zero-slop 2.5.8 → 2.6.1

package/data/patterns.json

@@ -157,7 +157,7 @@
   {
    "name": "performed-candor",
    "cat": "performed",
-   "rx": "\\b(?:let(?:(?:'|\u2019)s| us) be (?:honest|real|clear)|here(?:(?:'|\u2019)s| is) the (?:thing|truth|kicker|deal|catch)|i(?:'|\u2019)ll be honest|the (?:uncomfortable|hard) truth is|truth be told|no fluff|real talk|not gonna lie|if i(?:'|\u2019)m being honest|let me be (?:crystal |perfectly )?clear)\\b",
+   "rx": "\\b(?:let(?:(?:'|\u2019)s| us) be (?:honest|real|clear)|here(?:(?:'|\u2019)s| is) the (?:thing|truth|kicker|deal|catch|detail|part|wrinkle|nuance|upshot|punchline|rub)|i(?:'|\u2019)ll be honest|the (?:uncomfortable|hard) truth is|truth be told|no fluff|real talk|not gonna lie|if i(?:'|\u2019)m being honest|let me be (?:crystal |perfectly )?clear)\\b",
    "w": 4,
    "first_seen": "2026-08-03",
    "last_confirmed": "2026-08-15"
@@ -523,6 +523,33 @@
    "first_seen": "2026-08-14",
    "last_confirmed": "2026-08-14"
   },
+  {
+   "name": "isocolon-ditransitive",
+   "cat": "contrast",
+   "rx": "\\b(let|give|hand|show|tell|offer|teach|buy|cost|earn|save|bring|send|win)s? you\\b[^.!?]{0,70}[.!?]\\s+[^.!?]{0,70}\\b\\1s? you\\b",
+   "hints": ["you"],
+   "w": 4.5,
+   "first_seen": "2026-08-26",
+   "last_confirmed": "2026-08-26"
+  },
+  {
+   "name": "this-is-what-looks-like",
+   "cat": "contrast",
+   "rx": "(?:^|[.!?]\\s+|\\n)(?:this|that) is what [\\w '\u2019-]{2,40} looks like\\b",
+   "hints": ["looks like"],
+   "w": 4,
+   "first_seen": "2026-08-26",
+   "last_confirmed": "2026-08-26"
+  },
+  {
+   "name": "no-x-had-to",
+   "cat": "contrast",
+   "rx": "(?:^|[.!?]\\s+|\\n)No [\\w '\u2019-]{2,40} (?:had to|needed to|has to|ever) [\\w '\u2019-]{2,60}\\.\\s+[\\w '\u2019-]{2,40} (?:did|made|chose|decided|built|released|shipped|published)\\b",
+   "hints": ["had to", "needed to", "has to", "ever"],
+   "w": 4,
+   "first_seen": "2026-08-26",
+   "last_confirmed": "2026-08-26"
+  },
   {
    "name": "not-the-but-the",
    "cat": "contrast",
@@ -1709,7 +1736,7 @@
   {
    "name": "chatgpt-artifact",
    "cat": "artifact",
-   "rx": "\\boaicite\\b|\\boai_citation\\b|\\bciteturn\\d|\\butm_source=(?:chatgpt(?:\\.com)?|openai)\\b|:contentReference\\[|\\battributableIndex\\b|\\[cite: ?\\d|\\bturn\\d+(?:search|news|image|view)\\d+\\b|\\[span_\\d|\\(start_span\\)|\\bgrok_(?:card|render)|\\bppl-ai-file-upload\\b|\\battached_file\\b",
+   "rx": "\\boaicite\\b|\\boai_citation\\b|\\bciteturn\\d|\\butm_source=(?:chatgpt(?:\\.com)?|openai(?:\\.com)?|copilot(?:\\.com)?|claude\\.ai|perplexity\\.ai|gemini\\.google\\.com)\\b|\\breferrer=grok\\.com\\b|:?contentReference\\[(?:oaicite:)?|\\battributableIndex\\b|\\[cite: ?\\d|\\bturn\\d+(?:search|news|image|view)\\d+\\b|\\[span_\\d|\\(start_span\\)|\\bgrok_(?:card|render)|\\bppl-ai-file-upload\\b|\\battached_file\\b",
    "w": 10,
    "first_seen": "2026-08-14",
    "last_confirmed": "2026-08-22"

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "zero-slop",
-  "version": "2.5.8",
+  "version": "2.6.1",
   "description": "An Agent Skill that scores AI-sounding prose 0-100 locally and rewrites it without losing a fact. Runs inside Claude Code, Codex, Cursor, Warp, Zed and other SKILL.md agents. Offline, zero dependencies, MIT.",
   "keywords": [
     "agent-skill",

package/references/copy-desk.md

@@ -69,7 +69,7 @@ known voice signals, and immutable facts when available. Then use this brief:
 > terse note only for unresolved ambiguities or unusual forms deliberately kept.
 
 Apply the corrected version to the deliverable, then send that exact artifact
-through the final read-aloud pass in `references/readalong.md`. Verify the
+through the read-aloud pass in `references/readalong.md`. Verify the
 artifact returned by the read-aloud editor:
 
 1. Rerun the heuristic surface scorer and scripted fidelity check.
@@ -77,11 +77,13 @@ artifact returned by the read-aloud editor:
    claims, qualifiers, intended voice, regional spelling, format, and non-prose
    structure. The script cannot detect every semantic or stylistic change.
 3. If any check or comparison requires a repair, apply it, send the repaired
-   text through the copy desk and final read-aloud pass again, and repeat all
+   text through the copy desk and read-aloud pass again, and repeat all
    final checks.
 
-Stop only when the same artifact clears the copy desk, final read-aloud pass,
-semantic and format review, scorer, and fidelity check. Limit this repair loop to
+After verification, send that exact text through the finalizer in
+`references/fresh-eyes.md`. Stop only when the same artifact clears the copy desk,
+read-aloud pass, semantic and format review, scorer, fidelity check, and receives a
+no-change fresh-eyes approval. Limit this repair loop to
 three rounds. If an issue still cannot be resolved without guessing, return the best
 source-preserving version that completed both editorial passes, flag the unresolved
 span and failed check plainly, and do not describe the fallback as fully verified.

package/references/evidence.md

@@ -47,6 +47,28 @@ not a deception.
 8. **Affect skew.** LLM text is joy-skewed and uniformly positive
    (Muñoz-Ortiz). Counter: widen affect.
 
+## Incumbent audit: what transferred and what did not
+
+Zero Slop v2.5.9 audited
+[`conorbronsdon/avoid-ai-writing`](https://github.com/conorbronsdon/avoid-ai-writing)
+at commit `40328bd292bc682d46010a6f9ac2cdbf4fb4ceca`. The ideas that survived
+transfer tests were zero-width and mixed-script normalization, exact protection
+for structured document spans, broader AI-tool tracker residue, three narrowly
+defined phrase families, and one conservative long-form word-variety signal.
+On the incumbent's pinned 875-human/779-machine
+paragraph corpus, its low-TTR signal fired on 1 human and 20 machine paragraphs
+(22.46x lift). Zero Slop keeps it weak and corroboration-dependent.
+
+Function-word entropy, punctuation-distribution uniformity, and cross-paragraph
+rhythm were also tested. None fired on Zero Slop's 38 consensus-labelled
+editorial passages; on the Beemo paired set they were rare and only directional
+proxies because Beemo labels provenance and editing history, not slop quality.
+They were not promoted. The incumbent's hand-shaped class probabilities were
+also rejected: its documentation correctly says they are not calibrated against
+a labelled corpus, and its own composite reports paragraph ROC-AUC 0.501 and
+document ROC-AUC 0.623. Zero Slop does not turn an uncalibrated writing score
+into an authorship probability.
+
 ## Why the scorer measures features, not detector verdicts
 
 Detectors are brittle: RAID (2405.07940) shows trivial perturbations fool

package/references/fresh-eyes.md

@@ -0,0 +1,62 @@
+# The fresh-eyes finalizer
+
+This is the last role in the editing workflow. It receives the exact text that
+already cleared the copy desk, read-aloud editor, and verifier. Its job is to read
+that text as a first-time reader and catch the small but consequential problems an
+editor can stop seeing after repeated passes.
+
+Use a new, role-isolated editor when the harness supports agents or subagents.
+Otherwise start a separate pass with no drafting or scoring mindset. Do not ask the
+rewriter to approve its own work.
+
+## What to check
+
+- **The whole arc.** The opening sets up the real point, sections arrive in a useful
+  order, and the ending resolves rather than repeats the piece.
+- **First-use clarity.** Names, pronouns, abbreviations, references, and transitions
+  make sense when encountered, without knowledge from the editing process.
+- **Reader effort.** A smart first-time reader can follow the argument once through.
+  Unpack only a genuine stumble; do not dilute expert language the audience needs.
+- **Voice continuity.** The same person seems to have written the beginning, middle,
+  and end. Restore source-backed warmth or texture lost to over-editing.
+- **Residual process language.** Remove internal labels, scoring talk, evaluation
+  jargon, or comments meant for the editor rather than the reader.
+- **Genre and format.** The text looks and sounds native to its destination. Preserve
+  all legitimate lists, tables, code, headings, citations, links, and layout.
+- **Last-mile polish.** Correct a safe leftover repetition, vague handoff, awkward
+  phrase, or mechanical inconsistency that survived the earlier passes.
+
+## Boundaries
+
+Preserve every fact, claim, qualifier, name, number, date, link, quotation, source,
+voice signal, regional spelling choice, and protected non-prose element. Do not add
+examples, experiences, certainty, novelty, emotion, or specificity. Do not make a
+substantive rewrite. If the intended correction is uncertain, leave the text alone
+and name the ambiguity.
+
+## Finalizer brief
+
+> You are the fresh-eyes finalizer. Read the complete verified text as a first-time
+> reader, from title to final line. Apply only safe last-mile polish for overall arc,
+> first-use clarity, reader effort, voice continuity, genre fit, residual process
+> language, repetition, and mechanical consistency. Preserve every fact, claim,
+> qualifier, name, number, date, link, quotation, source, voice signal, regional
+> spelling choice, and non-prose element. Do not add detail, certainty, emotion,
+> novelty, or generic polish. Return the complete text in its original format,
+> followed by exactly one status: `approve without changes`, `changed — rerun final
+> checks`, or `unresolved — needs the writer`.
+
+## Closed finalization loop
+
+Approval is valid only when the finalizer returns `approve without changes`. If it
+changes even one character, apply the complete revision and rerun, in order:
+
+1. the copy desk;
+2. the read-aloud editor;
+3. the verifier, including local and contextual checks; and
+4. this fresh-eyes finalizer.
+
+Repeat for at most three rounds. The same exact text must clear all four roles, with
+the fresh-eyes finalizer approving it unchanged. If the remaining issue cannot be
+fixed without guessing, return the best source-preserving text that completed every
+pass, identify the unresolved span, and do not describe it as fully verified.

package/references/overcorrection.md

@@ -56,6 +56,11 @@ experience — these alone are NOT evidence of AI:
 Require corroboration. A paragraph needs multiple independent tells, or a failed
 removal test, before it's slop.
 
+This governs lexical flags only. It does not apply to the performed-register
+family: register is a property of the piece, not of a paragraph. Four unmarked
+antithesis pairs across four paragraphs *is* the corroboration — each one is
+locally defensible, and the repetition is the whole finding.
+
 ## Signs of human writing — preserve on sight
 
 When a draft shows these, protect them through the rewrite; deleting them is

package/references/readalong.md

@@ -6,8 +6,8 @@ listener hears it: from the first line to the last, with each sentence setting u
 next. A stumble, cold transition, unclear antecedent, or change of voice can still
 survive a clean score and correct grammar.
 
-Run this pass on every deliverable after the copy desk. It is the last editorial pass
-before final verification and the Report step. Use a dedicated editor with fresh eyes
+Run this pass on every deliverable after the copy desk. It is the spoken-flow pass
+before verification and the separate fresh-eyes finalizer. Use a dedicated editor with fresh ears
 when the harness supports subagents; otherwise perform a separate, role-isolated pass.
 The editor must fix the actual deliverable and return the corrected artifact in the
 same format. An audit or list of suggestions is not a completed pass.
@@ -21,17 +21,33 @@ safe correction for:
   endings that make a reader stop or back up.
 - **Cold transitions.** Add or repair the hinge when a sentence, paragraph, or
   section arrives without a clear connection to what came before.
+- **Paragraph-order dependence.** If adjacent prose paragraphs can trade places
+  without changing the argument, rebuild the progression. Do not impose a story
+  arc on FAQs, reference entries, independent findings, or genuine lists.
 - **Performed candor.** Remove announcements of honesty such as "honestly" or "to be
   fair" when the sentence can simply make its point.
 - **Reflexive agreement.** Remove automatic praise or agreement that appears before
   the substance has been checked. Let the facts determine whether the draft agrees,
   qualifies, or disagrees.
+- **Recap-flattery.** In a reply, cut praise and a needless restatement of the
+  question before the answer. Keep setup that materially changes the answer.
+- **Wall-of-text reply.** Break an answer where the reader must change task,
+  decision, time, or subject. Do not split a coherent narrative paragraph merely
+  to make it look lighter.
 - **Communicative drift.** Stop when fluent sentences no longer advance a clear
   point or reader need. Cut the passage, rebuild it around its purpose, or flag the
   missing intent rather than inventing one.
 - **Rhetorical scale mismatch.** Reduce grand reveals, lessons, or contrasts when
   the underlying point is too small or unsupported for the framing. Preserve a
   contrast that corrects a real, supported misconception.
+- **Unsupported novelty.** Remove claims that nobody has noticed or named an idea
+  unless the source supplies a defensible comparison.
+- **Self-labeling significance.** Replace an unsupported declaration that a point
+  is important with the consequence that makes it important.
+- **Moral-adjective category error.** Do not call a system design, metric, or
+  technical choice brave, honest, ethical, or courageous when the sentence means
+  accurate, transparent, conservative, or reliable. Preserve a sourced moral
+  judgment about an actual agent or decision.
 - **Performed-writer register.** Flatten theatrical framing of ordinary work ("we
   hired an adversary"), epigram closers, staccato antithesis pairs ("Not perfect.
   Honest."), extended conceits (billing, courtroom, forensics, recipe), one-word
@@ -58,6 +74,8 @@ safe correction for:
 Do not merely flag these problems. Correct them directly wherever the intended
 meaning is certain.
 
+For consistent reporting, use these names: paragraph-order dependence, unsupported novelty, self-labeling significance, moral-adjective category error, recap-flattery, and wall-of-text reply.
+
 ## Boundaries
 
 - Preserve every fact, claim, qualifier, number, name, date, link, and source.
@@ -103,7 +121,8 @@ Verify the exact artifact returned by the read-aloud editor:
    this read-aloud pass again, and repeat every final check.
 
 Stop only when the same artifact has cleared the copy desk, final read-aloud pass,
-semantic and format review, scorer, and fidelity check. Limit this repair loop to
+semantic and format review, scorer, fidelity check, and the separate fresh-eyes
+finalizer in `fresh-eyes.md`. Limit this repair loop to
 three rounds. If an issue still cannot be resolved without guessing, return the best
 source-preserving version that completed both editorial passes, state the unresolved
 span and failed check plainly, and do not describe the fallback as fully verified.

package/references/tells.md

@@ -1,6 +1,6 @@
 # The Tell Taxonomy
 
-A hundred and five tells in six families, merged from WP:AICATCH (Wikipedia's editor
+A hundred and thirteen tells in six families, merged from WP:AICATCH (Wikipedia's editor
 catalog, built from thousands of caught instances), the de-slop/stop-slop
 detector line, petergyang/no-ai-slop, blader/humanizer, the academic
 lexicon studies (Kobak, Liang, Juzek & Ward), and community taxonomies of
@@ -26,6 +26,8 @@ as weak evidence unless it is generic in context or appears in a cluster. A
 lone dash, formal sentence, transition, or supported contrast remains a style
 choice. See `evidence.md` for the study, limitations, and adoption decision.
 
+Contextual review names six checks explicitly: paragraph-order dependence, unsupported novelty, self-labeling significance, moral-adjective category error, recap-flattery, and wall-of-text reply.
+
 ## 1. Lexical
 
 | Tell | Fix |
@@ -76,6 +78,8 @@ choice. See `evidence.md` for the study, limitations, and adoption decision.
 | Mechanical sentence openings: several consecutive sentences begin with the same subject or frame without building deliberate rhythm | Merge or vary the sentences; preserve purposeful anaphora |
 | Jargon compression: invented compound terms in place of explanation — "threshold cliff", "length-blind floor", "pinned high forever" | Unpack into the plain explanation once, then a short name only if the document truly reuses it; the fix is unpacking, not a synonym |
 | Stat pile-up: several datasets or tests crammed into one paragraph with no connective explanation | One test per paragraph, opening with what the test checks in plain words ("The first test checks that the score falls as humans get more involved"), numbers after the plain-language setup |
+| Paragraph-order dependence: prose paragraphs can be shuffled without changing the argument | Rebuild a progression in which each paragraph earns the next; exempt FAQs, reference entries, independent findings, and genuine lists |
+| Wall-of-text reply: an answer hides distinct steps or decisions in one unbroken block | Add only the paragraph breaks or list structure the reader needs; length alone is not the signal |
 
 ## 3. Rhetorical
 
@@ -86,6 +90,9 @@ choice. See `evidence.md` for the study, limitations, and adoption decision.
 | Manufactured stakes: "in today's fast-paced world", "now more than ever" | Start where the reader needs to start |
 | Performed candor: "let's be honest", "here's the thing", "truth be told" | State the point |
 | Rhetorical-question openers: "Ever wondered…?", "What if I told you…?" | The answer, as a statement |
+| Unsupported novelty: "the problem nobody is naming" without a comparison or source | Make the narrower supported claim, or ask for the missing basis |
+| Self-labeling significance: "this matters", "this is important", or "the key insight" substitutes a label for a consequence | State the concrete consequence and let it carry the weight |
+| Moral-adjective category error: a technical choice or metric is called brave, honest, ethical, or courageous without a moral agent or decision | Name the engineering property or trade-off; preserve a real moral judgment when the source supports one |
 | Throat-clearing: "The uncomfortable truth is", "Let me be clear" | Cut; the claim stands alone |
 | Emphasis crutches: "Make no mistake", "Let that sink in", "Read that again" | Show the weight with the fact itself |
 | Meta-commentary: "In this post we'll explore", "Let me walk you through" | Just do it |
@@ -113,6 +120,8 @@ choice. See `evidence.md` for the study, limitations, and adoption decision.
 | Hyperbole universals: "nothing on earth", "on the planet", "in history", "known to man" | State the actual scope; the honest comparison is smaller and stronger |
 | Cute meta-taglines and campaign framing: "a meter you can argue with", "the fight against X" as a slogan | Describe the thing; "posts about writing quality" beats a campaign poster. "The fight against" is real usage in history and civic prose — flag the marketing register, not the phrase |
 | Staccato antithesis: two short balanced sentences, the second landing the twist — "Not perfect. Honest.", "Slop isn't a vibe. It's measurable.", "The draft was cheap. The signal it sent was not." | One plain sentence with the claim; at most one antithesis per piece |
+| Unmarked antithesis: the same figure with no negation marker at all, so the whole "not X, it's Y" family walks past it. Four shapes — bare subject swap ("Llama is open-weights. Dolma releases the data."); isocolon, one verb frame with both arguments swapped ("Open weights let you adapt a model. An open stack lets you adapt the machinery that created it."); the stock closer ("Ai2 argues for a principle. This is what that principle looks like."); unmarked reversal ("No frontier lab had to decide. Thai researchers made that call themselves.") | State the claim once, plainly. The meter now catches the last three (`isocolon-ditransitive`, `this-is-what-looks-like`, `no-x-had-to`); bare subject swap stays a judgment call. **Count them** — one is a device, three in a short piece is the register |
+| Significance scaffolding: a sentence announcing that a point matters instead of delivering it — "Here's the detail that matters:", "This is what that principle looks like when it works." | Delete the announcement and keep the point. Budget: zero |
 | Extended conceit: a process or abstraction dressed as physical drama — billing ("the bill lands on reputation", "gets billed to a reader"), courtroom ("never allowed to convict"), forensics ("rhythm leaves prints"), machinery ("opens the hood"), recipe ("has four ingredients") | At most one metaphor per piece, then plain language; name the actual mechanism |
 | Vibe-slang: "just a vibe", "vibe check", "argue with vibes", "has receipts" | The plain word: impression, judgment, evidence |
 | One-word drama beat: "Fine." dropped between claims as a rhythm device | Cut it or fold it into the sentence it interrupts |
@@ -125,13 +134,28 @@ same costume seen at detection time instead of rewrite time. The scorer
 catches the mechanical subset (`hired-adversary`, `turns-out-payoff`,
 `has-receipts`, `hyperbole-universal`, `argue-with-artifact`,
 `vibe-register`, `where-x-lives`, `billed-conceit`, `on-the-tin`,
-`minding-own-business`, `economics-brutal`, `opens-the-hood`, and the
-rider-gated "fight against"); epigram cadence, staccato antithesis, most
-conceits, jargon compression, and tagline register need the judgment pass,
-because their literal forms are legitimate in news, history, crime, and
-civic writing. The human-flagged spans that motivated the family live in
+`minding-own-business`, `economics-brutal`, `opens-the-hood`, the
+rider-gated "fight against", and — since v2.5.10 — three of the four unmarked
+antithesis shapes: `isocolon-ditransitive`, `this-is-what-looks-like`, and
+`no-x-had-to`. Epigram cadence, marked staccato antithesis, bare subject swap,
+most conceits, jargon compression, and tagline register still need the
+performed-register pass, because their literal forms are legitimate in news,
+history, crime, and civic writing.
+
+`isocolon-ditransitive` is worth reading closely, because it marks the boundary
+between what a rule can safely reach and what it cannot. It fires only when the
+**same verb** is repeated in a give-you frame across a sentence break. That
+identity requirement is the whole safety property: rhetorical anaphora repeats
+its frame with a *different* verb every time — "we can not dedicate, we can not
+consecrate, we can not hallow" — so the rule cannot touch it. Relaxing the
+backreference from the verb to the frame was tested and fires on the Gettysburg
+Address, the Federalist, and an ESL engineer's email. Do not relax it.
+
+The human-flagged spans that motivated the family live in
 `data/corpus/performed-register/` — the mechanical half is regression-tested,
-the judgment half is the read-aloud pass's fixture list.
+the judgment half is the performed-register pass's fixture list. Files move
+between the two halves in both directions: `verdict-arithmetic.txt` graduated
+from judgment to mechanical in v2.5.10 when a safe rule finally reached it.
 
 ## 4. Punctuation & formatting
 
@@ -153,6 +177,7 @@ the judgment half is the read-aloud pass's fixture list.
 |---|---|
 | Assistant voice: "Great question!", "I hope this helps", "I'd be happy to" | Delete |
 | Reflexive agreement or praise: approving the premise before checking it, flattering the writer, or refusing to take a supported position | Answer the substance first; agree, qualify, or disagree according to the facts |
+| Recap-flattery: a reply opens by praising and paraphrasing the question before answering it | Start with the answer; keep only context the reader actually needs |
 | Chatbot residue: "Would you like me to…", "Let me know if you'd like…", "my training data" | Delete — it is proof of paste, not style |
 | Knowledge-cutoff residue: "as of my last update", "not widely documented" | Delete; verify the claim |
 | Passive or subjectless wording that hides an actor who matters | Name the actor and use the direct verb; keep passive voice when the actor is unknown, irrelevant, or native to the genre |