Run: 2026-03-18-01KM0ARW372RXDRRSQFZYF2NSP

Run Details

Duration:
14.6s
Cost:
$0.001555
Provider:
Mistral

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 evidence tape snapped taut in Inspector Harlow Quinn’s grip, the plastic strands slicing into her leather gloves as she ducked beneath it. The underground platform wasn’t just damp—it was *breathing*, seeping water from the cracked tiles in a slow, rhythmic pulse. Her boots sank slightly into blackened grime that hadn’t seen sunlight in decades. Not a drop of rain ever fell here. Not legally. But the ceiling glistened like it had cried all night, the tiles peeling in wet strips. Above her head, the noise of Camden Town station echoed—distant announcements, the rumble of trains, the squeal of brakes. But down here, in the tunnels that weren’t on any map, there was only silence. The kind of silence that hummed in the ears. The kind that made you check your watch just to hear something tick. Then she saw him. Sergeant Mark Davies stood over the body, his torch beam trembling. Not from the cold—he never did—but from something else. Something unseen. His jaw was set, but his fingers twitched at his side like he was fighting the urge to reach out and straighten his tie. Again. Always adjusting it when things got too real. “You’re late,” he said, not looking up. Harlow stepped closer, the torchlight cutting through the dark like a knife. The body lay sprawled in the centre of the platform, limbs splayed at unnatural angles, one arm stretched toward the tracks as if clawing for a train that would never come. Dark stains pooled beneath the torso, thick and slow. Not just blood. *Something else.* She crouched. The victim was young—early twenties, maybe. Black hoodie, ripped jeans, scuffed trainers. A student, maybe. Off to university. He looked like a dozen others she’d seen—lost in the city, light on purpose, carrying the weight of the future in a backpack. But not tonight. His face was frozen in terror. Eyes wide, mouth open. Not screaming. *Begging.* Harlow reached out—stopped. The torch flickered. “Power’s acting up,” Davies muttered. “Whole system’s glitching down here. Happens after full moons. Always.” She ignored him. Instead, she followed the hand outstretched toward the tracks. The fingers were curled, stiff. She pried one open gently. Something glinted in the palm. A bone token. Small. Worn. Etched with symbols she didn’t recognise. Not the usual tourist trinkets from St. Martin-in-the-Fields. These were older. Thinner. Darker at the edges. Like blood had been used in the carving. “What the hell is that?” Davies asked, stepping closer. His breath hitched. Harlow didn’t answer. She was already standing, scanning the platform. The air smelled wrong. Not just damp. Not just rot. It smelled like burnt copper and wet earth. Like something had been dragged through here recently. Fresh. She walked to the edge of the platform, torch sweeping over the tracks. No blood. No drag marks. Just rusted rails and a single, fresh scuff in the gravel. Then she saw it. A symbol. Scratched into the side of the tunnel wall. Not spray-painted. *Carved.* Deep gouges in the concrete, like claws had dug in. The shape was jagged—three downward strokes, then a jagged circle. Not a letter. Not a sigil she knew. But it *felt* right. Like a lock clicking. Her pulse quickened. “That wasn’t there when I came down,” Davies said suddenly, voice tight. “I checked the route. Matter of fact, I *know* it wasn’t there.” She didn’t answer. She was already moving, torch shifting upward. There, on the ceiling, half-hidden in the shadows—another symbol. Larger. Chipped into the brickwork. Rough. Amateur. But undeniable. And it was *fresh.* She turned to Davies. “You said this tunnel was empty last night.” “Empty as a politician’s promise,” he said. “I walked it myself. Lights, cameras, everything clean.” “So how did this get here?” Davies exhaled sharply. “No idea, boss. But I’ve been down here since six. No deliveries. No contractors. Nothing.” Harlow stepped back, eyes still locked on the ceiling. The symbols weren’t random. They were a path. A trail of breadcrumbs. And they led toward the abandoned tunnel mouth at the far end—the one that hadn’t been open in years. The one that opened into the old station platforms, now swallowed by the Veil Market. She pulled out her phone. No signal. Of course not. Not down here. “Tell me again what happened,” she said. Davies rubbed his temple. “Dispatch called it in. Jogger. Said he heard footsteps. Then a scream. Came down, found him like this. Rigor’s not set in yet. Must’ve happened—” “An hour ago,” Harlow finished. “Maybe less.” She pulled her leather satchel higher on her shoulder. Her fingers brushed the watch on her left wrist. The leather was cracked. The hands had stopped at 3:17. Morris’s time. She pushed the thought away. “You check for a pulse?” she asked. Davies hesitated. “He was—cold. Too cold. Like he’d been here longer than he should’ve.” Harlow stepped forward again. She didn’t touch the body. Didn’t need to. She saw the lividity pattern. The blood had settled in the torso, but the hands and feet were pale. *Too* pale. Like the blood had been drawn out. Or *taken.* She crouched again, this time focusing on the torso. The hoodie was dark. Black. But under the fabric, something was *wrong.* She reached out—then stopped. Not the hoodie. The *back.* There was a bulge. Not from padding. Not from a bag. Something *under* the skin. She pulled out her toolkit. Gloved fingers probed carefully. The hoodie split at the seam. Fabric tore like wet paper. And then she saw it. Three small, *raised* bumps along the spine. Like third-degree burns. But not burns. *Scars.* Fresh ones. Still weeping a dark fluid that smelled like burnt almonds and wet ash. Harlow’s breath caught. A shiver ran up her spine. She stood abruptly. “Get forensics down here. Now.” Davies didn’t move. “Boss?” She didn’t answer. Instead, she strode toward the tunnel mouth at the far end, torch cutting through the dark. The symbols led there. And something else. A sound. A *click.* Like a switch being thrown. Then a voice. Soft. Whispered. Almost a laugh. “Inspector Quinn.” She froze. The voice wasn’t coming from in front of her. It was coming from *inside her head.* And it knew her name.
created_at"2026-03-18T11:19:54.234Z" 3/18/2026, 11:19:54 AM
model"mistralai/mistral-small-2603" 1/1/2603, 12:00:00 AM
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency499
moderation_latency(null)
generation_time14548
tokens_prompt4671
tokens_completion1711
native_tokens_prompt4334
native_tokens_completion1508
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)
origin"https://ncbench.com/"
is_byokfalse
finish_reason"stop"
native_finish_reason"stop"
usage0.0015549
router(null)
provider_responses
0
endpoint_id"f5ed6283-4e17-457d-98cd-2ec0c318171d"
id"c001199591fd4f6ab69aead869fb1ad4"
is_byokfalse
latency499
model_permaslug"mistralai/mistral-small-2603" 1/1/2603, 12:00:00 AM
provider_name"Mistral"
status200
user_agent"langchainjs-openai/1.0.0 ((node/v24.14.0; linux; x64))"
http_referer(null)
api_type"completions"
id"gen-1773832794-nHOWCYm8MbNa6tiRYrxY"
upstream_id"c001199591fd4f6ab69aead869fb1ad4"
total_cost0.0015549
cache_discount(null)
upstream_inference_cost0
provider_name"Mistral"

Evaluation details

Result Evaluator Details Meta Data
100.00% Adverbs in dialogue tags
Target: ≤10% dialogue tags with adverbs
totalTags8
adverbTagCount1
adverbTags
0"Davies said suddenly [suddenly]"
dialogueSentences20
tagDensity0.4
leniency0.8
rawRatio0.125
effectiveRatio0.1
76.19% AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount1050
totalAiIsmAdverbs5
found
0
adverb"slightly"
count1
1
adverb"gently"
count1
2
adverb"suddenly"
count1
3
adverb"sharply"
count1
4
adverb"carefully"
count1
highlights
0"slightly"
1"gently"
2"suddenly"
3"sharply"
4"carefully"
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)
38.10% AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount1050
totalAiIsms13
found
0
word"rhythmic"
count1
1
word"pulse"
count3
2
word"echoed"
count1
3
word"silence"
count2
4
word"weight"
count1
5
word"flickered"
count1
6
word"etched"
count1
7
word"scanning"
count1
8
word"quickened"
count1
9
word"footsteps"
count1
highlights
0"rhythmic"
1"pulse"
2"echoed"
3"silence"
4"weight"
5"flickered"
6"etched"
7"scanning"
8"quickened"
9"footsteps"
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
narrationSentences158
matches
0"n in terror"
100.00% Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount1
hedgeCount0
narrationSentences158
filterMatches
0"watch"
hedgeMatches(empty)
100.00% Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences170
gibberishSentences0
adjustedGibberishSentences0
longSentenceCount0
runOnParagraphCount0
giantParagraphCount0
wordSaladCount0
repetitionLoopCount0
controlTokenCount0
maxSentenceWordsSeen31
ratio0
matches(empty)
100.00% Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans16
markdownWords19
totalWords1040
ratio0.018
matches
0"breathing"
1"Something else."
2"Begging."
3"Carved."
4"felt"
5"know"
6"fresh."
7"Too"
8"taken."
9"wrong."
10"back."
11"under"
12"raised"
13"Scars."
14"click."
15"inside her head."
100.00% Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions13
unquotedAttributions0
matches(empty)
83.33% Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions34
wordCount899
uniqueNames13
maxNameDensity1
worstName"Davies"
maxWindowNameDensity2.5
worstWindowName"Davies"
discoveredNames
Inspector1
Harlow8
Quinn1
Camden1
Town1
Mark1
Davies9
St1
Deep1
Veil1
Market1
Fresh2
Like6
persons
0"Harlow"
1"Quinn"
2"Mark"
3"Davies"
4"Like"
places
0"Inspector"
1"Camden"
2"Town"
3"St"
globalScore0.999
windowScore0.833
0.00% Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences52
glossingSentenceCount4
matches
0"as if clawing for a train that would never come"
1"looked like a dozen others she’d seen—los"
2"smelled like burnt copper and wet earth"
3"smelled like burnt almonds and wet ash"
100.00% "Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches0
per1kWords0
wordCount1040
matches(empty)
100.00% Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount0
totalSentences170
matches(empty)
100.00% Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs61
mean17.05
std17.74
cv1.041
sampleLengths
081
156
24
355
47
557
646
713
83
93
1015
1127
123
1332
1412
1537
1629
174
1849
193
2024
2110
2218
234
2412
2515
266
2718
2855
2913
307
3129
327
3330
345
357
3614
3742
3821
394
4016
414
4220
435
4429
453
466
478
484
4926
91.94% Passive voice overuse
Target: ≤2% passive sentences
passiveCount6
totalSentences158
matches
0"was frozen"
1"were curled"
2"been used"
3"been dragged"
4"been drawn"
5"being thrown"
0.00% Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount6
totalVerbs166
matches
0"was *breathing"
1"was fighting"
2"was already standing"
3"was already moving"
4"wasn’t coming"
5"was coming"
0.00% Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount11
semicolonCount0
flaggedSentences10
totalSentences170
ratio0.059
matches
0"The underground platform wasn’t just damp—it was *breathing*, seeping water from the cracked tiles in a slow, rhythmic pulse."
1"Above her head, the noise of Camden Town station echoed—distant announcements, the rumble of trains, the squeal of brakes."
2"Not from the cold—he never did—but from something else."
3"The victim was young—early twenties, maybe."
4"He looked like a dozen others she’d seen—lost in the city, light on purpose, carrying the weight of the future in a backpack."
5"Harlow reached out—stopped."
6"The shape was jagged—three downward strokes, then a jagged circle."
7"There, on the ceiling, half-hidden in the shadows—another symbol."
8"And they led toward the abandoned tunnel mouth at the far end—the one that hadn’t been open in years."
9"She reached out—then stopped."
89.05% Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount914
adjectiveStacks0
stackExamples(empty)
adverbCount48
adverbRatio0.0525164113785558
lyAdverbCount10
lyAdverbRatio0.010940919037199124
100.00% Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences170
echoCount0
echoWords(empty)
100.00% Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences170
mean6.12
std5.17
cv0.845
sampleLengths
023
119
213
38
42
516
619
715
89
913
104
1111
129
132
1424
151
168
177
1812
1931
209
213
222
232
246
256
263
273
2823
293
306
314
322
331
343
353
365
3710
383
399
405
415
425
433
441
451
466
477
481
493
63.73% Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats10
diversityRatio0.4176470588235294
totalSentences170
uniqueOpeners71
100.00% Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount10
totalSentences123
matches
0"Then she saw him."
1"Always adjusting it when things"
2"Instead, she followed the hand"
3"Just rusted rails and a"
4"Then she saw it."
5"Of course not."
6"Still weeping a dark fluid"
7"Instead, she strode toward the"
8"Then a voice."
9"Almost a laugh."
ratio0.081
100.00% Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount28
totalSentences123
matches
0"Her boots sank slightly into"
1"His jaw was set, but"
2"he said, not looking up"
3"He looked like a dozen"
4"His face was frozen in"
5"She ignored him."
6"She pried one open gently."
7"His breath hitched."
8"She was already standing, scanning"
9"It smelled like burnt copper"
10"She walked to the edge"
11"Her pulse quickened."
12"She didn’t answer."
13"She was already moving, torch"
14"She turned to Davies."
15"They were a path."
16"She pulled out her phone."
17"She pulled her leather satchel"
18"Her fingers brushed the watch"
19"She pushed the thought away."
ratio0.228
100.00% Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount71
totalSentences123
matches
0"The evidence tape snapped taut"
1"The underground platform wasn’t just"
2"Her boots sank slightly into"
3"The kind of silence that"
4"The kind that made you"
5"Sergeant Mark Davies stood over"
6"His jaw was set, but"
7"he said, not looking up"
8"Harlow stepped closer, the torchlight"
9"The body lay sprawled in"
10"The victim was young—early twenties,"
11"A student, maybe."
12"He looked like a dozen"
13"His face was frozen in"
14"Eyes wide, mouth open."
15"Harlow reached out—stopped."
16"The torch flickered."
17"She ignored him."
18"The fingers were curled, stiff."
19"She pried one open gently."
ratio0.577
0.00% Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount0
totalSentences123
matches(empty)
ratio0
80.75% Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences23
technicalSentenceCount2
matches
0"The kind that made you check your watch just to hear something tick."
1"The body lay sprawled in the centre of the platform, limbs splayed at unnatural angles, one arm stretched toward the tracks as if clawing for a train that would…"
0.00% Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags8
uselessAdditionCount2
matches
0"he said, not looking up"
1"Davies said suddenly, voice tight"
100.00% Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags7
fancyCount1
fancyTags
0"Davies muttered (mutter)"
dialogueSentences20
tagDensity0.35
leniency0.7
rawRatio0.143
effectiveRatio0.1
77.4359%