no-one-did-it

Audit the book-level callback graph that tracks setup → payoff edges across chapters. Verifies every planted anchor has its declared downstream payoff and every payoff still has its upstream plant. Catches orphaned plants and orphaned payoffs. Reads `book/registries/callback-graph.yml`; runs book-wide when any graph chapter is rewritten. Cousin of fair-clue-audit (which covers chapter-internal recognition).

Build a structured responsibility-laundering case file from a historical, political, legal, corporate, war, or AI event.

Turn approved case files into chapter architecture for serious trade nonfiction.

Diagnose a chapter against the 10 reader-experience values in rule 12 (5 core + 5 craft) and build a defect map naming which values fail, with cited prose evidence, and recommending one of the five treatment classes from rule 08. Output is `process/defect-map/<n>-<slug>.md` plus a treatment-class row appended to `book/registries/treatment-classes.yml`.

Prepare citation-ready notes for drafting, fact-checking, and legal review.

Audit chapter prose for verbose inline `[CITE:]` markers that violate rule-13's slug-only invariant. Inline `[CITE:]` brackets must carry only card slugs (separated by `;` for multi-source claims); full citation apparatus lives in the source-ledger card and is compile-generated as Chicago NB endnote. Catches the failure mode where citation metadata leaks from card to prose. Cousin to `scan-cite-density.py` (the cheap pattern-level pass); this skill is the deeper read.

Audit the book's cognitive arc — the discriminations and concepts the reader acquires chapter by chapter — against the actual prose. For each discrimination, verifies introduction, consolidation, and application in every required chapter. For each concept, verifies it is named and used. Reads `book/registries/cognitive-arc.yml`.

Audit a chapter against its declared per-chapter contract (Hoare triple of reader-state pre/postconditions) and verify the chapter delivers the declared `knows`, `can_discriminate`, `feels`, and `primed_for` slots. The `feels:` slot resolves through rule 12 reader-experience values; passing requires both structural delivery AND core-value preservation.

Manage versioned amendments to a chapter's per-chapter contract during a rewrite cycle. Diffs pre vs post contract, requires a reason for every changed field, flags amendments that would mask Gate B failure (e.g., a `feels:` slot weakened to match the rewrite rather than its promise), and snapshots both versions into the chapter's audit history. Used by Wayne, Bonnie, and jerry-crew-chief at Gate B.

Build a structured counter-case file — a situation where someone would have been laundered into the goat role but escaped, was freed, or had the alibi pierced. Paired with every scapegoat case file; documents the intercepting mechanism and the transferable lesson.

Red-team a claim, case, chapter, or book section against overclaim, category collapse, and partisan distortion.

Convert allegation-stage facts into legally defensible chapter wording. Maps every claim about a living person or company to the correct procedural stage (alleged / reported / charged / admitted / settled / found-liable / convicted) and proposes safer phrasings tied to the documented public record. Used by Nancy for legal review and by Wayne for self-policing during drafting.

Cross-chapter dependency analyzer — combines the callback graph, motif registry, and cognitive arc into a single DAG. Identifies forward dependencies (hard fail), lateral dependencies on revised chapters (soft fail with blast radius), and cut-chapter blast radius. Runs after every chapter rewrite to surface downstream consequences before they ship.

Assign A/B/C/D evidence grades to claims by walking source type, corroboration count, and procedural stage through a deterministic decision tree. Used by Stephen for the verification gate and by every researcher for self-grading before handoff.

Audit a chapter or case file for narrative implication of mental state, motive, knowledge, causation, or chain responsibility that exceeds what cited evidence supports. Catches structural implication (sentence sequence, focalization, juxtaposition, named-then-named ladders) that verb-level overclaim scanning misses. Used by Stephen, Laura, and Nancy.

Build and validate a KDP-ready reflowable EPUB 3 of *No One Did It* from the v5 source of truth, conforming to the Amazon Kindle Publishing Guidelines. Use when the user wants to compile, build, export, or validate the Kindle / EPUB / KDP edition of the book. Governed by rule 16-kdp-epub. Produces dist/no-one-did-it.epub.

Audit the book-level motif registry that tracks recurring objects, phrases, and images across chapters. For each motif, verifies declared appearances exist, no motif appears in its `forbidden_in:` chapters, frequency floor is met, and declared evolution actually progresses (no flat repetition). Reads `book/registries/motif-registry.yml`. Distinct from metaphor-audit and device-audit.

Per-domain playbook for finding load-bearing primary sources — names the canonical archives, docket systems, FOIA paths, primary-document repositories, and standard-of-evidence rules for the four research domains (historical, war/statecraft, AI/technology, public law/politics) plus the cross-domain ICC/UN bodies. Used by every researcher to know where to look first and by Alan to verify domain-authority citations.

Audit chapter prose for rule-14 violations — meta-frame language ('this chapter', 'the book', 'the reader', 'readers', 'this section', 'the author'), author-voice 'you', modal-prescriptive forms ('you should', 'we must remember'), evasive-collective forms ('people tend to'). Catches violations the scanner can't see (judgment-level 'we' laundering, passive-voice attribution misses). Cousin of `scan-pronoun-discipline.py`. Used by Wayne during drafting and by Laura during red-team.

Build book proposal, sample-chapter positioning, comp-title logic, and public-facing pitch materials.

Cold-read a single publication-form chapter (book/chapters-v3/<n>-<slug>.md) AS A READER and produce a friction report across seven axes (comprehension, engagement, recognition, orientation, trust, takeaway, mechanics). Reports lived experience with HARD/SOFT severity; never proposes fixes; reads only the chapter prose. Used by the-reader agent. Output: process/reader-reports/<n>-<slug>-<date>.md.

Cold-read the whole assembled manuscript (dist/manuscript-v3.md) in one continuous sitting AS A READER and report cross-chapter experience — repetition fatigue, arc legibility, callback recognition, cumulative-trust drift, taxonomy coherence across chapters. The book-level companion to reader-cold-read (which is per-chapter). Reports lived experience with HARD/SOFT severity; never fixes; reads only the manuscript. Used by the-reader agent. Output: process/reader-reports/sweep-<date>.md.

Orchestrate the seven-stage pipeline that turns a (source, claim) pair into a verified, queryable, accumulating research card. Wires the existing source-ledger-discipline, citation-hygiene, evidence-grading, and case-file-method skills into a single operating procedure with Layer A (mechanical), Layer B (Stephen-led), and Layer C (specialist) verification.

Map control, benefit, knowledge, preventability, record control, and cost-bearing for a case.

Build narrative scenes from approved case files following the project's chapter rhythm. Covers opening-hook patterns, hidden-architecture reveal mechanics, recognition-reversal beats, and anti-laundering-rule endings. Used by Wayne to turn a chapter brief into prose; integrates audio-cadence considerations so audiobook narration works without rework.

Build source ledgers, evidence grades, quote logs, and disputed-claim registers.

Classify an event into the project's 4 canonical case categories (pure scapegoat / partial scapegoat / system-or-object alibi / cost-bearing goat) by walking diagnostic questions per category. Used by researchers, Bonnie, and Alan whenever a case's category is in dispute or not yet assigned.

Use when writing, reviewing, or naming any responsibility-laundering book artifact — pick the canonical noun or verb from this registry rather than coining a synonym. Loaded by NLPM's scorer and checker when R51 is enabled in .claude/nlpm.local.md.

Audit a chapter for voice-register distribution across three registers — R-primary (primary document quoted at full force), R-frame (newsroom-style paraphrase), R-analytic (the book's analytical voice). Verifies paragraph-level register tags exist, distribution falls within tunable thresholds, and register transitions are marked rather than silent. Used by Wayne and Stephen on `structural-polish` and `full-craft-rewrite` chapters.