `imports` at the TypeScript sources instead of `dist/`. */
+const SOURCE_CONDITION = "--conditions=paperlint-source";
+
+/** `env` with the source condition first in NODE_OPTIONS, whatever the caller already had kept. */
+export function withSources(env: NodeJS.ProcessEnv): NodeJS.ProcessEnv {
+  const own = env.NODE_OPTIONS?.trim();
+  return {
+    ...env,
+    NODE_OPTIONS: own ? `${SOURCE_CONDITION} ${own}` : SOURCE_CONDITION,
+  };
+}
+
+export const SUITES: readonly Suite[] = [
+  { name: "vitest", command: ["vitest", "run"] },
+  { name: "harnesses", command: ["vigiles", "test", "--min=1"] },
+];
+
+/**
+ * Run every suite, whatever the one before it returned, and name the ones that failed.
+ * @returns 0 when every suite passed; otherwise the first failing suite's exit code (1 for a signal).
+ */
+export function runSuites(
+  args: readonly string[],
+  {
+    spawn = spawnSync,
+    err = console.error,
+    suites = SUITES,
+    env = process.env,
+  }: {
+    spawn?: Spawn;
+    err?: (line: string) => void;
+    suites?: readonly Suite[];
+    env?: NodeJS.ProcessEnv;
+  } = {},
+): number {
+  const failed = suites.flatMap(({ name, command }) => {
+    const [file, ...rest] = command;
+    const r = spawn(file, [...rest, ...(name === "harnesses" ? args : [])], {
+      stdio: "inherit",
+      env: withSources(env),
+    });
+    return r.status === 0 ? [] : [{ name, code: r.status ?? 1 }];
+  });
+  for (const f of failed)
+    err(
+      `✗ ${f.name} failed (exit ${String(f.code)}) — its own report is above`,
+    );
+  const [first] = failed;
+  return first === undefined ? 0 : first.code;
+}
+
+if (isMain(import.meta.url)) process.exit(runSuites(process.argv.slice(2)));

package/skills/analyze-sibling-paper/SKILL.md

@@ -5,24 +5,10 @@ context: fork
 allowed-tools: [WebSearch, WebFetch, Read, Write, Grep, Glob, Bash, Agent]
 ---
 
-<!-- vigiles:sha256:f528cbe9e892d6d0 compiled from skills/analyze-sibling-paper/SKILL.md.spec.ts -->
+<!-- vigiles:sha256:238796152df07749 compiled from skills/analyze-sibling-paper/SKILL.md.spec.ts -->
 
 # analyze-sibling-paper — settle "isn't this just X?" before a reviewer does
 
-## Run me
-
-🔴 FIRST, before any other step:
-
-```
-node .claude/skills/paper-pipeline/scripts/announce.mjs analyze-sibling-paper <paper-dir>
-```
-
-An advisory pass cannot be observed failing — silence is both its error state and its normal
-state — so starting is an event, and events get written down.
-
-The `<paper-dir>` argument is **your** paper, not the sibling — the row belongs to the paper being
-defended. The sibling is named by `<report-path>` when the verdict is recorded.
-
 When a paper close to yours surfaces, the wrong move is to cite it from its abstract and move on — that
 leaves a scoop risk you can't see and a reviewer can. This skill reads the *actual* competitor, judges
 whether your contribution genuinely differs, and produces a saved analysis with concrete action points
@@ -114,30 +100,6 @@ and the action points (with the exact clause text to add/replace). Per the save-
 analysis that lives only in a chat is lost the moment the session ends — and it's exactly what you'll need
 again at rebuttal. **A close sibling with no file in `<paper-dir>/siblings/` is an unfinished analysis.**
 
-## Record the verdict
-
-🔴 LAST step, once the deliverable exists:
-
-```
-node .claude/skills/paper-pipeline/scripts/ledger.mjs record analyze-sibling-paper <paper-dir> FINDING <count> <report-path>
-node .claude/skills/paper-pipeline/scripts/ledger.mjs record analyze-sibling-paper <paper-dir> ABSTAINED <reason> "<one line>"
-```
-
-**FINDING** — `<count>` is the number of action points the card produced (positioning clauses plus
-*MUST CITE* entries), `<report-path>` is the saved card, which names the sibling. Add `--blocking`
-for a genuine scoop, which the skill already treats as an escalation rather than a clause.
-**ABSTAINED** — `no-witness`: the sibling was read in full and the delta needs no text to change.
-`blocked`: the sibling's full text could not be obtained, so only its abstract was seen — which is
-explicitly not an analysis and must never be recorded as one.
-
-🔴 **There is no PASS.** "The delta is real" read identically whether the sibling had been read
-whole or skimmed, and this skill's own first rule is that an abstract-only delta is not a verdict.
-`no-witness` and `blocked` now say which happened.
-
-One row per sibling analysed, filed under its own `--check=<sibling-slug>`; several finding rows
-against one paper is the normal shape here, not a check that keeps failing. Before 2026-08-10 they
-would have overwritten one another.
-
 ## Rules
 - **Read the paper, not the abstract.** An abstract-only "delta" is not a verdict — and the card must
   say so: `read: abstract` in its frontmatter, and which parts in its `**Read:**` line.

package/skills/analyze-sibling-paper/SKILL.md.spec.ts

@@ -24,20 +24,6 @@ export default experimental_skill({
   body: `
 # analyze-sibling-paper — settle "isn't this just X?" before a reviewer does
 
-## Run me
-
-🔴 FIRST, before any other step:
-
-\`\`\`
-node .claude/skills/paper-pipeline/scripts/announce.mjs analyze-sibling-paper <paper-dir>
-\`\`\`
-
-An advisory pass cannot be observed failing — silence is both its error state and its normal
-state — so starting is an event, and events get written down.
-
-The \`<paper-dir>\` argument is **your** paper, not the sibling — the row belongs to the paper being
-defended. The sibling is named by \`<report-path>\` when the verdict is recorded.
-
 When a paper close to yours surfaces, the wrong move is to cite it from its abstract and move on — that
 leaves a scoop risk you can't see and a reviewer can. This skill reads the *actual* competitor, judges
 whether your contribution genuinely differs, and produces a saved analysis with concrete action points
@@ -129,30 +115,6 @@ and the action points (with the exact clause text to add/replace). Per the save-
 analysis that lives only in a chat is lost the moment the session ends — and it's exactly what you'll need
 again at rebuttal. **A close sibling with no file in \`<paper-dir>/siblings/\` is an unfinished analysis.**
 
-## Record the verdict
-
-🔴 LAST step, once the deliverable exists:
-
-\`\`\`
-node .claude/skills/paper-pipeline/scripts/ledger.mjs record analyze-sibling-paper <paper-dir> FINDING <count> <report-path>
-node .claude/skills/paper-pipeline/scripts/ledger.mjs record analyze-sibling-paper <paper-dir> ABSTAINED <reason> "<one line>"
-\`\`\`
-
-**FINDING** — \`<count>\` is the number of action points the card produced (positioning clauses plus
-*MUST CITE* entries), \`<report-path>\` is the saved card, which names the sibling. Add \`--blocking\`
-for a genuine scoop, which the skill already treats as an escalation rather than a clause.
-**ABSTAINED** — \`no-witness\`: the sibling was read in full and the delta needs no text to change.
-\`blocked\`: the sibling's full text could not be obtained, so only its abstract was seen — which is
-explicitly not an analysis and must never be recorded as one.
-
-🔴 **There is no PASS.** "The delta is real" read identically whether the sibling had been read
-whole or skimmed, and this skill's own first rule is that an abstract-only delta is not a verdict.
-\`no-witness\` and \`blocked\` now say which happened.
-
-One row per sibling analysed, filed under its own \`--check=<sibling-slug>\`; several finding rows
-against one paper is the normal shape here, not a check that keeps failing. Before 2026-08-10 they
-would have overwritten one another.
-
 ## Rules
 - **Read the paper, not the abstract.** An abstract-only "delta" is not a verdict — and the card must
   say so: \`read: abstract\` in its frontmatter, and which parts in its \`**Read:**\` line.

package/skills/argument-arc/SKILL.md

@@ -1,10 +1,10 @@
 ---
 name: argument-arc
 description: Build or repair the paper's argument architecture — the one-sentence-per-section outline, the bottom-up inevitability pass, and the name/number budget. Run it when the reader says the paper throws ideas at them, when a structural objection repeats, or before any large rewrite. Not a prose or length skill.
-allowed-tools: [Read, Write, Grep, Glob, Agent, Bash(node .claude/skills/paper-pipeline/scripts/announce.mjs:*), Bash(node .claude/skills/paper-pipeline/scripts/ledger.mjs:*)]
+allowed-tools: [Read, Write, Grep, Glob, Agent]
 ---
 
-<!-- vigiles:sha256:05a1eaa79bb596d5 compiled from skills/argument-arc/SKILL.md.spec.ts -->
+<!-- vigiles:sha256:66be3161e5bde916 compiled from skills/argument-arc/SKILL.md.spec.ts -->
 
 # argument-arc — does the paper carry the reader to one conclusion
 
@@ -14,17 +14,6 @@ allowed-tools: [Read, Write, Grep, Glob, Agent, Bash(node .claude/skills/paper-p
 > whether the argument exists. Run it *before* them — cutting words inside a broken arc is how a
 > session burns a day and ships the same paper.
 
-## Run me
-
-🔴 FIRST, before any other step:
-
-```
-node .claude/skills/paper-pipeline/scripts/announce.mjs argument-arc <paper-dir>
-```
-
-An advisory pass cannot be observed failing — silence is both its error state and its normal
-state — so starting is an event, and events get written down.
-
 The failure it exists to catch has a signature: every paragraph is defensible, every number is real,
 and the reader still finishes the section unable to say what it was for. That is not a prose problem
 and no amount of rewriting sentences fixes it.
@@ -48,7 +37,6 @@ came out — which is how a run gets thrown away. That is not hypothetical: it w
 data is collected costs the data. Costs a paragraph; saves a study.**
 
 `build-benchmark` reads this paragraph before designing, and refuses to proceed if `frame` is empty.
-`pipeline-check.mjs` reports a study that ran with no stated claim.
 
 *Added 2026-08-03 alongside the replacement of the numbered stage list — this skill previously existed
 only as a repair, which meant nobody stated the claim while stating it was still cheap.*
@@ -125,28 +113,6 @@ most needs help. This skill does:
   the calendar against it is a category error.
 - **Rebuild produces a new outline through steps 1–4 above, and it too gets shown before editing.**
 
-## Record the verdict
-
-🔴 LAST step, once the deliverable exists:
-
-```
-node .claude/skills/paper-pipeline/scripts/ledger.mjs record argument-arc <paper-dir> FINDING <count> <report-path>
-node .claude/skills/paper-pipeline/scripts/ledger.mjs record argument-arc <paper-dir> ABSTAINED <reason> "<one line>"
-```
-
-🔴 **There is no PASS.** "The arc carries the reader" is not a value this pass can write down; it is
-what a reader may conclude from the absence of findings, and the concluding is theirs.
-
-**FINDING** — the arc is broken; `<count>` is the number of sections the new outline moves, merges
-or deletes, and `<report-path>` is that outline. Add `--blocking` when there is no conclusion
-sentence to build an arc from: that refusal is a finding about the draft, not an aborted run, and
-`<report-path>` is the one-line statement of what is missing.
-**ABSTAINED** — `no-witness`: the outline was read end to end and nothing moved. `blocked`: there
-was no outline to read at all.
-
-An `ABSTAINED no-witness` on a draft the author has twice called a pile is a missed finding, and
-`status.mjs` will start asking about a check that has only ever abstained.
-
 ## Rules
 
 - **The arc is judged on the outline, never on the draft.** If you find yourself rereading paragraphs

package/skills/argument-arc/SKILL.md.spec.ts

@@ -10,15 +10,7 @@ export default experimental_skill({
   name: "argument-arc",
   description:
     "Build or repair the paper's argument architecture — the one-sentence-per-section outline, the bottom-up inevitability pass, and the name/number budget. Run it when the reader says the paper throws ideas at them, when a structural objection repeats, or before any large rewrite. Not a prose or length skill.",
-  tools: [
-    "Read",
-    "Write",
-    "Grep",
-    "Glob",
-    "Agent",
-    "Bash(node .claude/skills/paper-pipeline/scripts/announce.mjs:*)",
-    "Bash(node .claude/skills/paper-pipeline/scripts/ledger.mjs:*)",
-  ],
+  tools: ["Read", "Write", "Grep", "Glob", "Agent"],
   body: `
 # argument-arc — does the paper carry the reader to one conclusion
 
@@ -28,17 +20,6 @@ export default experimental_skill({
 > whether the argument exists. Run it *before* them — cutting words inside a broken arc is how a
 > session burns a day and ships the same paper.
 
-## Run me
-
-🔴 FIRST, before any other step:
-
-\`\`\`
-node .claude/skills/paper-pipeline/scripts/announce.mjs argument-arc <paper-dir>
-\`\`\`
-
-An advisory pass cannot be observed failing — silence is both its error state and its normal
-state — so starting is an event, and events get written down.
-
 The failure it exists to catch has a signature: every paragraph is defensible, every number is real,
 and the reader still finishes the section unable to say what it was for. That is not a prose problem
 and no amount of rewriting sentences fixes it.
@@ -62,7 +43,6 @@ came out — which is how a run gets thrown away. That is not hypothetical: it w
 data is collected costs the data. Costs a paragraph; saves a study.**
 
 \`build-benchmark\` reads this paragraph before designing, and refuses to proceed if \`frame\` is empty.
-\`pipeline-check.mjs\` reports a study that ran with no stated claim.
 
 *Added 2026-08-03 alongside the replacement of the numbered stage list — this skill previously existed
 only as a repair, which meant nobody stated the claim while stating it was still cheap.*
@@ -139,28 +119,6 @@ most needs help. This skill does:
   the calendar against it is a category error.
 - **Rebuild produces a new outline through steps 1–4 above, and it too gets shown before editing.**
 
-## Record the verdict
-
-🔴 LAST step, once the deliverable exists:
-
-\`\`\`
-node .claude/skills/paper-pipeline/scripts/ledger.mjs record argument-arc <paper-dir> FINDING <count> <report-path>
-node .claude/skills/paper-pipeline/scripts/ledger.mjs record argument-arc <paper-dir> ABSTAINED <reason> "<one line>"
-\`\`\`
-
-🔴 **There is no PASS.** "The arc carries the reader" is not a value this pass can write down; it is
-what a reader may conclude from the absence of findings, and the concluding is theirs.
-
-**FINDING** — the arc is broken; \`<count>\` is the number of sections the new outline moves, merges
-or deletes, and \`<report-path>\` is that outline. Add \`--blocking\` when there is no conclusion
-sentence to build an arc from: that refusal is a finding about the draft, not an aborted run, and
-\`<report-path>\` is the one-line statement of what is missing.
-**ABSTAINED** — \`no-witness\`: the outline was read end to end and nothing moved. \`blocked\`: there
-was no outline to read at all.
-
-An \`ABSTAINED no-witness\` on a draft the author has twice called a pile is a missed finding, and
-\`status.mjs\` will start asking about a check that has only ever abstained.
-
 ## Rules
 
 - **The arc is judged on the outline, never on the draft.** If you find yourself rereading paragraphs

package/skills/build-benchmark/SKILL.md

@@ -5,21 +5,10 @@ context: fork
 allowed-tools: [Read, Write, Edit, Grep, Glob, Bash, Agent]
 ---
 
-<!-- vigiles:sha256:067ada6f8aa44d5b compiled from skills/build-benchmark/SKILL.md.spec.ts -->
+<!-- vigiles:sha256:0b91129ca6a6b2a3 compiled from skills/build-benchmark/SKILL.md.spec.ts -->
 
 # build-benchmark — the study + the artifact reviewers can run
 
-## Run me
-
-🔴 FIRST, before any other step:
-
-```
-node .claude/skills/paper-pipeline/scripts/announce.mjs build-benchmark <paper-dir>
-```
-
-An advisory pass cannot be observed failing — silence is both its error state and its normal
-state — so starting is an event, and events get written down.
-
 A measurement paper is only as strong as the artifact a reviewer can `cd` into and re-run. This skill
 covers both halves: the study design that makes the finding true, and the self-checking artifact that
 makes it *verifiable*. The contribution is the **method**, not the one tool you happened to test — build
@@ -163,35 +152,6 @@ real-code-through-real-contract execution reveals it.
 Before submitting, verify the artifact you built with the reviewer-side reproduction protocol:
 **`references/adversarial-cold-repro.md`** (cold re-run, three-way reconcile, robustness attacks).
 
-## Record the verdict
-
-🔴 LAST step, once the deliverable exists:
-
-```
-node .claude/skills/paper-pipeline/scripts/ledger.mjs record build-benchmark <paper-dir> FINDING <count> <report-path>
-node .claude/skills/paper-pipeline/scripts/ledger.mjs record build-benchmark <paper-dir> ABSTAINED <reason> "<one line>"
-```
-
-🔴 **There is no PASS.** An artifact that recomputes every headline number and exits 0 has produced
-no finding; it has not certified the study. Record the absence, do not name it a success.
-
-**FINDING** — `<count>` numbers did not reproduce, or reproduce only with caveats; `<report-path>`
-is the artifact output. Add `--blocking` for the §0 refusal: `frame` is empty, so the study was not
-designed.
-**ABSTAINED** — `no-witness`: the artifact ran and every number reproduced. `input-missing`: the
-raw data is not in the repo. `crashed`: the harness itself died.
-
-🔴 That §0 refusal is a **finding, not an aborted run** — it is a fact about the work, so it is a
-FINDING and not an abstention. Record it and stop. A study that was never designed leaves exactly
-the same silence as one that is still running, and the difference costs a week to rediscover.
-
-🔴 **THREE MECHANICAL CHECKS FILE UNDER THIS SKILL** and each has its own ledger row:
-`build-benchmark/check-provenance`, `build-benchmark/arm-permutation`,
-`build-benchmark/delivered-pdf` (see `.claude/skills/paper-pipeline/scripts/run-mechanical.mjs`). Until 2026-08-10 the
-ledger keyed on the SKILL, so a clean run of one erased a finding of another from every derived
-view — which is why two of the three sat unwired. This block records the JUDGEMENT pass, under the
-bare key `build-benchmark`; never file a mechanical result here.
-
 ## Compose with
 - **argument-arc (frame mode)** — 🔴 **hard input.** Owns row `frame`, the stated claim. No `frame`, no study.
 - **research-ideate** (upstream) — supplies the contribution and the pitfall to invert; this skill turns

package/skills/build-benchmark/SKILL.md.spec.ts

@@ -15,17 +15,6 @@ export default experimental_skill({
   body: `
 # build-benchmark — the study + the artifact reviewers can run
 
-## Run me
-
-🔴 FIRST, before any other step:
-
-\`\`\`
-node .claude/skills/paper-pipeline/scripts/announce.mjs build-benchmark <paper-dir>
-\`\`\`
-
-An advisory pass cannot be observed failing — silence is both its error state and its normal
-state — so starting is an event, and events get written down.
-
 A measurement paper is only as strong as the artifact a reviewer can \`cd\` into and re-run. This skill
 covers both halves: the study design that makes the finding true, and the self-checking artifact that
 makes it *verifiable*. The contribution is the **method**, not the one tool you happened to test — build
@@ -169,35 +158,6 @@ real-code-through-real-contract execution reveals it.
 Before submitting, verify the artifact you built with the reviewer-side reproduction protocol:
 **\`references/adversarial-cold-repro.md\`** (cold re-run, three-way reconcile, robustness attacks).
 
-## Record the verdict
-
-🔴 LAST step, once the deliverable exists:
-
-\`\`\`
-node .claude/skills/paper-pipeline/scripts/ledger.mjs record build-benchmark <paper-dir> FINDING <count> <report-path>
-node .claude/skills/paper-pipeline/scripts/ledger.mjs record build-benchmark <paper-dir> ABSTAINED <reason> "<one line>"
-\`\`\`
-
-🔴 **There is no PASS.** An artifact that recomputes every headline number and exits 0 has produced
-no finding; it has not certified the study. Record the absence, do not name it a success.
-
-**FINDING** — \`<count>\` numbers did not reproduce, or reproduce only with caveats; \`<report-path>\`
-is the artifact output. Add \`--blocking\` for the §0 refusal: \`frame\` is empty, so the study was not
-designed.
-**ABSTAINED** — \`no-witness\`: the artifact ran and every number reproduced. \`input-missing\`: the
-raw data is not in the repo. \`crashed\`: the harness itself died.
-
-🔴 That §0 refusal is a **finding, not an aborted run** — it is a fact about the work, so it is a
-FINDING and not an abstention. Record it and stop. A study that was never designed leaves exactly
-the same silence as one that is still running, and the difference costs a week to rediscover.
-
-🔴 **THREE MECHANICAL CHECKS FILE UNDER THIS SKILL** and each has its own ledger row:
-\`build-benchmark/check-provenance\`, \`build-benchmark/arm-permutation\`,
-\`build-benchmark/delivered-pdf\` (see \`.claude/skills/paper-pipeline/scripts/run-mechanical.mjs\`). Until 2026-08-10 the
-ledger keyed on the SKILL, so a clean run of one erased a finding of another from every derived
-view — which is why two of the three sat unwired. This block records the JUDGEMENT pass, under the
-bare key \`build-benchmark\`; never file a mechanical result here.
-
 ## Compose with
 - **argument-arc (frame mode)** — 🔴 **hard input.** Owns row \`frame\`, the stated claim. No \`frame\`, no study.
 - **research-ideate** (upstream) — supplies the contribution and the pitfall to invert; this skill turns

package/skills/camera-ready/SKILL.md

@@ -4,21 +4,10 @@ description: On acceptance, turn the anonymized-for-review paper into the de-ano
 allowed-tools: [Read, Write, Edit, Grep, Glob, Bash, WebSearch, WebFetch]
 ---
 
-<!-- vigiles:sha256:8fa0190054cc5314 compiled from skills/camera-ready/SKILL.md.spec.ts -->
+<!-- vigiles:sha256:5c85ef4004c31956 compiled from skills/camera-ready/SKILL.md.spec.ts -->
 
 # camera-ready — de-anonymize an accepted paper into the final proceedings version
 
-## Run me
-
-🔴 FIRST, before any other step:
-
-```
-node .claude/skills/paper-pipeline/scripts/announce.mjs camera-ready <paper-dir>
-```
-
-An advisory pass cannot be observed failing — silence is both its error state and its normal
-state — so starting is an event, and events get written down.
-
 The reviewed PDF was anonymized on purpose. Acceptance flips that: the camera-ready carries your
 real name, your real repo, and an archival DOI — and it's the version that gets indexed, so it's the
 actual authorship evidence. This skill is the reverse of the anonymization you did at
@@ -113,28 +102,6 @@ If tight, ACM allows references to spill into the reference-only extra pages.
 - Record the paper's DOI, the artifact DOI, and the ORCID in the paper's HANDOFF — those three IDs are
   the authorship evidence and the anchor the extension (`extend-paper`) builds on.
 
-## 6. Record the verdict
-
-🔴 LAST step, once the deliverable exists:
-
-```
-node .claude/skills/paper-pipeline/scripts/ledger.mjs record camera-ready <paper-dir> FINDING <count> <report-path>
-node .claude/skills/paper-pipeline/scripts/ledger.mjs record camera-ready <paper-dir> ABSTAINED <reason> "<one line>"
-```
-
-**FINDING** — `<count>` residual items still open; `<report-path>` names them. Add `--blocking` for
-anything that must not be pushed past: anonymization residue, a dead artifact link, or — on a
-security paper — disclosure not yet complete.
-**ABSTAINED** — `no-witness`: shipped, de-anonymized, DOI live, page limit re-checked, with the DOI
-in the note. `blocked`: the acceptance notice has not arrived, so there is nothing to make ready.
-
-🔴 That blocking finding is the only one in this pipeline whose consequence is **irreversible**. The
-public de-anonymized repo is Google-findable the moment it is pushed, so record it before, not after.
-
-🔴 **There is no PASS**, and on this skill that is not a formality: a stored "shipped" would have
-been the one row in the pipeline that could be true of a repo nobody had looked at. The DOI in the
-note is the witness. Without it there is nothing to check the row against.
-
 ## Compose with
 - **submit-paper** (upstream — this reverses what it anonymized).
 - **paper-pipeline/references/anonymization.md** — the canonical list of anonymization moves; undo each.

package/skills/camera-ready/SKILL.md.spec.ts

@@ -23,17 +23,6 @@ export default experimental_skill({
   body: `
 # camera-ready — de-anonymize an accepted paper into the final proceedings version
 
-## Run me
-
-🔴 FIRST, before any other step:
-
-\`\`\`
-node .claude/skills/paper-pipeline/scripts/announce.mjs camera-ready <paper-dir>
-\`\`\`
-
-An advisory pass cannot be observed failing — silence is both its error state and its normal
-state — so starting is an event, and events get written down.
-
 The reviewed PDF was anonymized on purpose. Acceptance flips that: the camera-ready carries your
 real name, your real repo, and an archival DOI — and it's the version that gets indexed, so it's the
 actual authorship evidence. This skill is the reverse of the anonymization you did at
@@ -128,28 +117,6 @@ If tight, ACM allows references to spill into the reference-only extra pages.
 - Record the paper's DOI, the artifact DOI, and the ORCID in the paper's HANDOFF — those three IDs are
   the authorship evidence and the anchor the extension (\`extend-paper\`) builds on.
 
-## 6. Record the verdict
-
-🔴 LAST step, once the deliverable exists:
-
-\`\`\`
-node .claude/skills/paper-pipeline/scripts/ledger.mjs record camera-ready <paper-dir> FINDING <count> <report-path>
-node .claude/skills/paper-pipeline/scripts/ledger.mjs record camera-ready <paper-dir> ABSTAINED <reason> "<one line>"
-\`\`\`
-
-**FINDING** — \`<count>\` residual items still open; \`<report-path>\` names them. Add \`--blocking\` for
-anything that must not be pushed past: anonymization residue, a dead artifact link, or — on a
-security paper — disclosure not yet complete.
-**ABSTAINED** — \`no-witness\`: shipped, de-anonymized, DOI live, page limit re-checked, with the DOI
-in the note. \`blocked\`: the acceptance notice has not arrived, so there is nothing to make ready.
-
-🔴 That blocking finding is the only one in this pipeline whose consequence is **irreversible**. The
-public de-anonymized repo is Google-findable the moment it is pushed, so record it before, not after.
-
-🔴 **There is no PASS**, and on this skill that is not a formality: a stored "shipped" would have
-been the one row in the pipeline that could be true of a repo nobody had looked at. The DOI in the
-note is the witness. Without it there is nothing to check the row against.
-
 ## Compose with
 - **submit-paper** (upstream — this reverses what it anonymized).
 - **paper-pipeline/references/anonymization.md** — the canonical list of anonymization moves; undo each.