Run: 2026-02-19-01KHTXMF98295C0DD8FEJG6HMA

Run Details

Duration:
1m 25s
Cost:
$0.004855
Provider:
AtlasCloud

Model input

System
You are an expert and award-winning novel writer in the dark Literary Fiction 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="4412" name="Aurora Carter" aliases="Rory, Laila, Aurora, Carter, Malphora" pronouns="she/her" species="Human" storyRole="Protagonist"> <eyeColor>bright blue</eyeColor> <hair>straight shoulder-length black</hair> <height>5'6"</height> <age>25</age> <scar>small crescent-shaped scar on her left wrist from a childhood accident</scar> <description>Aurora, referred to by her friends as Rory, is cool-headed, intelligent, and known for quick out-of-the-box thinking.</description> <backstory>Born in Cardiff to an Irish barrister father (Brendan Carter) and Welsh teacher mother (Jennifer Carter née Ellis), Rory reluctantly pursued Pre-Law at Cardiff University. She fled to London at the behest of her childhood friend Eva after leaving an abusive ex named Evan. By day, Rory works part-time as a delivery person for Yu-Fei Cheung's Golden Empress restaurant. She lives in a flat above Silas' bar.</backstory> </character> <character id="4413" name="Silas Blackwood" aliases="Silas, Si, the Spymaster" pronouns="he/him" species="Human" storyRole="Mentor"> <eyeColor>hazel</eyeColor> <hair>grey-streaked auburn</hair> <height>6'1"</height> <age>58</age> <beard>neatly trimmed, matching his grey-streaked auburn hair</beard> <limp>slight limp in his left leg from an old knee injury</limp> <signetRing>silver signet ring, always worn on his right hand</signetRing> <description>Silas is a retired intelligence operative turned bar owner. He carries himself with quiet authority.</description> <backstory>Former MI6 field agent who retired after a botched operation in Prague left him with a permanent knee injury. He opened "The Raven's Nest" bar in Soho as a front for his network of contacts.</backstory> </character> <location id="854" name="The Raven's Nest" aliases="the Nest, Raven, Silas' bar" realm="Earth"> <signColor>distinctive green neon sign above the entrance</signColor> <secretRoom>hidden back room accessible through a bookshelf, used for clandestine meetings</secretRoom> <description>A dimly lit bar in Soho, London. The walls are covered with old maps and black-and-white photographs.</description> </location> </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 literary fiction genre. Two old friends who haven't seen each other in years run into each other unexpectedly at a bar. One of them has changed significantly. Through their conversation and the tension between who they were and who they've become, reveal the weight of time and unspoken regret. 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 ice in Aurora's glass had melted long ago. She hadn't touched the drink in twenty minutes, too occupied with watching Silas debate the football scores with a regular at the far end of the bar. The familiar rhythm of their voices blended with the low jazz piping through the speakers, creating the kind of background noise that made solitude feel like company. She was about to leave when the door swung open and a figure stepped through. For a moment, the face didn't register. The years had sharpened someone's features, carved new lines around their eyes. The hair was different, shorter, perhaps. Then their gaze met across the room, and recognition struck like a match in darkness. No. Not him. The shock must have shown on her face because he stopped halfway through the doorway, one hand still on the door. The same hesitation. The same uncertainty he'd always had, back when things were different. "Aurora?" The name came out like a question he already knew the answer to. She stood. The bar stool scraped against the floor, too loud in the sudden stillness. "Marcus?" He crossed the distance between them in three long strides, and then he was there, standing in front of her, and suddenly it was eight years ago and they were twenty again, penniless and full of possibilities in their cramped Cardiff flat. "Christ," he breathed. "You look exactly the same." "Liar." But she was smiling, despite everything. Old habits. "You look like a completely different person." He laughed. The same laugh, at least. That hadn't changed. "Bit of an upgrade, I suppose. Got rid of the terrible jumpers." "Your mother loved those jumpers." "My mother still asks about you. Every Christmas. Wants to know why her son's only friend from university vanished off the face of the earth." The words landed somewhere between accusation and jest. Aurora Signal for another drink, her throat suddenly dry. "I've been here. Same city. Same—" She gestured vaguely at the bar, the photographs on the walls, the whole dimly lit world she'd built in this corner of Soho. "Raven's Nest." Marcus looked around properly now, taking in the narrow room with its mismatched furniture and its walls covered in old maps and black-and-white photographs. "Fitting, actually. You always did like hiding in dark corners." "Pot, kettle." "Fair enough." He settled onto the barstool beside her, and Silas appeared with a fresh glass without being asked. Old habits in this place too. "What are you drinking?" "Whiskey. Neat." "Grown-up." He flagged down Silas. "Gin and tonic. Whatever's in the good bottle." Silas raised an eyebrow at Aurora. She gave a tiny nod. The old man had his own ways of reading situations. "Long time," Marcus said when Silas had poured and retreated to his end of the bar. "Eight years." "You remember." "I count." She took a sip of her whiskey, letting the burn settle her nerves. "How's London treating you? Big-shot corporate life suiting you?" He flinched slightly. Good. Let him. "It's not—I don't do that anymore. I left that behind." "When?" "Three years ago. After—" He stopped, glanced away. "After the divorce." The word hung between them like smoke. Aurora felt something twist in her chest, some old wound she'd thought had scarred over. "Emma seemed nice," she said carefully. "When I met her. At the thing. The summer do." "She was." Marcus turned his glass in his hands, watching the light catch the liquid. "She wasn't. It doesn't matter now." "Children?" "No. Thank God. Would've made everything messier." Aurora didn't say anything. The jazz shifted to something slower, sadder. On the wall behind Marcus, an old photograph showed a London that didn't exist anymore, trams and bowler hats and streets that had been bombed and rebuilt into something new. "I looked for you," Marcus said eventually. "After. When I came back to myself. But you'd moved, and your phone number changed, and—" He shrugged. "You were good at disappearing." "Occupational hazard." "What does that mean?" She considered lying. It would be easy, given their history, given everything left unsaid between them. But the whiskey was warm in her blood, and the late hour made honesty feel like a gift she could afford to give. "Silas knew a man," she said. "Back when I first arrived. In London. I was running from—" She stopped, restarted. "I needed to disappear for a while. New name, new job, new everything. Silas helped." "Helped with what?" "Identity. Documentation. The kind of things you don't ask questions about." Marcus stared at her. In the low light, his eyes looked darker than she remembered, more guarded. The boy who'd argued politics with her until three in the morning, who'd believed they could change the world with enough conviction and cheap wine, was nowhere to be seen. In his place sat a man who'd built walls so high not even memory could climb over. "You're not a criminal," he said slowly. "No." "You're not—" He stopped, laughed, ran a hand through his hair. "I don't know what I thought. When I saw you through the window. I thought maybe I'd imagined it." "You don't imagine in The Raven's Nest. That's Silas' job." "Who's Silas?" "The man pouring your drinks." Marcus looked at Silas, properly looked, taking in the grey-streaked auburn hair, the neatly trimmed beard, the silver signet ring glinting on his right hand. Silas caught his gaze and nodded once, a small acknowledgment that somehow managed to convey decades of experience and absolutely nothing about what he'd done or seen or know. "He knows things," Aurora said. "About the city. About people. About the kind of problems that don't have legal solutions." "And you've been—what? Working for him?" "Working for myself." She finished her whiskey, set the glass down with a precise click. "I deliver food. Chinese. Excellent dumplings, if you're hungry." "You're a delivery driver." "You're a divorcee with money to burn on fancy drinks. We all have our crosses to bear." The sharpness in her voice finally got through to him. He flinched again, more visibly this time, and something shifted in his expression. The careful mask cracked, just for a moment, and she caught a glimpse of the boy underneath—the one who'd held her hair back when she was sick, who'd read her poetry when she couldn't sleep, who'd promised they'd always be friends no matter what. "I'm sorry," he said quietly. "For not being there. After. When you needed—" "I didn't need anyone." "Aurora." "I survived." She stood, pulled her jacket from the back of the chair. "That's what I do. I survive. You taught me that, actually. When you left." The words came out harder than she intended, and she saw them hit him like blows. Good. Let him feel it. Let him carry some of the weight she'd been holding for eight years, some of the silence that had become so familiar she'd forgotten it was supposed to hurt. "I didn't want to leave," he said. "You know that. My father was dying, and my mother couldn't—and I had to go home, I had to—" "I know." "So why are you—" "Because you didn't write." Her voice cracked, just slightly, just enough. "You didn't call. You didn't send a single word for three years, and when you finally did, it was to tell me you were getting married. To someone I'd never met. To someone you'd known for six months. And you expected me to be happy about it." "I know." "I was happy for you." The lie tasted like copper in her mouth. "I was. I just—I thought we were different. I thought what we had meant—" "It did." He stood too, reaching for her arm but stopping just short of touching her. "It still does. That's why I'm here. That's why I've been trying to find you." "You found me." "I never stopped looking." The jazz had stopped. In the silence, Aurora could hear her own heartbeat, loud and steady in her ears. Somewhere in the back room, a clock ticked. The old maps on the walls seemed to lean closer, listening. "You should go," she said. "Back to your life. Your other life. The one where you made it." "And you?" "I'm right here. Where I've always been." Marcus reached into his pocket, pulled out a card. Expensive, minimal. He set it on the bar between them. "My number's on there. If you ever—" "I won't." "I know." He smiled, just a little, just enough to remind her of who he used to be. "But I had to try." He turned and walked toward the door, and Aurora watched him go. At the threshold, he paused, looked back, and for a moment she saw the boy he used to be, the one who believed in things, who loved without conditions, who promised forever and meant it. "Goodbye, Aurora." "Goodbye, Marcus." The door swung shut behind him. The jazz started up again, something slow and sad and beautiful. Silas appeared with the bottle, refilled her glass without a word, and retreated to his end of the bar. Aurora sat alone with the card on the counter, white and crisp and full of numbers she would never dial. Outside, London continued its eternal spin, millions of lives intersecting and diverging, people finding each other and losing each other in the dark. She picked up the card, turned it over once, and then dropped it into the ashtray beside her glass. Some things couldn't be recovered. Some people couldn't be found, no matter how hard you looked. Some doors, once closed, stayed that way. She drank her whiskey slowly, letting the burn fade to warmth, and watched the neon sign outside flicker green against the darkness.
created_at"2026-02-19T12:22:42.734Z" 2/19/2026, 12:22:42 PM
model"minimax/minimax-m2.5-20260211"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency3493
moderation_latency(null)
generation_time84925
tokens_prompt4618
tokens_completion4868
native_tokens_prompt4093
native_tokens_completion3943
native_tokens_completion_images(null)
native_tokens_reasoning1870
native_tokens_cached4092
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"
usage0.00485466
router(null)
provider_responses
0
endpoint_id"acf82778-f331-40d9-ad3f-8c57494d4c4b"
id"21546512bf7b4d76ae3f59c48abd88c6"
is_byokfalse
latency3492
model_permaslug"minimax/minimax-m2.5-20260211"
provider_name"AtlasCloud"
status200
api_type"completions"
id"gen-1771503762-nWkcFVxH8TuYmrpZvXiI"
upstream_id"21546512bf7b4d76ae3f59c48abd88c6"
total_cost0.00485466
cache_discount0.00110484
upstream_inference_cost0
provider_name"AtlasCloud"

Evaluation details

Result Evaluator Details Meta Data
0.00% Adverbs in dialogue tags
Target: ≤10% dialogue tags with adverbs
totalTags27
adverbTagCount10
adverbTags
0"She gestured vaguely [vaguely]"
1"Marcus looked around [around]"
2"she said carefully [carefully]"
3"Marcus said eventually [eventually]"
4"he said slowly [slowly]"
5"he said quietly [quietly]"
6"Her voice cracked just [just]"
7"The lie tasted like [like]"
8"He stood too [too]"
9"He smiled just [just]"
dialogueSentences86
tagDensity0.314
leniency0.628
rawRatio0.37
effectiveRatio0.233
75.61% AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount1640
totalAiIsmAdverbs8
found
0
adverb"suddenly"
count2
1
adverb"completely"
count1
2
adverb"slightly"
count2
3
adverb"carefully"
count1
4
adverb"slowly"
count2
highlights
0"suddenly"
1"completely"
2"slightly"
3"carefully"
4"slowly"
80.00% AI-ism character names
Target: 0 AI-default names (16 tracked, −20% each)
codexExemptions
0"Blackwood"
found
0"Marcus"
100.00% AI-ism location names
Target: 0 AI-default location names (33 tracked, −20% each)
codexExemptions(empty)
found(empty)
69.51% AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount1640
totalAiIsms10
found
0
word"familiar"
count2
1
word"eyebrow"
count1
2
word"glinting"
count1
3
word"absolutely"
count1
4
word"weight"
count1
5
word"silence"
count2
6
word"warmth"
count1
7
word"flicker"
count1
highlights
0"familiar"
1"eyebrow"
2"glinting"
3"absolutely"
4"weight"
5"silence"
6"warmth"
7"flicker"
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
narrationSentences97
matches(empty)
69.22% Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount3
hedgeCount2
narrationSentences97
filterMatches
0"feel"
hedgeMatches
0"managed to"
1"seemed to"
100.00% Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences155
gibberishSentences0
adjustedGibberishSentences0
longSentenceCount0
runOnParagraphCount0
giantParagraphCount0
wordSaladCount0
repetitionLoopCount0
controlTokenCount0
maxSentenceWordsSeen47
ratio0
matches(empty)
100.00% Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans0
markdownWords0
totalWords1630
ratio0
matches(empty)
100.00% Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions19
unquotedAttributions1
matches
0"Outside, London continued its eternal spin, millions of lives intersecting and diverging, people finding each other and …"
83.33% Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions35
wordCount1094
uniqueNames9
maxNameDensity0.82
worstName"Aurora"
maxWindowNameDensity2.5
worstWindowName"Marcus"
discoveredNames
Aurora9
Silas8
Cardiff1
Old2
Signal1
Soho1
Marcus8
London2
Let3
persons
0"Aurora"
1"Silas"
2"Marcus"
places
0"Cardiff"
1"Old"
2"Soho"
3"London"
globalScore1
windowScore0.833
71.88% Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences64
glossingSentenceCount2
matches
0"ed again, more visibly this time, and some"
1"tasted like copper in her mouth"
100.00% "Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches0
per1kWords0
wordCount1630
matches(empty)
100.00% Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount1
totalSentences155
matches
0"stayed that way"
100.00% Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs84
mean19.4
std17.06
cv0.879
sampleLengths
063
115
240
33
435
514
616
742
88
916
1022
115
1225
1346
1436
152
1629
172
1813
1921
2016
212
222
2324
2416
251
2611
2722
2816
2921
301
317
3241
3330
342
354
3639
3735
383
3911
4064
417
421
4330
4410
452
465
4754
4820
496
94.41% Passive voice overuse
Target: ≤2% passive sentences
passiveCount3
totalSentences97
matches
0"being asked"
1"been bombed"
2"was supposed"
100.00% Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount0
totalVerbs200
matches(empty)
100.00% Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount1
semicolonCount0
flaggedSentences1
totalSentences155
ratio0.006
matches
0"The careful mask cracked, just for a moment, and she caught a glimpse of the boy underneath—the one who'd held her hair back when she was sick, who'd read her poetry when she couldn't sleep, who'd promised they'd always be friends no matter what."
90.37% Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount1098
adjectiveStacks0
stackExamples(empty)
adverbCount56
adverbRatio0.051001821493624776
lyAdverbCount17
lyAdverbRatio0.015482695810564663
100.00% Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences155
echoCount0
echoWords(empty)
100.00% Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences155
mean10.52
std8.89
cv0.846
sampleLengths
09
127
227
315
47
512
66
715
81
92
1021
113
1211
1314
142
1513
161
1742
183
195
207
212
227
232
245
253
2612
275
2825
298
309
3129
3226
3310
342
3519
366
374
382
395
408
416
425
4310
4416
452
462
4715
489
493
52.26% Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats14
diversityRatio0.36774193548387096
totalSentences155
uniqueOpeners57
81.30% Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount2
totalSentences82
matches
0"Then their gaze met across"
1"Somewhere in the back room,"
ratio0.024
88.29% Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount27
totalSentences82
matches
0"She hadn't touched the drink"
1"She was about to leave"
2"He crossed the distance between"
3"She gestured vaguely at the"
4"He settled onto the barstool"
5"He flagged down Silas"
6"She gave a tiny nod."
7"She took a sip of"
8"He flinched slightly."
9"He stopped, glanced away"
10"she said carefully"
11"She considered lying."
12"It would be easy, given"
13"She stopped, restarted"
14"he said slowly"
15"He stopped, laughed, ran a"
16"She finished her whiskey, set"
17"He flinched again, more visibly"
18"he said quietly"
19"She stood, pulled her jacket"
ratio0.329
45.37% Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount68
totalSentences82
matches
0"The ice in Aurora's glass"
1"She hadn't touched the drink"
2"The familiar rhythm of their"
3"She was about to leave"
4"The years had sharpened someone's"
5"The hair was different, shorter,"
6"The shock must have shown"
7"The same hesitation."
8"The same uncertainty he'd always"
9"The name came out like"
10"The bar stool scraped against"
11"He crossed the distance between"
12"The same laugh, at least."
13"That hadn't changed."
14"The words landed somewhere between"
15"Aurora Signal for another drink,"
16"She gestured vaguely at the"
17"Marcus looked around properly now,"
18"He settled onto the barstool"
19"He flagged down Silas"
ratio0.829
0.00% Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount0
totalSentences82
matches(empty)
ratio0
100.00% Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences35
technicalSentenceCount2
matches
0"The familiar rhythm of their voices blended with the low jazz piping through the speakers, creating the kind of background noise that made solitude feel like co…"
1"On the wall behind Marcus, an old photograph showed a London that didn't exist anymore, trams and bowler hats and streets that had been bombed and rebuilt into …"
100.00% Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags27
uselessAdditionCount0
matches(empty)
100.00% Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags10
fancyCount1
fancyTags
0"he breathed (breathe)"
dialogueSentences86
tagDensity0.116
leniency0.233
rawRatio0.1
effectiveRatio0.023
83.3851%