Run: 2026-02-17-01KHMNFV3VKD3CZAY0ZNSJDCV6

Run Details

Duration:
5m 5s
Cost:
$0.000069

Model input

System
You are an expert novelist with a gift for vivid, immersive prose. You write in tight third-person limited point of view with a strong narrative voice. Your prose is clean, precise, and engaging — you favor strong verbs, concrete details, and natural-sounding dialogue. You will be given a story bible (codex) containing canonical details about characters, locations, items, and lore. Use these details to ground your writing in the established world. Stay consistent with the codex. Write only the prose of the scene. Do not include titles, chapter headings, markdown formatting, or any commentary before or after the scene.
User/Human
<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> 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.

Model response

AI
The flickering neon glow of the abandoned Tube station pulsed like a dying heartbeat, casting jagged shadows across the cracked concrete floor. Detective Harlow Quinn adjusted the strap of her leather jacket, her salt-and-pepper hair catching the dim light as she stepped inside the Veil Market’s latest hideaway. The air smelled of damp earth and something older—something *wrong*. The bone token she’d slipped into the lock had been a gamble, but Quinn had no choice. Not when the case demanded answers. She moved through the dim corridor, her boots crunching on broken glass, her sharp jaw set in determination. The station’s doors were sealed shut, the metal rusted through in places. Her watch, worn leather and ticking like a metronome, kept time with the creaking of the station’s skeletal structure. The evidence was there—scattered, but unmistakable. A single silver locket, its clasp broken, lay half-buried in the dirt. Inside, a small black feather had been pressed against the glass. Not human. Not animal. Something else. “Detective Quinn?” Quinn turned at the sound of her name, her military precision sharp despite the unease creeping up her spine. Standing in the dim glow of a flickering lantern was DS Morris, her partner from years gone by. Her eyes were wide, her usual confidence replaced by something raw—fear, maybe, or something deeper. “Morris,” Quinn said, voice low. “What the hell are you doing here?” Morris hesitated, tucking a strand of dark hair behind her ear, her freckles standing out against her pale skin. “I followed the lead. The locket’s been found in the same district as the other cases. The Veil Market’s always been a hotspot for supernatural activity.” Quinn’s jaw tightened. “And you think this is just another case of stolen heirlooms?” Morris shook her head. “No. Look.” She gestured to the locket. “That feather—it’s not from any bird I’ve seen. And the sigils on the compass around the corner—” “You found a Veil Compass?” Quinn’s voice was a blade. She’d heard rumors, but she’d never seen one up close. The brass casing gleamed faintly under the lantern’s light, its patina dark with age. The needle—if it was a needle—wasn’t pointing north. It was pointing *down*, toward the shadows beneath the station. Morris’s eyes flickered to the compass. “It’s attuned to supernatural energy. That’s why the needle’s acting like this.” Quinn exhaled sharply, her fingers tightening around the handle of her baton. “Then tell me, Morris. What do you think this is?” “A ritual,” Morris said quietly. “Something’s being prepared. And if the Veil Market’s involved, then someone’s pulling the strings.” Quinn’s mind raced. The Veil Market moved every full moon, shifting locations like a ghost. And this time, it had chosen this station—not for the usual reasons of convenience or secrecy, but because of something *else*. Something that pulsed beneath the earth. She knelt, brushing the dirt from the locket’s edge. The black feather was still there, pressed against the glass, as if waiting. She picked it up, running her thumb over its smooth surface. It wasn’t just a feather. It was a key. A key to something buried deep beneath London. “Quinn,” Morris said, her voice urgent. “What are you thinking?” Quinn stood slowly, her gaze fixed on the compass. “I’m thinking we’re not just dealing with a market. We’re dealing with something older. Something that doesn’t play by the rules.” A distant hum vibrated through the station, like the low growl of a storm. The needle on the compass twitched, then pointed straight at her. And for the first time, Quinn saw what was missing. The evidence wasn’t just scattered. It was *hidden*. And it wasn’t for the reasons anyone would expect.
total_cost0.00006936

Evaluation details

Result Evaluator Details Meta Data
66.67% Adverbs in dialogue tags
Target: ≤10% dialogue tags with adverbs
totalTags4
adverbTagCount1
adverbTags
0"Morris said quietly [quietly]"
dialogueSentences15
tagDensity0.267
leniency0.533
rawRatio0.25
effectiveRatio0.133
83.87% AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount620
totalAiIsmAdverbs2
found
0
adverb"sharply"
count1
1
adverb"slowly"
count1
highlights
0"sharply"
1"slowly"
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)
51.61% AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount620
totalAiIsms6
found
0
word"pulsed"
count2
1
word"structure"
count1
2
word"flickered"
count1
3
word"raced"
count1
4
word"vibrated"
count1
highlights
0"pulsed"
1"structure"
2"flickered"
3"raced"
4"vibrated"
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
emotionTells1
narrationSentences48
matches
0"t in determination"
100.00% Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount1
hedgeCount0
narrationSentences48
filterMatches
0"watch"
hedgeMatches(empty)
100.00% Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences58
gibberishSentences0
adjustedGibberishSentences0
longSentenceCount0
runOnParagraphCount0
giantParagraphCount0
wordSaladCount0
repetitionLoopCount0
controlTokenCount0
maxSentenceWordsSeen28
ratio0
matches(empty)
100.00% Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans4
markdownWords4
totalWords613
ratio0.007
matches
0"wrong"
1"down"
2"else"
3"hidden"
100.00% Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions4
unquotedAttributions0
matches(empty)
45.40% Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions23
wordCount478
uniqueNames7
maxNameDensity2.09
worstName"Quinn"
maxWindowNameDensity3
worstWindowName"Quinn"
discoveredNames
Tube1
Harlow1
Quinn10
Veil2
Market2
Morris6
London1
persons
0"Harlow"
1"Quinn"
2"Market"
3"Morris"
places
0"Veil"
1"London"
globalScore0.454
windowScore0.667
74.24% Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences33
glossingSentenceCount1
matches
0"as if waiting"
36.87% "Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches1
per1kWords1.631
wordCount613
matches
0"not for the usual reasons of convenience or secrecy, but because of something *else*"
100.00% Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount0
totalSentences58
matches(empty)
100.00% Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs17
mean36.06
std23.15
cv0.642
sampleLengths
081
184
22
364
445
514
628
752
818
922
1019
1142
1250
1310
1430
1525
1627
90.64% Passive voice overuse
Target: ≤2% passive sentences
passiveCount2
totalSentences48
matches
0"been pressed"
1"was *hidden"
29.06% Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount2
totalVerbs78
matches
0"wasn’t pointing"
1"was pointing"
0.00% Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount6
semicolonCount0
flaggedSentences5
totalSentences58
ratio0.086
matches
0"The air smelled of damp earth and something older—something *wrong*."
1"The evidence was there—scattered, but unmistakable."
2"Her eyes were wide, her usual confidence replaced by something raw—fear, maybe, or something deeper."
3"The needle—if it was a needle—wasn’t pointing north."
4"And this time, it had chosen this station—not for the usual reasons of convenience or secrecy, but because of something *else*."
100.00% Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount487
adjectiveStacks0
stackExamples(empty)
adverbCount13
adverbRatio0.026694045174537988
lyAdverbCount4
lyAdverbRatio0.008213552361396304
100.00% Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences58
echoCount0
echoWords(empty)
100.00% Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences58
mean10.57
std6.12
cv0.579
sampleLengths
022
126
210
317
46
518
612
719
86
912
1011
112
122
132
142
1519
1618
1715
185
197
2019
2126
223
2311
244
257
2617
2710
2810
2914
308
3110
326
3312
3412
3510
365
3714
383
3912
4021
416
429
4313
4411
455
464
478
486
494
47.70% Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats4
diversityRatio0.3275862068965517
totalSentences58
uniqueOpeners19
0.00% Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount0
totalSentences45
matches(empty)
ratio0
100.00% Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount11
totalSentences45
matches
0"She moved through the dim"
1"Her watch, worn leather and"
2"Her eyes were wide, her"
3"She gestured to the locket"
4"She’d heard rumors, but she’d"
5"It was pointing *down*, toward"
6"She knelt, brushing the dirt"
7"She picked it up, running"
8"It wasn’t just a feather."
9"It was a key."
10"It was *hidden*."
ratio0.244
26.67% Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount39
totalSentences45
matches
0"The flickering neon glow of"
1"Detective Harlow Quinn adjusted the"
2"The air smelled of damp"
3"The bone token she’d slipped"
4"She moved through the dim"
5"The station’s doors were sealed"
6"Her watch, worn leather and"
7"The evidence was there—scattered, but"
8"A single silver locket, its"
9"Quinn turned at the sound"
10"Her eyes were wide, her"
11"Quinn said, voice low"
12"Morris hesitated, tucking a strand"
13"Quinn’s jaw tightened."
14"Morris shook her head."
15"She gestured to the locket"
16"Quinn’s voice was a blade"
17"She’d heard rumors, but she’d"
18"The brass casing gleamed faintly"
19"The needle—if it was a"
ratio0.867
0.00% Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount0
totalSentences45
matches(empty)
ratio0
85.71% Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences25
technicalSentenceCount2
matches
0"Morris hesitated, tucking a strand of dark hair behind her ear, her freckles standing out against her pale skin."
1"The black feather was still there, pressed against the glass, as if waiting."
0.00% Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags4
uselessAdditionCount2
matches
0"Quinn said, voice low"
1"Morris said, her voice urgent"
100.00% Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags3
fancyCount0
fancyTags(empty)
dialogueSentences15
tagDensity0.2
leniency0.4
rawRatio0
effectiveRatio0
71.2815%