| 33.33% | Adverbs in dialogue tags | Target: ≤10% dialogue tags with adverbs | | totalTags | 18 | | adverbTagCount | 3 | | adverbTags | | 0 | "Tomás stepped back [back]" | | 1 | "Tomás said softly [softly]" | | 2 | "Tomás replied coldly [coldly]" |
| | dialogueSentences | 34 | | tagDensity | 0.529 | | leniency | 1 | | rawRatio | 0.167 | | effectiveRatio | 0.167 | |
| 82.79% | AI-ism adverb frequency | Target: <2% AI-ism adverbs (58 tracked) | | wordCount | 1162 | | totalAiIsmAdverbs | 4 | | found | | | highlights | | 0 | "softly" | | 1 | "really" | | 2 | "coldly" |
| |
| 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) | |
| 48.36% | AI-ism word frequency | Target: <2% AI-ism words (290 tracked) | | wordCount | 1162 | | totalAiIsms | 12 | | found | | | highlights | | 0 | "rhythmic" | | 1 | "gloom" | | 2 | "pulse" | | 3 | "facade" | | 4 | "flicked" | | 5 | "standard" | | 6 | "velvet" | | 7 | "flickered" | | 8 | "scanned" | | 9 | "chaotic" | | 10 | "familiar" |
| |
| 100.00% | Cliché density | Target: ≤1 cliche(s) per 800-word window | | totalCliches | 0 | | maxInWindow | 0 | | found | (empty) | | highlights | (empty) | |
| 100.00% | Emotion telling (show vs. tell) | Target: ≤3% sentences with emotion telling | | emotionTells | 0 | | narrationSentences | 73 | | matches | (empty) | |
| 100.00% | Filter word density | Target: ≤3% sentences with filter/hedge words | | filterCount | 1 | | hedgeCount | 0 | | narrationSentences | 73 | | filterMatches | | | hedgeMatches | (empty) | |
| 100.00% | Gibberish response detection | Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words) | | analyzedSentences | 89 | | gibberishSentences | 0 | | adjustedGibberishSentences | 0 | | longSentenceCount | 0 | | runOnParagraphCount | 0 | | giantParagraphCount | 0 | | wordSaladCount | 0 | | repetitionLoopCount | 0 | | controlTokenCount | 0 | | repeatedSegmentCount | 0 | | maxSentenceWordsSeen | 31 | | ratio | 0 | | matches | (empty) | |
| 100.00% | Markdown formatting overuse | Target: ≤5% words in markdown formatting | | markdownSpans | 0 | | markdownWords | 0 | | totalWords | 1162 | | ratio | 0 | | matches | (empty) | |
| 100.00% | Missing dialogue indicators (quotation marks) | Target: ≤10% speech attributions without quotation marks | | totalAttributions | 11 | | unquotedAttributions | 0 | | matches | (empty) | |
| 50.00% | Name drop frequency | Target: ≤1.0 per-name mentions per 100 words | | totalMentions | 47 | | wordCount | 935 | | uniqueNames | 18 | | maxNameDensity | 1.82 | | worstName | "Harlow" | | maxWindowNameDensity | 3.5 | | worstWindowName | "Harlow" | | discoveredNames | | Harlow | 17 | | Soho | 2 | | Dean | 1 | | Street | 1 | | Tube | 1 | | Northern | 1 | | Transport | 1 | | London | 3 | | Glock | 1 | | Morris | 4 | | Underground | 1 | | Veil | 1 | | Market | 1 | | Scotland | 1 | | Yard | 1 | | Herrera | 1 | | Spanish | 1 | | Tomás | 8 |
| | persons | | 0 | "Harlow" | | 1 | "Morris" | | 2 | "Herrera" | | 3 | "Tomás" |
| | places | | 0 | "Soho" | | 1 | "Dean" | | 2 | "Street" | | 3 | "London" | | 4 | "Scotland" |
| | globalScore | 0.591 | | windowScore | 0.5 | |
| 25.00% | Narrator intent-glossing | Target: ≤2% narration sentences with intent-glossing patterns | | analyzedSentences | 60 | | glossingSentenceCount | 3 | | matches | | 0 | "smelled like warm blood and crushed bay le" | | 1 | "felt like a physical blow" | | 2 | "as if fighting a physical spasm beneath his skin" |
| |
| 100.00% | "Not X but Y" pattern overuse | Target: ≤1 "not X but Y" per 1000 words | | totalMatches | 0 | | per1kWords | 0 | | wordCount | 1162 | | matches | (empty) | |
| 100.00% | Overuse of "that" (subordinate clause padding) | Target: ≤2% sentences with "that" clauses | | thatCount | 0 | | totalSentences | 89 | | matches | (empty) | |
| 96.20% | Paragraph length variance | Target: CV ≥0.5 for paragraph word counts | | totalParagraphs | 40 | | mean | 29.05 | | std | 14.14 | | cv | 0.487 | | sampleLengths | | 0 | 23 | | 1 | 38 | | 2 | 5 | | 3 | 33 | | 4 | 43 | | 5 | 38 | | 6 | 49 | | 7 | 24 | | 8 | 52 | | 9 | 17 | | 10 | 51 | | 11 | 25 | | 12 | 72 | | 13 | 24 | | 14 | 29 | | 15 | 35 | | 16 | 18 | | 17 | 43 | | 18 | 20 | | 19 | 41 | | 20 | 2 | | 21 | 28 | | 22 | 30 | | 23 | 38 | | 24 | 12 | | 25 | 30 | | 26 | 19 | | 27 | 13 | | 28 | 23 | | 29 | 12 | | 30 | 46 | | 31 | 22 | | 32 | 7 | | 33 | 32 | | 34 | 31 | | 35 | 41 | | 36 | 19 | | 37 | 21 | | 38 | 32 | | 39 | 24 |
| |
| 100.00% | Passive voice overuse | Target: ≤2% passive sentences | | passiveCount | 0 | | totalSentences | 73 | | matches | (empty) | |
| 100.00% | Past progressive (was/were + -ing) overuse | Target: ≤2% past progressive verbs | | pastProgressiveCount | 1 | | totalVerbs | 156 | | matches | | |
| 100.00% | Em-dash & semicolon overuse | Target: ≤2% sentences with em-dashes/semicolons | | emDashCount | 0 | | semicolonCount | 0 | | flaggedSentences | 0 | | totalSentences | 89 | | ratio | 0 | | matches | (empty) | |
| 100.00% | Purple prose (modifier overload) | Target: <4% adverbs, <2% -ly adverbs, no adj stacking | | wordCount | 938 | | adjectiveStacks | 0 | | stackExamples | (empty) | | adverbCount | 20 | | adverbRatio | 0.021321961620469083 | | lyAdverbCount | 13 | | lyAdverbRatio | 0.013859275053304905 | |
| 100.00% | Repeated phrase echo | Target: ≤20% sentences with echoes (window: 2) | | totalSentences | 89 | | echoCount | 0 | | echoWords | (empty) | |
| 100.00% | Sentence length variance | Target: CV ≥0.4 for sentence word counts | | totalSentences | 89 | | mean | 13.06 | | std | 7 | | cv | 0.536 | | sampleLengths | | 0 | 23 | | 1 | 13 | | 2 | 25 | | 3 | 5 | | 4 | 8 | | 5 | 5 | | 6 | 20 | | 7 | 15 | | 8 | 22 | | 9 | 6 | | 10 | 7 | | 11 | 10 | | 12 | 7 | | 13 | 14 | | 14 | 8 | | 15 | 19 | | 16 | 3 | | 17 | 19 | | 18 | 10 | | 19 | 2 | | 20 | 3 | | 21 | 9 | | 22 | 9 | | 23 | 31 | | 24 | 12 | | 25 | 17 | | 26 | 14 | | 27 | 25 | | 28 | 12 | | 29 | 15 | | 30 | 10 | | 31 | 21 | | 32 | 6 | | 33 | 22 | | 34 | 23 | | 35 | 3 | | 36 | 21 | | 37 | 21 | | 38 | 8 | | 39 | 9 | | 40 | 15 | | 41 | 11 | | 42 | 7 | | 43 | 11 | | 44 | 18 | | 45 | 25 | | 46 | 20 | | 47 | 3 | | 48 | 10 | | 49 | 21 |
| |
| 67.79% | Sentence opener variety | Target: ≥60% unique sentence openers | | consecutiveRepeats | 8 | | diversityRatio | 0.4606741573033708 | | totalSentences | 89 | | uniqueOpeners | 41 | |
| 0.00% | Adverb-first sentence starts | Target: ≥3% sentences starting with an adverb | | adverbCount | 0 | | totalSentences | 69 | | matches | (empty) | | ratio | 0 | |
| 100.00% | Pronoun-first sentence starts | Target: ≤30% sentences starting with a pronoun | | pronounCount | 18 | | totalSentences | 69 | | matches | | 0 | "She recovered instantly, her boots" | | 1 | "Her voice bounced off the" | | 2 | "He cleared a stack of" | | 3 | "He was leading her somewhere" | | 4 | "He lunged toward a disused" | | 5 | "It gave way with a" | | 6 | "She knew the blueprints for" | | 7 | "It smelled like warm blood" | | 8 | "Her thumb flicked the safety" | | 9 | "She took a deep breath," | | 10 | "She reached the bottom of" | | 11 | "She’d heard the whispers in" | | 12 | "She didn't lower her weapon," | | 13 | "She scanned the chaotic crowd," | | 14 | "His hand slid into his" | | 15 | "He carried himself with military" | | 16 | "she whispered, her voice choking" | | 17 | "His eyes were entirely black," |
| | ratio | 0.261 | |
| 17.97% | Subject-first sentence starts | Target: ≤72% sentences starting with a subject | | subjectCount | 61 | | totalSentences | 69 | | matches | | 0 | "The heavy steel fire exit" | | 1 | "She recovered instantly, her boots" | | 2 | "Her voice bounced off the" | | 3 | "The suspect didn't even flinch." | | 4 | "He cleared a stack of" | | 5 | "Harlow rounded the corner, her" | | 6 | "Soho at night was a" | | 7 | "He was leading her somewhere" | | 8 | "He lunged toward a disused" | | 9 | "Harlow closed the gap, her" | | 10 | "The suspect shoved a heavy" | | 11 | "It gave way with a" | | 12 | "Harlow skidded to a halt" | | 13 | "Camden’s disused networks." | | 14 | "She knew the blueprints for" | | 15 | "A sharp, coppery stench drifted" | | 16 | "It smelled like warm blood" | | 17 | "Her thumb flicked the safety" | | 18 | "Backup didn't save you from" | | 19 | "She took a deep breath," |
| | ratio | 0.884 | |
| 72.46% | Subordinate conjunction sentence starts | Target: ≥2% sentences starting with a subordinating conjunction | | subConjCount | 1 | | totalSentences | 69 | | matches | | 0 | "Before Harlow could react, a" |
| | ratio | 0.014 | |
| 100.00% | Technical jargon density | Target: ≤6% sentences with technical-jargon patterns | | analyzedSentences | 36 | | technicalSentenceCount | 2 | | matches | | 0 | "People in long coats, figures shrouded in heavy velvet, and things that walked like men but moved with a terrifying, fluid stillness." | | 1 | "She scanned the chaotic crowd, her eyes locking onto a familiar dark coat weaving aggressively through the throng near a stall selling polished bone daggers." |
| |
| 13.89% | Useless dialogue additions | Target: ≤5% dialogue tags with trailing filler fragments | | totalTags | 18 | | uselessAdditionCount | 4 | | matches | | 0 | "Harlow said, her voice hard as granite" | | 1 | "Tomás snapped, his calm facade cracking to reveal a fierce, desperate light" | | 2 | "Harlow warned, her grip tightening on her sidearm inside her coat" | | 3 | "she whispered, her voice choking off" |
| |
| 0.00% | Dialogue tag variety (said vs. fancy) | Target: ≤10% fancy dialogue tags | | totalTags | 13 | | fancyCount | 7 | | fancyTags | | 0 | "Harlow yelled (yell)" | | 1 | "Harlow snapped (snap)" | | 2 | "Tomás snapped (snap)" | | 3 | "Harlow warned (warn)" | | 4 | "she whispered (whisper)" | | 5 | "Harlow yelled (yell)" | | 6 | "Morris grunted (grunt)" |
| | dialogueSentences | 34 | | tagDensity | 0.382 | | leniency | 0.765 | | rawRatio | 0.538 | | effectiveRatio | 0.412 | |