| 100.00% | Adverbs in dialogue tags | Target: ≤10% dialogue tags with adverbs | | totalTags | 6 | | adverbTagCount | 0 | | adverbTags | (empty) | | dialogueSentences | 11 | | tagDensity | 0.545 | | leniency | 1 | | rawRatio | 0 | | effectiveRatio | 0 | |
| 100.00% | AI-ism adverb frequency | Target: <2% AI-ism adverbs (58 tracked) | | wordCount | 1039 | | totalAiIsmAdverbs | 0 | | found | (empty) | | highlights | (empty) | |
| 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) | |
| 56.69% | AI-ism word frequency | Target: <2% AI-ism words (290 tracked) | | wordCount | 1039 | | totalAiIsms | 9 | | found | | | highlights | | 0 | "glistening" | | 1 | "flickered" | | 2 | "glinting" | | 3 | "loomed" | | 4 | "chill" | | 5 | "echoing" | | 6 | "could feel" | | 7 | "weight" |
| |
| 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 | 54 | | matches | (empty) | |
| 37.04% | Filter word density | Target: ≤3% sentences with filter/hedge words | | filterCount | 2 | | hedgeCount | 2 | | narrationSentences | 54 | | filterMatches | | | hedgeMatches | | |
| 100.00% | Gibberish response detection | Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words) | | analyzedSentences | 59 | | gibberishSentences | 0 | | adjustedGibberishSentences | 0 | | longSentenceCount | 0 | | runOnParagraphCount | 0 | | giantParagraphCount | 0 | | wordSaladCount | 0 | | repetitionLoopCount | 0 | | controlTokenCount | 0 | | repeatedSegmentCount | 0 | | maxSentenceWordsSeen | 58 | | ratio | 0 | | matches | (empty) | |
| 100.00% | Markdown formatting overuse | Target: ≤5% words in markdown formatting | | markdownSpans | 0 | | markdownWords | 0 | | totalWords | 1039 | | ratio | 0 | | matches | (empty) | |
| 100.00% | Missing dialogue indicators (quotation marks) | Target: ≤10% speech attributions without quotation marks | | totalAttributions | 4 | | unquotedAttributions | 0 | | matches | (empty) | |
| 100.00% | Name drop frequency | Target: ≤1.0 per-name mentions per 100 words | | totalMentions | 27 | | wordCount | 965 | | uniqueNames | 15 | | maxNameDensity | 0.83 | | worstName | "Harlow" | | maxWindowNameDensity | 2 | | worstWindowName | "Harlow" | | discoveredNames | | Harlow | 8 | | Quinn | 2 | | Soho | 1 | | Raven | 1 | | Nest | 1 | | Tomás | 3 | | Herrera | 2 | | Saint | 1 | | Christopher | 1 | | Morris | 2 | | Camden | 1 | | London | 1 | | Tube | 1 | | Veil | 1 | | Market | 1 |
| | persons | | 0 | "Harlow" | | 1 | "Quinn" | | 2 | "Raven" | | 3 | "Nest" | | 4 | "Tomás" | | 5 | "Herrera" | | 6 | "Saint" | | 7 | "Christopher" | | 8 | "Morris" | | 9 | "Camden" |
| | places | | | globalScore | 1 | | windowScore | 1 | |
| 100.00% | Narrator intent-glossing | Target: ≤2% narration sentences with intent-glossing patterns | | analyzedSentences | 43 | | glossingSentenceCount | 0 | | matches | (empty) | |
| 7.51% | "Not X but Y" pattern overuse | Target: ≤1 "not X but Y" per 1000 words | | totalMatches | 2 | | per1kWords | 1.925 | | wordCount | 1039 | | matches | | 0 | "not from the torches, but from something older, something" | | 1 | "not to an answer, but to a door" |
| |
| 100.00% | Overuse of "that" (subordinate clause padding) | Target: ≤2% sentences with "that" clauses | | thatCount | 1 | | totalSentences | 59 | | matches | | |
| 100.00% | Paragraph length variance | Target: CV ≥0.5 for paragraph word counts | | totalParagraphs | 24 | | mean | 43.29 | | std | 32.16 | | cv | 0.743 | | sampleLengths | | 0 | 83 | | 1 | 78 | | 2 | 22 | | 3 | 6 | | 4 | 30 | | 5 | 84 | | 6 | 14 | | 7 | 102 | | 8 | 54 | | 9 | 82 | | 10 | 91 | | 11 | 2 | | 12 | 25 | | 13 | 8 | | 14 | 32 | | 15 | 23 | | 16 | 55 | | 17 | 4 | | 18 | 29 | | 19 | 92 | | 20 | 39 | | 21 | 16 | | 22 | 10 | | 23 | 58 |
| |
| 100.00% | Passive voice overuse | Target: ≤2% passive sentences | | passiveCount | 0 | | totalSentences | 54 | | matches | (empty) | |
| 100.00% | Past progressive (was/were + -ing) overuse | Target: ≤2% past progressive verbs | | pastProgressiveCount | 0 | | totalVerbs | 151 | | matches | (empty) | |
| 100.00% | Em-dash & semicolon overuse | Target: ≤2% sentences with em-dashes/semicolons | | emDashCount | 0 | | semicolonCount | 0 | | flaggedSentences | 0 | | totalSentences | 59 | | ratio | 0 | | matches | (empty) | |
| 100.00% | Purple prose (modifier overload) | Target: <4% adverbs, <2% -ly adverbs, no adj stacking | | wordCount | 971 | | adjectiveStacks | 0 | | stackExamples | (empty) | | adverbCount | 21 | | adverbRatio | 0.021627188465499485 | | lyAdverbCount | 7 | | lyAdverbRatio | 0.007209062821833162 | |
| 100.00% | Repeated phrase echo | Target: ≤20% sentences with echoes (window: 2) | | totalSentences | 59 | | echoCount | 0 | | echoWords | (empty) | |
| 100.00% | Sentence length variance | Target: CV ≥0.4 for sentence word counts | | totalSentences | 59 | | mean | 17.61 | | std | 11.42 | | cv | 0.649 | | sampleLengths | | 0 | 29 | | 1 | 28 | | 2 | 4 | | 3 | 22 | | 4 | 32 | | 5 | 19 | | 6 | 27 | | 7 | 10 | | 8 | 12 | | 9 | 6 | | 10 | 5 | | 11 | 25 | | 12 | 27 | | 13 | 21 | | 14 | 16 | | 15 | 20 | | 16 | 14 | | 17 | 4 | | 18 | 24 | | 19 | 4 | | 20 | 30 | | 21 | 40 | | 22 | 8 | | 23 | 22 | | 24 | 24 | | 25 | 8 | | 26 | 12 | | 27 | 17 | | 28 | 21 | | 29 | 24 | | 30 | 5 | | 31 | 18 | | 32 | 14 | | 33 | 16 | | 34 | 18 | | 35 | 20 | | 36 | 2 | | 37 | 2 | | 38 | 23 | | 39 | 8 | | 40 | 24 | | 41 | 8 | | 42 | 5 | | 43 | 18 | | 44 | 4 | | 45 | 14 | | 46 | 37 | | 47 | 4 | | 48 | 29 | | 49 | 25 |
| |
| 46.89% | Sentence opener variety | Target: ≥60% unique sentence openers | | consecutiveRepeats | 9 | | diversityRatio | 0.3728813559322034 | | totalSentences | 59 | | uniqueOpeners | 22 | |
| 0.00% | Adverb-first sentence starts | Target: ≥3% sentences starting with an adverb | | adverbCount | 0 | | totalSentences | 53 | | matches | (empty) | | ratio | 0 | |
| 91.70% | Pronoun-first sentence starts | Target: ≤30% sentences starting with a pronoun | | pronounCount | 17 | | totalSentences | 53 | | matches | | 0 | "She did not shout." | | 1 | "She had pushed through the" | | 2 | "His warm brown eyes had" | | 3 | "She did not turn back." | | 4 | "Her coat had soaked through," | | 5 | "she called out, her voice" | | 6 | "His face was sharp, narrow," | | 7 | "He did not slow." | | 8 | "He turned into a narrow" | | 9 | "She had lost DS Morris" | | 10 | "She descended concrete steps that" | | 11 | "She passed a rusted ticket" | | 12 | "he said, extending a weathered" | | 13 | "She looked past him." | | 14 | "She made her decision." | | 15 | "She could feel the weight" | | 16 | "He held something small and" |
| | ratio | 0.321 | |
| 0.00% | Subject-first sentence starts | Target: ≤72% sentences starting with a subject | | subjectCount | 50 | | totalSentences | 53 | | matches | | 0 | "The suspect's heel struck a" | | 1 | "Rain plastered her closely cropped" | | 2 | "She did not shout." | | 3 | "Shouting gave chase targets an" | | 4 | "She had pushed through the" | | 5 | "His warm brown eyes had" | | 6 | "Tomás had said" | | 7 | "Harlow had snapped" | | 8 | "She did not turn back." | | 9 | "The suspect's dark coat whipped" | | 10 | "The chase moved north, past" | | 11 | "The rain slapped her cheeks" | | 12 | "Her coat had soaked through," | | 13 | "The suspect's trainers squeaked against" | | 14 | "she called out, her voice" | | 15 | "The suspect glanced back." | | 16 | "His face was sharp, narrow," | | 17 | "He did not slow." | | 18 | "He turned into a narrow" | | 19 | "She had lost DS Morris" |
| | ratio | 0.943 | |
| 0.00% | Subordinate conjunction sentence starts | Target: ≥2% sentences starting with a subordinating conjunction | | subConjCount | 0 | | totalSentences | 53 | | matches | (empty) | | ratio | 0 | |
| 0.00% | Technical jargon density | Target: ≤6% sentences with technical-jargon patterns | | analyzedSentences | 35 | | technicalSentenceCount | 11 | | matches | | 0 | "Behind her, the distinctive green neon sign of The Raven's Nest flickered above the doorway, casting a sickly glow over old maps and black-and-white photographs…" | | 1 | "The suspect's dark coat whipped around the next corner, and she followed, her boots splashing through gutters that smelled of rotting leaves and old grease." | | 2 | "The suspect's trainers squeaked against brick, a tick-tock rhythm of panic that matched the jerking second hand of her watch." | | 3 | "He turned into a narrow alley that smelled of damp brick and rotting leaves, and she followed, her breathing even, her university training buried deep beneath y…" | | 4 | "She had lost DS Morris three years ago under circumstances that had left a hollow behind her ribs, circumstances that supernatural origins could not explain, an…" | | 5 | "Old brick arches loomed overhead, their mortar crumbling with age, their shadowed interiors hiding doorways that smelled of mildew and old secrets." | | 6 | "The suspect turned down a steep set of concrete stairs that led beneath the surface, away from the rain, and Harlow followed without pause." | | 7 | "She descended concrete steps that smelled of rust and forgotten tunneling, her boots echoing in the dark." | | 8 | "The air smelled of copper, herbal smoke, and something older, something that made Harlow's teeth ache." | | 9 | "The back room of her mind, the part that had learned from Tomás Herrera and his unauthorized treatments, whispered that the clique had built this place specific…" | | 10 | "He held something small and white in his grip, a bone token carved with markings that matched the guard's coat." |
| |
| 0.00% | Useless dialogue additions | Target: ≤5% dialogue tags with trailing filler fragments | | totalTags | 6 | | uselessAdditionCount | 2 | | matches | | 0 | "she called out, her voice flat against the thunder of rain" | | 1 | "the suspect said, his voice low," |
| |
| 59.09% | Dialogue tag variety (said vs. fancy) | Target: ≤10% fancy dialogue tags | | totalTags | 4 | | fancyCount | 1 | | fancyTags | | 0 | "she called out (call out)" |
| | dialogueSentences | 11 | | tagDensity | 0.364 | | leniency | 0.727 | | rawRatio | 0.25 | | effectiveRatio | 0.182 | |