| 100.00% | Adverbs in dialogue tags | Target: ≤10% dialogue tags with adverbs | |
| 92.76% | AI-ism adverb frequency | Target: <2% AI-ism adverbs (58 tracked) | | wordCount | 1381 | | totalAiIsmAdverbs | 2 | | found | | | highlights | | |
| 100.00% | AI-ism character names | Target: 0 AI-default names (17 tracked, −20% each) | | codexExemptions | (empty) | | found | (empty) | |
| 100.00% | AI-ism location names | Target: 0 AI-default location names (33 tracked, −20% each) | | codexExemptions | (empty) | | found | (empty) | |
| 34.83% | AI-ism word frequency | Target: <2% AI-ism words (290 tracked) | | wordCount | 1381 | | totalAiIsms | 18 | | found | | | highlights | | 0 | "weight" | | 1 | "measured" | | 2 | "jaw clenched" | | 3 | "flicker" | | 4 | "echoing" | | 5 | "shimmered" | | 6 | "flickered" | | 7 | "structure" | | 8 | "clandestine" | | 9 | "electric" | | 10 | "almost alive" | | 11 | "etched" | | 12 | "silence" | | 13 | "familiar" | | 14 | "echoed" |
| |
| 66.67% | Cliché density | Target: ≤1 cliche(s) per 800-word window | | totalCliches | 3 | | maxInWindow | 2 | | found | | 0 | | label | "eyes widened/narrowed" | | count | 2 |
| | 1 | | label | "jaw/fists clenched" | | count | 1 |
|
| | highlights | | 0 | "eyes narrowed" | | 1 | "eyes widened" | | 2 | "jaw clenched" |
| |
| 100.00% | Emotion telling (show vs. tell) | Target: ≤3% sentences with emotion telling | | emotionTells | 1 | | narrationSentences | 115 | | matches | | |
| 93.17% | Filter word density | Target: ≤3% sentences with filter/hedge words | | filterCount | 2 | | hedgeCount | 2 | | narrationSentences | 115 | | filterMatches | | | hedgeMatches | | |
| 100.00% | Gibberish response detection | Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words) | | analyzedSentences | 115 | | gibberishSentences | 0 | | adjustedGibberishSentences | 0 | | longSentenceCount | 0 | | runOnParagraphCount | 0 | | giantParagraphCount | 0 | | wordSaladCount | 0 | | repetitionLoopCount | 0 | | controlTokenCount | 0 | | repeatedSegmentCount | 0 | | maxSentenceWordsSeen | 39 | | ratio | 0 | | matches | (empty) | |
| 100.00% | Markdown formatting overuse | Target: ≤5% words in markdown formatting | | markdownSpans | 0 | | markdownWords | 0 | | totalWords | 1381 | | ratio | 0 | | matches | (empty) | |
| 100.00% | Missing dialogue indicators (quotation marks) | Target: ≤10% speech attributions without quotation marks | | totalAttributions | 0 | | unquotedAttributions | 0 | | matches | (empty) | |
| 100.00% | Name drop frequency | Target: ≤1.0 per-name mentions per 100 words | | totalMentions | 28 | | wordCount | 1381 | | uniqueNames | 16 | | maxNameDensity | 0.58 | | worstName | "Harlow" | | maxWindowNameDensity | 1.5 | | worstWindowName | "Harlow" | | discoveredNames | | Soho | 1 | | Harlow | 8 | | Quinn | 2 | | Metropolitan | 1 | | Police | 1 | | Morris | 5 | | Veil | 1 | | Market | 1 | | Tube | 1 | | Camden | 1 | | Raven | 1 | | Nest | 1 | | Saint | 1 | | Christopher | 1 | | Herrera | 1 | | London | 1 |
| | persons | | 0 | "Harlow" | | 1 | "Quinn" | | 2 | "Police" | | 3 | "Morris" | | 4 | "Market" | | 5 | "Raven" | | 6 | "Saint" | | 7 | "Christopher" | | 8 | "Herrera" |
| | places | | | globalScore | 1 | | windowScore | 1 | |
| 100.00% | Narrator intent-glossing | Target: ≤2% narration sentences with intent-glossing patterns | | analyzedSentences | 81 | | glossingSentenceCount | 0 | | matches | (empty) | |
| 55.18% | "Not X but Y" pattern overuse | Target: ≤1 "not X but Y" per 1000 words | | totalMatches | 2 | | per1kWords | 1.448 | | wordCount | 1381 | | matches | | 0 | "not with panic, but with a grim acknowledgment" | | 1 | "not on her pistol, but on the bone token" |
| |
| 100.00% | Overuse of "that" (subordinate clause padding) | Target: ≤2% sentences with "that" clauses | | thatCount | 1 | | totalSentences | 115 | | matches | | |
| 24.34% | Paragraph length variance | Target: CV ≥0.5 for paragraph word counts | | totalParagraphs | 11 | | mean | 125.55 | | std | 29.53 | | cv | 0.235 | | sampleLengths | | 0 | 171 | | 1 | 126 | | 2 | 130 | | 3 | 131 | | 4 | 153 | | 5 | 166 | | 6 | 131 | | 7 | 101 | | 8 | 68 | | 9 | 98 | | 10 | 106 |
| |
| 90.01% | Passive voice overuse | Target: ≤2% passive sentences | | passiveCount | 5 | | totalSentences | 115 | | matches | | 0 | "was plastered" | | 1 | "been cleaned" | | 2 | "were joined" | | 3 | "were struck" | | 4 | "was carved" |
| |
| 100.00% | Past progressive (was/were + -ing) overuse | Target: ≤2% past progressive verbs | | pastProgressiveCount | 0 | | totalVerbs | 235 | | matches | (empty) | |
| 100.00% | Em-dash & semicolon overuse | Target: ≤2% sentences with em-dashes/semicolons | | emDashCount | 0 | | semicolonCount | 0 | | flaggedSentences | 0 | | totalSentences | 115 | | ratio | 0 | | matches | (empty) | |
| 100.00% | Purple prose (modifier overload) | Target: <4% adverbs, <2% -ly adverbs, no adj stacking | | wordCount | 1391 | | adjectiveStacks | 0 | | stackExamples | (empty) | | adverbCount | 32 | | adverbRatio | 0.023005032350826744 | | lyAdverbCount | 10 | | lyAdverbRatio | 0.007189072609633357 | |
| 100.00% | Repeated phrase echo | Target: ≤20% sentences with echoes (window: 2) | | totalSentences | 115 | | echoCount | 0 | | echoWords | (empty) | |
| 100.00% | Sentence length variance | Target: CV ≥0.4 for sentence word counts | | totalSentences | 115 | | mean | 12.01 | | std | 8.09 | | cv | 0.674 | | sampleLengths | | 0 | 17 | | 1 | 26 | | 2 | 11 | | 3 | 29 | | 4 | 6 | | 5 | 15 | | 6 | 7 | | 7 | 22 | | 8 | 2 | | 9 | 18 | | 10 | 18 | | 11 | 21 | | 12 | 6 | | 13 | 39 | | 14 | 16 | | 15 | 22 | | 16 | 22 | | 17 | 25 | | 18 | 4 | | 19 | 11 | | 20 | 15 | | 21 | 19 | | 22 | 23 | | 23 | 18 | | 24 | 1 | | 25 | 2 | | 26 | 12 | | 27 | 5 | | 28 | 17 | | 29 | 9 | | 30 | 3 | | 31 | 14 | | 32 | 4 | | 33 | 11 | | 34 | 11 | | 35 | 17 | | 36 | 26 | | 37 | 7 | | 38 | 7 | | 39 | 6 | | 40 | 10 | | 41 | 19 | | 42 | 5 | | 43 | 8 | | 44 | 3 | | 45 | 3 | | 46 | 6 | | 47 | 16 | | 48 | 5 | | 49 | 4 |
| |
| 39.42% | Sentence opener variety | Target: ≥60% unique sentence openers | | consecutiveRepeats | 23 | | diversityRatio | 0.3565217391304348 | | totalSentences | 115 | | uniqueOpeners | 41 | |
| 0.00% | Adverb-first sentence starts | Target: ≥3% sentences starting with an adverb | | adverbCount | 0 | | totalSentences | 108 | | matches | (empty) | | ratio | 0 | |
| 68.15% | Pronoun-first sentence starts | Target: ≤30% sentences starting with a pronoun | | pronounCount | 41 | | totalSentences | 108 | | matches | | 0 | "It built a rhythm in" | | 1 | "She kept her breathing low," | | 2 | "Her salt-and-pepper hair was plastered" | | 3 | "Her sharp jaw clenched against" | | 4 | "She didn't know his name" | | 5 | "She knew only that he" | | 6 | "She kept her hand loose" | | 7 | "She rounded a corner littered" | | 8 | "He took a hard left" | | 9 | "He dropped onto the first" | | 10 | "She hit the stairs after" | | 11 | "She reached the bottom landing." | | 12 | "It moved with the moon," | | 13 | "It sold enchanted goods, banned" | | 14 | "She had always filed it" | | 15 | "He pressed his palm against" | | 16 | "They were moving people." | | 17 | "His last call had come" | | 18 | "She leaned in, her brown" | | 19 | "She could see the faint" |
| | ratio | 0.38 | |
| 52.59% | Subject-first sentence starts | Target: ≤72% sentences starting with a subject | | subjectCount | 88 | | totalSentences | 108 | | matches | | 0 | "Rain fell in sheets, turning" | | 1 | "Detective Harlow Quinn moved through" | | 2 | "It built a rhythm in" | | 3 | "She kept her breathing low," | | 4 | "Her salt-and-pepper hair was plastered" | | 5 | "Her sharp jaw clenched against" | | 6 | "The man in the dark" | | 7 | "She didn't know his name" | | 8 | "She knew only that he" | | 9 | "She kept her hand loose" | | 10 | "She rounded a corner littered" | | 11 | "He took a hard left" | | 12 | "The mouth of the stairwell" | | 13 | "The suspect didn't slow." | | 14 | "He dropped onto the first" | | 15 | "Harlow caught him, her shoulder" | | 16 | "She hit the stairs after" | | 17 | "The air grew thick, heavy" | | 18 | "The metallic tang of blood" | | 19 | "She reached the bottom landing." |
| | ratio | 0.815 | |
| 92.59% | Subordinate conjunction sentence starts | Target: ≥2% sentences starting with a subordinating conjunction | | subConjCount | 2 | | totalSentences | 108 | | matches | | 0 | "Now, watching him adjust a" | | 1 | "Now, she just kept moving." |
| | ratio | 0.019 | |
| 20.09% | Technical jargon density | Target: ≤6% sentences with technical-jargon patterns | | analyzedSentences | 64 | | technicalSentenceCount | 11 | | matches | | 0 | "She knew only that he was moving toward the coordinates that had bled from a recovered ledger, moving toward the clique she had spent twelve months triangulatin…" | | 1 | "He took a hard left into a narrow passage that smelled of damp timber and spilled gin, and Harlow followed without hesitation." | | 2 | "Harlow caught him, her shoulder checking a stack of rotting pallets, and closed the gap." | | 3 | "She hit the stairs after him, descending in two strides to three, her breath pluming in the cooling air." | | 4 | "The suspect was already thirty yards ahead, vanishing through a wrought-iron gate that shouldn't have been there." | | 5 | "It sold enchanted goods, banned alchemical substances, and information that could buy a life or end one." | | 6 | "She had always filed it under urban legend, the kind of paranoid fiction that took root after too many sleepless nights and a dead partner's ghost." | | 7 | "His last call had come in over static, his voice cutting out mid-sentence, leaving behind a room that was exactly as it had been, and yet entirely different." | | 8 | "She could see the faint effervescence of liquids that moved against gravity, curling up the sides of sealed bottles." | | 9 | "Cross it, and she surrendered eighteen years of procedure, of chain of command, of everything that kept a detective from becoming just another ghost in a closed…" | | 10 | "It was carved with the same impossible geometry as the symbol etched into the wall of Morris's final scene, the same angles that had defied every forensic sketc…" |
| |
| 100.00% | Useless dialogue additions | Target: ≤5% dialogue tags with trailing filler fragments | | totalTags | 0 | | uselessAdditionCount | 0 | | matches | (empty) | |
| 100.00% | Dialogue tag variety (said vs. fancy) | Target: ≤10% fancy dialogue tags | |