Run: 2026-05-31-01KSYX8JEYJW9DT0DWSMT91Z8E

Run Details

Duration:
43.8s
Cost:
$0.087890
Provider:
Anthropic

Model input

System
You are an expert and award-winning novel writer in the dark Mystery genre. Your readers are hooked on your stories and can't wait to read the book you have in store. <important> - MUST: Start each chapter in medias res (in the middle of action). AVOID talking about the weather, time of day, the position of the sun, or other boring stuff. - The instructions/summary are just a that, a summary. Feel free to add details, stretch sections and add interesting transitions/descriptions/fillers. - When called for it, have fast-paced action, but otherwise take things slow. This is an experience, and not for people with short attention spans. Enjoy the wine, not slurp Red Bull. - Add descriptions when transitioning places/times/etc, or when coming by new places (e.g. a corner shop, a cafe, etc.). But remember: NOT at the start or end of a chapter. - MUST: AVOID ending in internal monologue, reminiscing or waiting for the next day. A good chapter end is when we're ending right when shit hits the fan. We want to have the reader be excited for what comes next. So no reminiscing, contemplating or summarizing the day. It's popcorn time! </important>
User/Human
Take into account the following glossary of characters/locations/items/lore... when writing your response: <codex> <character id="4416" name="Detective Harlow Quinn" aliases="Quinn, Detective Quinn, Harlow" pronouns="she/her" species="Human" storyRole="Antagonist"> <eyeColor>brown</eyeColor> <hair>closely cropped salt-and-pepper</hair> <height>5'9"</height> <age>41</age> <jawline>sharp jaw</jawline> <watch>worn leather watch on her left wrist</watch> <bearing>military precision</bearing> <description>A Metropolitan Police detective with 18 years of decorated service who suspects the clique is involved in criminal activity.</description> <backstory>She lost her partner, DS Morris, during a case three years ago under unexplained circumstances that had supernatural origins she doesn't yet understand.</backstory> </character> <character id="4414" name="Eva Kowalski" aliases="Eva, Evie" pronouns="she/her" species="Human" storyRole="Best Friend"> <eyeColor>green</eyeColor> <hair>curly red</hair> <height>5'4"</height> <age>26</age> <glasses>round glasses</glasses> <satchel>worn leather satchel full of books</satchel> <freckles>freckled complexion</freckles> <nervousHabit>tucking hair behind her left ear</nervousHabit> <description>Aurora's childhood friend and an occult researcher.</description> <backstory>Moved to London two years before Aurora and works as a research assistant at the British Museum's restricted archives. She holds a master's degree in Ancient History from Oxford.</backstory> </character> <location id="856" name="The Veil Market" aliases="Veil Market, the Market, underground market" realm="Earth"> <currentLocation>abandoned Tube station beneath Camden</currentLocation> <entryRequirement>bone token</entryRequirement> <schedule>moves locations every full moon</schedule> <description>A hidden supernatural black market that sells enchanted goods, banned alchemical substances, and information.</description> </location> <item id="2004" name="Veil Compass" aliases="the Compass, shadow compass" type="Tool" origin="The Veil Market"> <casingMaterial>small brass compass</casingMaterial> <faceMarkings>face etched with protective sigils</faceMarkings> <needle>points toward the nearest supernatural rift or portal</needle> <patina>casing has a patina of verdigris</patina> <creator>crafted by a Shade artisan</creator> <description>A compass attuned to supernatural energy.</description> </item> </codex> <proseGuidelines> <styleGuide> - Write in past tense and use British English spelling and grammar - Keep a Flesch reading ease score of 60 - Respect the the Royal Order of Adjectives: The order is: opinion, size, age, shape, color, origin, material, purpose, followed by the noun itself (e.g., "a lovely little old rectangular green French silver whittling knife") - Respect the ablaut reduplication rule (e.g. tick-tock, flip-flop) - Write in active voice - Passive voice: <bad>The book was read by Sarah.</bad> - Active voice: <good>Sarah read the book.</good> - Reduce the use of passive verbs - <bad>For a moment, I was tempted to throw in the towel.</bad> - <good>For a moment, I felt tempted to throw in the towel.</good> - Avoid misplaced modifiers that can cause confusion when starting with "-ing" words: - <bad>Considering going to the store, the empty fridge reflected in Betty's eyes.</bad> - <good>Betty stared into the empty fridge. It was time to go to the store.</good> - Avoid redundant adverbs that state the obvious meaning already contained in the verb: - <bad>She whispered quietly to her mom.</bad> - <good>She whispered to her mom.</good> - Use stronger, more descriptive verbs over weak ones: - <bad>Daniel drove quickly to his mother's house.</bad> - <good>Daniel raced to his mother's house.</good> - Omit adverbs that don't add solid meaning like "extremely", "definitely", "truly", "very", "really": - <bad>The movie was extremely boring.</bad> - <good>The movie was dull.</good> - Use adverbs to replace clunky phrasing when they increase clarity: - <bad>He threw the bags into the corner in a rough manner.</bad> - <good>He threw the bags into the corner roughly.</good> - Avoid making simple thoughts needlessly complex: - <bad>After I woke up in the morning the other day, I went downstairs, turned on the stove, and made myself a very good omelet.</bad> - <good>I cooked a delicious omelet for breakfast yesterday morning.</good> - Never backload sentences by putting the main idea at the end: - <bad>I decided not to wear too many layers because it's really hot outside.</bad> - <good>It's sweltering outside today, so I dressed light.</good> - Omit nonessential details that don't contribute to the core meaning: - <bad>It doesn't matter what kind of coffee I buy, where it's from, or if it's organic or not—I need to have cream because I really don't like how the bitterness makes me feel.</bad> - <good>I add cream to my coffee because the bitter taste makes me feel unwell.</good> - Always follow the "show, don't tell" principle. For instance: - Telling: <bad>Michael was terribly afraid of the dark.</bad> - Showing: <good>Michael tensed as his mother switched off the light and left the room.</good>- Telling: <bad>I walked through the forest. It was already Fall, and I was getting cold.</bad> - Showing: <good>Dry orange leaves crunched under my feet. I pulled my coat's collar up and rubbed my hands together.</good>- Add sensory details (sight, smell, taste, sound, touch) to support the "showing" (but keep an active voice) - <bad>The room was filled with the scent of copper.</bad> - <good>Copper stung my nostrils. Blood. Recent.</good> - Use descriptive language more sporadically. While vivid descriptions are engaging, human writers often use them in bursts rather than consistently throughout a piece. When adding them, make them count! Like when we transition from one location to the next, or someone is reminiscing their past, or explaining a concept/their dream... - Avoid adverbs and clichés and overused/commonly used phrases. Aim for fresh and original descriptions. - Avoid writing all sentences in the typical subject, verb, object structure. Mix short, punchy sentences with long, descriptive ones. Drop fill words to add variety. Like so: <good>Locked. Seems like someone doesn't want his secrets exposed. I can work with that.</good> - Convey events and story through dialogue. It is important to keep a unique voice for every character and make it consistent. - Write dialogue that reveals characters' personalities, motivations, emotions, and attitudes in an interesting and compelling manner - Leave dialogue unattributed. If needed, only use "he/she said" dialogue tags and convey people's actions or face expressions through their speech. Dialogue always is standalone, never part of a paragraph. Like so: - <bad>"I don't know," Helena said nonchalantly, shrugging her shoulders</bad> - <good>"No idea" "Why not? It was your responsibility"</good> - Avoid boring and mushy dialog and descriptions, have dialogue always continue the action, never stall or include unnecessary fluff. Vary the descriptions to not repeat yourself. Avoid conversations that are just "Let's go" "yes, let's" or "Are you ready?" "Yes I'm ready". Those are not interesting. Think hard about every situtation and word of text before writing dialogue. If it doesn't serve a purpose and it's just people talking about their day, leave it. No one wants to have a normal dinner scene, something needs to happen for it to be in the story. Words are expensive to print, so make sure they count! - Put dialogue on its own paragraph to separate scene and action. - Use body language to reveal hidden feelings and implied accusations- Imply feelings and thoughts, never state them directly - NEVER use indicators of uncertainty like "trying" or "maybe" - NEVER use em-dashes, use commas for asides instead </styleGuide> <voiceGuide> Each character in the story needs to have distinct speech patterns: - Word choice preferences - Sentence length tendencies - Cultural/educational influences - Verbal tics and catchphrases Learn how each person talks and continue in their style, and use their Codex entries as reference. <examples> - <bad>"We need to go now." "Yes, we should leave." "I agree."</bad> <good>"Time's up." "Indeed, our departure is rather overdue." "Whatever, let's bounce."</good> - Power Dynamic Example: <bad> "We need to discuss the contract." "Yes, let's talk about it." "I have concerns." </bad> <good> "A word about the contract." "Of course, Mr. Blackwood. Whatever you need." "The terms seem..." A manicured nail tapped the desk. "Inadequate." "I can explain every-" "Can you?" </good> </examples> </voiceGuide> <dialogueFlow> When writing dialogue, consider that it usually has a goal in mind, which gives it a certain flow. Make dialogue sections also quite snappy in the back and forth, and don't spread the lines out as much. It's good to have details before, after, or as a chunk in-between, but we don't want to have a trail of "dialogue breadcrumbs" spread throughout a conversation. <examples> - Pattern 1 - Question/Deflection/Revelation: <good> "Where were you last night?" "Work. The usual." "Lipstick's an interesting shade for spreadsheets." </good> - Pattern 2 - Statement/Contradiction/Escalation: <good> "Your brother's clean." "Tommy doesn't touch drugs." "I'm holding his tox screen." </good> - Pattern 3 - Observation/Denial/Truth: <good> "That's a new watch." "Birthday gift." "We both know what birthdays mean in this business." </good> - Example - A Simple Coffee Order: <bad> "I'll have a coffee." "What size?" "Large, please." </bad> <good> "Black coffee.""Size?""Large. Been a long night." "That bodega shooting?" "You watch too much news." "My brother owns that store." </good> This short exchange: - Advances plot (reveals connection to crime) - Shows character (cop working late) - Creates tension (unexpected connection) - Sets up future conflict (personal stake) - Example - Dinner Scene: <bad> "Pass the salt." "Here you go." "Thanks." </bad> <good> "Salt?" "Perfect as is. Mother's recipe." "Mother always did prefer... bland things." "Unlike your first wife?" </good> - Example - Office Small Talk: <bad> "Nice weather today." "Yes, very nice." "Good for golf." </bad> <good> "Perfect golf weather." "Shame about your membership." "Temporary suspension. Board meets next week." "I know. I called the vote." </good> </examples> </dialogueFlow> <subtextGuide> - Layer dialogue with hidden meaning: <bad>"I hate you!" she yelled angrily.</bad> <good>"I made your favorite dinner." The burnt pot sat accusingly on the stove.</good> - Create tension through indirect communication: <bad>"Are you cheating on me?"</bad> <good>"Late meeting again?" The lipstick stain on his collar caught the light.</good> <examples> - Example 1 - Unspoken Betrayal: <bad> "Did you tell them about our plans?" "No, I would never betray you." "I don't believe you." </bad> <good> "Funny. Johnson mentioned our expansion plans today." "The market's full of rumors." "Mentioned the exact numbers, actually." The pen in his hand snapped. </good> - Example 2 - Failed Marriage: <bad> "You're never home anymore." "I have to work late." "I miss you." </bad> <good> "Your dinner's in the microwave. Again." "Meetings ran long." "They always do." She folded the same shirt for the third time. </good> - Example 3 - Power Struggle: <bad> "You can't fire me." "I'm the boss." "I'll fight this." </bad> <good> "That's my father's nameplate you're sitting behind." "Was." "The board meeting's on Thursday." </good> </examples> </subtextGuide> <sceneDetail> While writing dialogue makes things more fun, sometimes we need to add detail to not have it be a full on theatre piece. <examples> - Example A (Power Dynamic Scene) <good> "Where's my money?" The ledger snapped shut. "I need more time." "Interesting." He pulled out a familiar gold pocket watch. My mother's. "Time is exactly what you bargained with last month." "That was different-" "Was it?" The watch dangled between us. "Four generations of O'Reillys have wound this every night. Your mother. Your grandmother. Your great-grandmother.Shall we see who winds it next?" </good> - Example B (Action Chase) It's much better to be in the head of the character experiencing it, showing a bit of their though-process, mannerisms and personality: <good> Three rules for surviving a goblin chase in Covent Garden: Don't run straight. Don't look back. Don't let them herd you underground. I broke the first rule at Drury Lane. Rookie mistake. The fruit cart I dodged sailed into the wall behind me. Glass shattered. Someone screamed about insurance. *Tourist season's getting rough*, the scream seemed to say. Londoners adapt fast. "Oi! Market's closed!" The goblin's accent was pure East End. They're evolving. Learning. I spotted the Warren Street tube station sign ahead. *Shit.* There went rule three. </good> - Example C (Crime Scene Investigation) <good> "Greek." Davies snapped photos of the symbols. "No, wait. Reverse Greek." "Someone's been watching too many horror films." I picked up a receipt from the floor. Occult supply shop in Camden. Paid by credit card. *Amateur hour*. "Could be dangerous though," Davies said. "Remember Bristol?" "Bristol was Sanskrit. And actual cultists." I pointed to the nearest symbol. "This genius wrote 'darkness' backwards but used a Sigma instead of an S. It's summoning Instagram followers at best." "Speaking of followers..." Davies pointed to heavy foot traffic in the dust. Multiple sets. All new trainers. *Ah.* "Anyone check local uni paranormal societies?" </good> - Example D (Dialogue-heavy) <good> "Found your card in her wallet." The detective slid it across the table. Worn edges. Folded corner. Three years old at least. "Standard practice. I work missing persons." "Funny thing about missing persons.Eventually they stop being missing. Turn up in the Thames. Under motorways. In pieces." "I don't-" "You found four last year. All breathing." She opened a file. "This would've been your first dead one. If we hadn't found her first." The card felt heavier somehow. </good> </examples> </sceneDetail> <sceneOpenings> KEY RULE: Never open with more than one paragraph of description, no matter how beautiful. Description should be earned through action and dialogue. Instead of opening with setting description, open with: - A character doing something specific - A line of dialogue that raises questions - An unexpected observation - A moment of tension or conflict - Start with a hook that's 1-2 sentences maximum - Follow with a smaller paragraph that provides immediate context - Vary paragraph size from the start to create visual interest </sceneOpenings> </proseGuidelines> Write a chapter based on the following instructions: <instructions> Write a fully fleshed out scene of at least 1000 words in the mystery genre. A detective arrives at a crime scene in an unusual location. Something is wrong — the evidence doesn't add up. A colleague is present, offering a different interpretation. Through careful observation and deduction, the detective begins to see what others have missed. Use the codex entries above as your world reference for characters and setting. Only include the prose of the scene without any markdown or commentary. </instructions>

Model response

AI
The body sat upright in the ticket booth, hands folded in its lap like a commuter waiting for a train that stopped running decades ago. Quinn ducked under the tape and stepped onto the platform. Camden Town's disused level, sealed since the seventies, smelled of rust and standing water. Someone had strung work lights along the tunnel mouth. The glare turned everything the colour of old bone. "Detective Quinn." A young constable hovered near the booth, notebook trembling. "DC Patel said you'd want to see it before forensics moved anything." "Patel's here?" "Down the tunnel. Said the entry point was that way." Quinn crouched in front of the booth. The dead man wore a wool overcoat, decades out of fashion, buttoned to the throat. No blood. No bruising on the visible skin. His eyes had gone milky, but his face held no horror, no surprise. Peaceful. Wrong sort of peaceful. She pulled on a glove and lifted one of his folded hands. Cold, but not the stiff cold of full rigor. The fingers moved. And underneath, pressed into the palm, sat a small disc of yellowed bone, drilled through the centre. She knew that token. Knew exactly what door it opened. Footsteps splashed up the tunnel. Patel emerged, picking his way around a puddle, holding his phone torch though the work lights drowned it out. "There you are." He flicked the torch off. "Bizarre one, isn't it. We reckon he got down through the maintenance hatch off Kentish Town Road. Took a fall somewhere, crawled here, expired sitting up. Heart, probably. Cold did the rest." Quinn didn't answer. She turned the bone token over. Sigils ringed its edge, scratched fine as hair. "Crawled here," she repeated. "Right. We found drag marks back by the junction." Patel nodded down the tunnel, pleased with himself. "Old fella, gets disoriented, exposure does the rest. Sad, but it happens. Urban explorers find one every couple of years." "Drag marks." She rose and faced him. "Show me his shoes." Patel blinked. "His shoes?" "Humour me." She crossed back to the booth and lifted the hem of the overcoat. Two leather brogues, polished, the soles barely scuffed. A faint coat of dust on the toes. Nothing more. No mud. No grit ground into the welt. No torn leather where a man might have dragged himself across forty feet of broken concrete. "He didn't crawl anywhere," she said. "The marks-" "Are someone else's. Or staged." She straightened. "A man crawls a tunnel on his hands and knees, his shoes shred. His trousers tear at the knee. Look at the creases. Sharp as a tailor's window." Patel frowned and crouched beside her. To his credit, he looked instead of arguing. "Could've been carried, then. By his explorer mates. Panicked, dumped him, ran." "Then why prop him up?" Quinn gestured at the folded hands. "Why fold his hands? Frightened men drop bodies and run. They don't arrange them like a Sunday portrait." "So someone wanted him found this way." "Someone wanted him found by us." She held up the token between two fingers. The work lights caught the drilled hole. "Or by whoever came looking." Patel squinted at it. "Old button?" "Bone." She let the word sit. "Carved. See the marks round the rim?" "Decoration." "No." She turned it so the lamplight raked across the surface. The scratches caught and threw tiny shadows. Not random. Deliberate. She'd seen their like once before, three years ago, in an evidence bag that vanished from the property store the same week Morris vanished from her life. She kept her face still. "What's it doing in his hand?" "That's the question." She tucked it into an evidence pouch, sealed it, and slid it into her coat. Patel opened his mouth. She spoke first. "Logged. My pocket. We'll book it together at the station." He let it go. New enough to defer. Old enough to remember it. Quinn walked a slow circle round the booth. The platform edge dropped to the track bed, choked with sleepers and weeds gone pale from a lifetime without sun. She stopped where the lamp shadow met the dark and crouched again. "Bring your torch." Patel knelt beside her and flicked it on. In the beam, the dust on the platform lay thick and undisturbed, a soft grey carpet untouched since the station closed. Except for one thing. A single track of footprints led from the booth to the platform edge and stopped. Just stopped. As if the walker had reached the rim and stepped off into nothing. No prints returning. No prints below in the track bed. "He had a friend," Patel said. "He had a visitor." Quinn followed the line of prints with the torch. They came from the booth, not toward it. Began at the dead man's feet. Ended at the edge of the world. "And the visitor didn't come up the tunnel. Look. No prints anywhere except this one line. The dust's perfect everywhere else. Nobody walked in from Kentish Town. Nobody walked the tunnel at all." Patel's confidence cracked at the seam. "Then how did either of them get here?" She rose. Her knees protested. Eighteen years and they kept score now. "That," she said, "is the right question. Finally." The lamp by the tunnel mouth flickered. Once. Twice. A low buzz, then steady again. Patel jumped. Quinn watched the dead man's milky eyes and the dust and the single line of footprints that began nowhere and ended at a drop into black, and she felt the cold thing she'd carried for three years stir behind her ribs. "Detective." Patel's voice had dropped. "What aren't you telling me?" She thought of the token in her pocket. Thought of Morris and a case file marked closed that never should have been. Thought of a needle she kept in a drawer at home, brass gone green, that had not stopped spinning since the night her partner disappeared. "Get forensics down here. Photograph every print before anyone breathes near them." She started toward the tunnel mouth. "And Patel, the maintenance hatch. Who reported the body?" He flipped his notebook. "Anonymous. Call box on the high street. Forty minutes ago." Quinn stopped walking. Forty minutes ago, the hatch had been welded shut for two years. She'd read the council notice on the way in. Behind her, the work lights went out all at once, and the dark came down the tunnel like water.
created_at"2026-05-31T11:38:45.117Z" 5/31/2026, 11:38:45 AM
model"anthropic/claude-4.8-opus-20260528"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency1527
moderation_latency(null)
generation_time43727
tokens_prompt4671
tokens_completion1627
native_tokens_prompt6538
native_tokens_completion2208
native_tokens_completion_images(null)
native_tokens_reasoning0
native_tokens_cached0
num_media_prompt(null)
num_input_audio_prompt(null)
num_media_completion0
num_search_results(null)
num_fetches(null)
web_search_engine(null)
origin"https://ncbench.com/"
is_byokfalse
finish_reason"stop"
native_finish_reason"end_turn"
service_tier"default"
usage0.08789
router(null)
provider_responses
0
endpoint_id"b0d3beaa-5ff7-4666-a749-b1bb2b14c916"
id"msg_011XdZ9gRC1KBCeTKs8W6ckb"
is_byokfalse
latency1527
model_permaslug"anthropic/claude-4.8-opus-20260528"
provider_name"Anthropic"
status200
user_agent"langchainjs-openai/1.0.0 ((node/v24.16.0; linux; x64))"
http_referer(null)
request_id"req-1780227525-pSvnDJly9jh8ON24o7kF"
session_id(null)
preset_id(null)
api_type"completions"
id"gen-1780227525-4sSexNFLRG0rZC6a0I8a"
upstream_id"msg_011XdZ9gRC1KBCeTKs8W6ckb"
total_cost0.08789
cache_discount(null)
upstream_inference_cost0
provider_name"Anthropic"
response_cache_source_id(null)

Evaluation details

Result Evaluator Details Meta Data
100.00% Adverbs in dialogue tags
Target: ≤10% dialogue tags with adverbs
totalTags16
adverbTagCount0
adverbTags(empty)
dialogueSentences42
tagDensity0.381
leniency0.762
rawRatio0
effectiveRatio0
100.00% AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount1075
totalAiIsmAdverbs0
found(empty)
highlights(empty)
80.00% AI-ism character names
Target: 0 AI-default names (17 tracked, −20% each)
codexExemptions(empty)
found
0"Patel"
100.00% AI-ism location names
Target: 0 AI-default location names (33 tracked, −20% each)
codexExemptions(empty)
found(empty)
76.74% AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount1075
totalAiIsms5
found
0
word"footsteps"
count1
1
word"flicked"
count2
2
word"perfect"
count1
3
word"flickered"
count1
highlights
0"footsteps"
1"flicked"
2"perfect"
3"flickered"
100.00% Cliché density
Target: ≤1 cliche(s) per 800-word window
totalCliches0
maxInWindow0
found(empty)
highlights(empty)
100.00% Emotion telling (show vs. tell)
Target: ≤3% sentences with emotion telling
emotionTells0
narrationSentences94
matches(empty)
100.00% Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount1
hedgeCount1
narrationSentences94
filterMatches
0"notice"
hedgeMatches
0"started to"
100.00% Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences119
gibberishSentences0
adjustedGibberishSentences0
longSentenceCount0
runOnParagraphCount0
giantParagraphCount0
wordSaladCount0
repetitionLoopCount0
controlTokenCount0
repeatedSegmentCount0
maxSentenceWordsSeen41
ratio0
matches(empty)
100.00% Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans0
markdownWords0
totalWords1075
ratio0
matches(empty)
100.00% Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions9
unquotedAttributions0
matches(empty)
77.15% Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions22
wordCount755
uniqueNames4
maxNameDensity1.46
worstName"Patel"
maxWindowNameDensity2.5
worstWindowName"Patel"
discoveredNames
Town1
Quinn8
Patel11
Morris2
persons
0"Quinn"
1"Patel"
2"Morris"
places
0"Town"
globalScore0.772
windowScore0.833
100.00% Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences56
glossingSentenceCount0
matches(empty)
100.00% "Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches0
per1kWords0
wordCount1075
matches(empty)
100.00% Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount1
totalSentences119
matches
0"knew that token"
100.00% Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs48
mean22.4
std18.27
cv0.816
sampleLengths
025
142
223
32
410
548
641
710
824
940
1017
114
1237
1311
144
152
1655
176
182
1935
2026
2129
227
2326
246
2513
261
2753
286
2935
3013
3140
323
3363
3410
356
3667
3714
3812
398
4058
4110
4247
4327
4414
453
4621
4719
100.00% Passive voice overuse
Target: ≤2% passive sentences
passiveCount1
totalSentences94
matches
0"been welded"
100.00% Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount0
totalVerbs138
matches(empty)
100.00% Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount0
semicolonCount0
flaggedSentences0
totalSentences119
ratio0
matches(empty)
100.00% Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount755
adjectiveStacks0
stackExamples(empty)
adverbCount20
adverbRatio0.026490066225165563
lyAdverbCount2
lyAdverbRatio0.0026490066225165563
100.00% Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences119
echoCount0
echoWords(empty)
100.00% Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences119
mean9.03
std7.29
cv0.807
sampleLengths
025
110
214
39
49
511
612
72
810
97
1015
112
126
1313
141
154
1612
179
183
1917
204
216
225
2319
248
2532
263
276
288
294
3017
3120
327
334
342
352
362
3713
388
398
402
412
426
4316
446
452
467
4728
486
498
82.35% Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats7
diversityRatio0.5294117647058824
totalSentences119
uniqueOpeners63
0.00% Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount0
totalSentences77
matches(empty)
ratio0
100.00% Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount22
totalSentences77
matches
0"His eyes had gone milky,"
1"She pulled on a glove"
2"She knew that token."
3"He flicked the torch off"
4"She turned the bone token"
5"She rose and faced him"
6"She crossed back to the"
7"She held up the token"
8"She let the word sit"
9"She turned it so the"
10"She'd seen their like once"
11"She kept her face still."
12"She tucked it into an"
13"She spoke first."
14"He let it go."
15"She stopped where the lamp"
16"They came from the booth,"
17"Her knees protested."
18"She thought of the token"
19"She started toward the tunnel"
ratio0.286
100.00% Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount54
totalSentences77
matches
0"The body sat upright in"
1"Quinn ducked under the tape"
2"Camden Town's disused level, sealed"
3"Someone had strung work lights"
4"The glare turned everything the"
5"A young constable hovered near"
6"Quinn crouched in front of"
7"The dead man wore a"
8"His eyes had gone milky,"
9"She pulled on a glove"
10"The fingers moved."
11"She knew that token."
12"Footsteps splashed up the tunnel."
13"Patel emerged, picking his way"
14"He flicked the torch off"
15"Quinn didn't answer."
16"She turned the bone token"
17"Sigils ringed its edge, scratched"
18"Patel nodded down the tunnel,"
19"She rose and faced him"
ratio0.701
100.00% Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount2
totalSentences77
matches
0"To his credit, he looked"
1"As if the walker had"
ratio0.026
100.00% Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences21
technicalSentenceCount1
matches
0"Quinn watched the dead man's milky eyes and the dust and the single line of footprints that began nowhere and ended at a drop into black, and she felt the cold …"
100.00% Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags16
uselessAdditionCount0
matches(empty)
100.00% Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags4
fancyCount1
fancyTags
0"she repeated (repeat)"
dialogueSentences42
tagDensity0.095
leniency0.19
rawRatio0.25
effectiveRatio0.048
93.8750%