| 100.00% | Adverbs in dialogue tags | Target: ≤10% dialogue tags with adverbs | | totalTags | 4 | | adverbTagCount | 1 | | adverbTags | | 0 | "he said quietly [quietly]" |
| | dialogueSentences | 23 | | tagDensity | 0.174 | | leniency | 0.348 | | rawRatio | 0.25 | | effectiveRatio | 0.087 | |
| 97.01% | AI-ism adverb frequency | Target: <2% AI-ism adverbs (58 tracked) | | wordCount | 1671 | | totalAiIsmAdverbs | 1 | | 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) | |
| 73.07% | AI-ism word frequency | Target: <2% AI-ism words (290 tracked) | | wordCount | 1671 | | totalAiIsms | 9 | | found | | | highlights | | 0 | "calculating" | | 1 | "whisper" | | 2 | "etched" | | 3 | "pulsed" | | 4 | "familiar" | | 5 | "flicked" | | 6 | "echoed" | | 7 | "porcelain" |
| |
| 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 | 150 | | matches | (empty) | |
| 100.00% | Filter word density | Target: ≤3% sentences with filter/hedge words | | filterCount | 2 | | hedgeCount | 1 | | narrationSentences | 150 | | filterMatches | | | hedgeMatches | | |
| 100.00% | Gibberish response detection | Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words) | | analyzedSentences | 169 | | gibberishSentences | 0 | | adjustedGibberishSentences | 0 | | longSentenceCount | 0 | | runOnParagraphCount | 0 | | giantParagraphCount | 0 | | wordSaladCount | 0 | | repetitionLoopCount | 0 | | controlTokenCount | 0 | | repeatedSegmentCount | 0 | | maxSentenceWordsSeen | 35 | | ratio | 0 | | matches | (empty) | |
| 100.00% | Markdown formatting overuse | Target: ≤5% words in markdown formatting | | markdownSpans | 0 | | markdownWords | 0 | | totalWords | 1671 | | ratio | 0 | | matches | (empty) | |
| 100.00% | Missing dialogue indicators (quotation marks) | Target: ≤10% speech attributions without quotation marks | | totalAttributions | 9 | | unquotedAttributions | 0 | | matches | (empty) | |
| 100.00% | Name drop frequency | Target: ≤1.0 per-name mentions per 100 words | | totalMentions | 57 | | wordCount | 1441 | | uniqueNames | 26 | | maxNameDensity | 0.9 | | worstName | "Harlow" | | maxWindowNameDensity | 2 | | worstWindowName | "Harlow" | | discoveredNames | | Harlow | 13 | | Berwick | 1 | | Street | 1 | | Regent | 1 | | Canal | 1 | | Raven | 1 | | Nest | 2 | | Silas | 4 | | Whitfield | 1 | | Morris | 4 | | Camden | 2 | | Northern | 1 | | Line | 1 | | Needles | 1 | | Metropolitan | 1 | | Police | 1 | | Veil | 2 | | Market | 4 | | Deptford | 1 | | London | 1 | | Herrera | 1 | | Saint | 1 | | Christopher | 1 | | Tomás | 6 | | Tube | 1 | | Protocol | 3 |
| | persons | | 0 | "Harlow" | | 1 | "Regent" | | 2 | "Silas" | | 3 | "Morris" | | 4 | "Line" | | 5 | "Police" | | 6 | "Market" | | 7 | "Herrera" | | 8 | "Saint" | | 9 | "Christopher" | | 10 | "Tomás" | | 11 | "Protocol" |
| | places | | 0 | "Berwick" | | 1 | "Street" | | 2 | "Raven" | | 3 | "Nest" | | 4 | "Deptford" | | 5 | "London" |
| | globalScore | 1 | | windowScore | 1 | |
| 100.00% | Narrator intent-glossing | Target: ≤2% narration sentences with intent-glossing patterns | | analyzedSentences | 100 | | glossingSentenceCount | 1 | | matches | | 0 | "looked like London's afterthoughts, the o" |
| |
| 100.00% | "Not X but Y" pattern overuse | Target: ≤1 "not X but Y" per 1000 words | | totalMatches | 1 | | per1kWords | 0.598 | | wordCount | 1671 | | matches | | 0 | "not to a maintenance tunnel but to a platform" |
| |
| 100.00% | Overuse of "that" (subordinate clause padding) | Target: ≤2% sentences with "that" clauses | | thatCount | 1 | | totalSentences | 169 | | matches | | |
| 100.00% | Paragraph length variance | Target: CV ≥0.5 for paragraph word counts | | totalParagraphs | 71 | | mean | 23.54 | | std | 21.63 | | cv | 0.919 | | sampleLengths | | 0 | 12 | | 1 | 38 | | 2 | 40 | | 3 | 2 | | 4 | 4 | | 5 | 87 | | 6 | 64 | | 7 | 4 | | 8 | 55 | | 9 | 29 | | 10 | 4 | | 11 | 32 | | 12 | 3 | | 13 | 53 | | 14 | 19 | | 15 | 82 | | 16 | 8 | | 17 | 62 | | 18 | 79 | | 19 | 9 | | 20 | 12 | | 21 | 17 | | 22 | 15 | | 23 | 34 | | 24 | 11 | | 25 | 54 | | 26 | 8 | | 27 | 92 | | 28 | 20 | | 29 | 16 | | 30 | 3 | | 31 | 7 | | 32 | 9 | | 33 | 1 | | 34 | 49 | | 35 | 11 | | 36 | 5 | | 37 | 20 | | 38 | 7 | | 39 | 32 | | 40 | 26 | | 41 | 15 | | 42 | 10 | | 43 | 15 | | 44 | 27 | | 45 | 33 | | 46 | 20 | | 47 | 31 | | 48 | 12 | | 49 | 11 |
| |
| 100.00% | Passive voice overuse | Target: ≤2% passive sentences | | passiveCount | 1 | | totalSentences | 150 | | matches | | |
| 100.00% | Past progressive (was/were + -ing) overuse | Target: ≤2% past progressive verbs | | pastProgressiveCount | 0 | | totalVerbs | 258 | | matches | (empty) | |
| 100.00% | Em-dash & semicolon overuse | Target: ≤2% sentences with em-dashes/semicolons | | emDashCount | 0 | | semicolonCount | 0 | | flaggedSentences | 0 | | totalSentences | 169 | | ratio | 0 | | matches | (empty) | |
| 100.00% | Purple prose (modifier overload) | Target: <4% adverbs, <2% -ly adverbs, no adj stacking | | wordCount | 1444 | | adjectiveStacks | 0 | | stackExamples | (empty) | | adverbCount | 48 | | adverbRatio | 0.0332409972299169 | | lyAdverbCount | 8 | | lyAdverbRatio | 0.00554016620498615 | |
| 100.00% | Repeated phrase echo | Target: ≤20% sentences with echoes (window: 2) | | totalSentences | 169 | | echoCount | 0 | | echoWords | (empty) | |
| 100.00% | Sentence length variance | Target: CV ≥0.4 for sentence word counts | | totalSentences | 169 | | mean | 9.89 | | std | 7.03 | | cv | 0.711 | | sampleLengths | | 0 | 12 | | 1 | 16 | | 2 | 16 | | 3 | 3 | | 4 | 3 | | 5 | 11 | | 6 | 26 | | 7 | 3 | | 8 | 2 | | 9 | 4 | | 10 | 8 | | 11 | 16 | | 12 | 35 | | 13 | 15 | | 14 | 13 | | 15 | 11 | | 16 | 16 | | 17 | 10 | | 18 | 18 | | 19 | 9 | | 20 | 4 | | 21 | 13 | | 22 | 2 | | 23 | 4 | | 24 | 5 | | 25 | 21 | | 26 | 1 | | 27 | 2 | | 28 | 7 | | 29 | 12 | | 30 | 6 | | 31 | 11 | | 32 | 4 | | 33 | 2 | | 34 | 15 | | 35 | 4 | | 36 | 11 | | 37 | 3 | | 38 | 19 | | 39 | 13 | | 40 | 3 | | 41 | 1 | | 42 | 5 | | 43 | 12 | | 44 | 6 | | 45 | 7 | | 46 | 6 | | 47 | 7 | | 48 | 8 | | 49 | 9 |
| |
| 60.55% | Sentence opener variety | Target: ≥60% unique sentence openers | | consecutiveRepeats | 16 | | diversityRatio | 0.42011834319526625 | | totalSentences | 169 | | uniqueOpeners | 71 | |
| 49.02% | Adverb-first sentence starts | Target: ≥3% sentences starting with an adverb | | adverbCount | 2 | | totalSentences | 136 | | matches | | 0 | "Of course he knew it." | | 1 | "Then he spoke, his voice" |
| | ratio | 0.015 | |
| 100.00% | Pronoun-first sentence starts | Target: ≤30% sentences starting with a pronoun | | pronounCount | 34 | | totalSentences | 136 | | matches | | 0 | "He vaulted the barrier and" | | 1 | "He cut left down Berwick" | | 2 | "Her left wrist stung where" | | 3 | "She'd torn something in her" | | 4 | "She kept running." | | 5 | "She gained a metre." | | 6 | "He cut hard down a" | | 7 | "She grabbed his ankle." | | 8 | "He tore free, dropped, landed" | | 9 | "He wanted distance more than" | | 10 | "They'd come out behind the" | | 11 | "She stood at the lip" | | 12 | "She'd arrived to find him" | | 13 | "She keyed her radio." | | 14 | "She thumped the unit against" | | 15 | "She looked at the tin" | | 16 | "It looked like London's afterthoughts," | | 17 | "His short curly hair was" | | 18 | "She pulled her arm free" | | 19 | "His warm brown eyes flicked" |
| | ratio | 0.25 | |
| 33.53% | Subject-first sentence starts | Target: ≤72% sentences starting with a subject | | subjectCount | 116 | | totalSentences | 136 | | matches | | 0 | "He vaulted the barrier and" | | 1 | "The kid couldn't have been" | | 2 | "He cut left down Berwick" | | 3 | "Harlow didn't shout." | | 4 | "Shouting wasted air." | | 5 | "Her left wrist stung where" | | 6 | "She'd torn something in her" | | 7 | "She kept running." | | 8 | "The kid ran faster." | | 9 | "This was the one from" | | 10 | "Silas's nephew, or runner, or" | | 11 | "An hour ago Harlow had" | | 12 | "The same tin box that" | | 13 | "The same tin box DS" | | 14 | "Harlow's boots skidded on the" | | 15 | "Soho bled into Camden after" | | 16 | "The smell of fried oil" | | 17 | "The boy slipped between two" | | 18 | "Palms flat on wet metal," | | 19 | "She gained a metre." |
| | ratio | 0.853 | |
| 36.76% | Subordinate conjunction sentence starts | Target: ≥2% sentences starting with a subordinating conjunction | | subConjCount | 1 | | totalSentences | 136 | | matches | | | ratio | 0.007 | |
| 100.00% | Technical jargon density | Target: ≤6% sentences with technical-jargon patterns | | analyzedSentences | 59 | | technicalSentenceCount | 2 | | matches | | 0 | "She'd arrived to find him with his throat opened, his eyes full of something that wasn't blood, and no footprints around his body in the dust." | | 1 | "Above, rain found a crack somewhere and dripped, heavy drops hitting metal with a tick that echoed like a clock." |
| |
| 100.00% | Useless dialogue additions | Target: ≤5% dialogue tags with trailing filler fragments | | totalTags | 4 | | uselessAdditionCount | 0 | | matches | (empty) | |
| 100.00% | Dialogue tag variety (said vs. fancy) | Target: ≤10% fancy dialogue tags | | totalTags | 2 | | fancyCount | 0 | | fancyTags | (empty) | | dialogueSentences | 23 | | tagDensity | 0.087 | | leniency | 0.174 | | rawRatio | 0 | | effectiveRatio | 0 | |