Etincel

___ ___ ___ ___ ___ ___ /\ \ /\ \ ___ /\__\ /\ \ /\ \ /\__\ /::\ \ \:\ \ /\ \ /::| | /::\ \ /::\ \ /:/ / /:/\:\ \ \:\ \ \:\ \ /:|:| | /:/\:\ \ /:/\:\ \ /:/ / /::\~\:\ \ /::\ \ /::\__\ /:/|:| |__ /:/ \:\ \ /::\~\:\ \ /:/ / /:/\:\ \:\__\ /:/\:\__\ __/:/\/__/ /:/ |:| /\__\ /:/__/ \:\__\ /:/\:\ \:\__\ /:/__/ \:\~\:\ \/__/ /:/ \/__/ /\/:/ / \/__|:|/:/ / \:\ \ \/__/ \:\~\:\ \/__/ \:\ \ \:\ \:\__\ /:/ / \::/__/ |:/:/ / \:\ \ \:\ \:\__\ \:\ \ \:\ \/__/ \/__/ \:\__\ |::/ / \:\ \ \:\ \/__/ \:\ \ \:\__\ \/__/ /:/ / \:\__\ \:\__\ \:\__\ \/__/ \/__/ \/__/ \/__/ \/__/

Find the AI tells in your prose. Deterministically, locally, in CI.

No install, no account, no model call, no network.

$ npx etincel lint drafts/announcement.md --register blog ✗ drafts/announcement.md RED 100/100 (8 findings, 169 words, register: blog) Heavy AI styling. Multiple strong tells stacking up, worth a structural rewrite, not a word-swap pass. Whole-piece rhythm medium uniform-paragraph-length 6 paragraphs, most running about the same length with little variation between them. Vary paragraph length more. medium low-burstiness 13 sentences averaging 13 words, with little variation in length from one sentence to the next. Mix short sentences with long; allow fragments. medium mechanical-register-drift Fragment rate and structural variety (sentence openers, punctuation mix) sit off where blog prose typically lands. Allow more sentence fragments and vary openers/punctuation more. Vocabulary and phrasing high comprehensive L3:C30 → thorough, complete high cutting-edge L3:C109 → newest, latest high leverage L3:C99 → use high seamless L3:C150 → smooth, easy high streamline L3:C70 → simplify, speed up strengths specificity 11.4/1k · concrete:abstract 0.40 · burstiness 0.32 1 file audited, 1 at or above orange.

Étincel is two things. Adeterministic auditthat finds the patterns making prose read as machine-written, as a CLI, a GitHub Action, and an MCP tool. And avoice layerthat trains Claude, Cursor, or any MCP client to draft in a style measured from your own writing, so the problem is smaller before you ever read the draft.

AI-drafted prose has a recognizable shape: uniform paragraphs, hedged authority, em dashes where a comma would do, closings that resolve too neatly. Étincel encodes the rules against that shape and, just as important, shows you what it found and why instead of quietly overwriting your voice. There is no model call anywhere in the audit path, and you decide what changes. You stay the author.

We measure it rather than assert it. Pooled AUC per register, measured byassayagainst labeled corpora with a fixed bootstrap seed, so any PR that drops these numbers fails CI:

Email is close to a coin flip. It's deliberately uncalibrated, and we track it anyway so an accidental regression doesn't go unnoticed.generalis uncalibrated too. The calibrated registers aredocs,blog,memo, andessay; use those if the number matters to you. Seeefficacy-baselines.jsonandsrc/data/SOURCES.mdfor method and provenance.

vs.Vale+vale-ai-tellsVale is an excellent markup-aware linter and vale-ai-tells is a serious 78-rule package. They match tokens against patterns. Étincel measures shape: sentence-rhythm variance, paragraph-length uniformity, and repetition against your own previous drafts, the kind of statistical layer vale-ai-tells' own README says needs analysis beyond what token matching can do. Étincel also feeds a trained voice to the model before you draft, which no linter does. Running both is reasonable; they overlap less than you'd expect.

Also listed on theofficial MCP registryasai.etincel/etincel-nonfiction, so MCP-aware clients that auto-discover servers from there (VS Code's@mcpgallery, for one) find it without any of the config below.

/plugin marketplace add AIStoryHub/etincel /plugin install etincel-nonfiction

{ "mcpServers": { "etincel-nonfiction": { "command": "npx", "args": ["etincel", "serve"] } } }

From a local clone instead:npm install && npm run build, then pointargsat["/path/to/etincel/dist/server.js"]with"command": "node".

A hosted version is also available atetincel.ai, exposing the same tools over Streamable HTTP (https://etincel.ai/api/mcp) with per-account auth instead of stdio. Point any MCP client at it directly:

{ "mcpServers": { "etincel-nonfiction": { "url": "https://etincel.ai/api/mcp" } } }

Train a style called "me" from these three emails I wrote: [paste samples]

Then either name it per-request ("write this in my voice") or set it as default:

Twelve premade presets ship out of the box: six emotional tones (Direct & Warm, Executive Brief, Reflective Essayist, Founder Memo, Plainspoken Analyst, Wry & Candid) plus six use-case presets (PR Review, Code Comment, Slack Message, LinkedIn Post, Website Copy, Blog Post). Each carries formality/warmth/directness dials plus a sentence-rhythm and voice description that gets fed to the model as drafting context, not a template that fills in blanks. The server reads these fromsrc/data/presets.json. Fork any preset into a trained voice withfork_styleto make it your own.

audit_textis a pure function under the hood, so it also ships as a CLI, for linting prose outside a chat client (READMEs, docs, PR descriptions in CI):

npx etincel lint 'docs//.md' npx etincel lint README.md --register docs --threshold yellow

- uses: AIStoryHub/etincel@main with: patterns: "docs//.md README.md" threshold: orange

Repo-local config: dictionary, instructions, and a shared team style

A team's rules don't have to live only in each person's local~/.etincel/. Drop a.etincelrc(or.etincelrc.json/etincel.config.json) at the repo root and it's picked up automatically by the CLI and by the local (stdio) server, reviewable in code review and versioned instead of invisible and gone when someone leaves:

{ "bannedWords": ["Acme Cloud Platform"], "allowedWords": ["leverage"], "register": "docs", "threshold": "orange", "instructions": "Always include a one-line CTA at the end.", "style": { "name": "House Voice", "dials": { "formality": 6, "warmth": 4, "directness": 7, "sentenceLength": 40, "sentenceRhythmVariance": 50, "paragraphVariance": 30, "contractionUse": 20, "emDashUse": 0, "fragmentTolerance": 10, "questionUse": 5, "entropy": 60 } } }

- bannedWords/allowedWordsmerge alongside whatever's in your account/style dictionary;register/thresholdact as repo-wide defaults that an explicit--register/--thresholdflag still overrides.
- instructionsis free text, folded intoget_style_guide'sinstructionsforeverystyle, not just the team one, ahead of your own account-level global instructions: the team-wide equivalent ofset_style_instructionswith nostyleId, but committed to the repo instead of living in one person's account.
- styledefines a shared "house voice" from dials, addressable everywhere asstyleId: "team"(get_style_guide, and once forked into a real trained voice withfork_style, everywhere else too) so a team has one already-tuned starting voice from day one instead of everyone hand-training or hand-tuning their own from scratch.list_stylesincludes it automatically when a.etincelrcin the current repo defines one.

The hosted server doesn't use any of this (it has no local repo to look in).

Sharing config across a team without committing it

.etincelrcis the versioned, code-reviewable layer above; the layer beneath it isETINCEL_HOME, an environment variable that points the local (stdio) server and CLI at a directory to use instead of the default~/.etincel/. Point every teammate'sETINCEL_HOMEat the same shared, synced, or mounted directory (a repo-external path everyone's machine can read, e.g. something synced by your usual file-sharing setup) and trained voices, the default style, and account-level instructions/dictionaries are shared too, not just the.etincelrc-committed subset:

{ "mcpServers": { "etincel-nonfiction": { "command": "node", "args": ["/path/to/etincel/dist/server.js"], "env": { "ETINCEL_HOME": "/path/to/shared/etincel-home" } } } }

Nothing else to export or import: pointingETINCEL_HOMEat the same directoryisthe sync, the same way it already is for a single person's~/.etincel/.

- An MCP server(src/server.ts) exposing twenty tools:

- list_styles: premade tone presets, any voices you've trained, and (if a repo-local.etincelrcdefines one) a shared team style
- get_style_guide: the drafting instructions for one style
- train_style: learn a voice from your own writing samples (sentence rhythm, contraction rate, em-dash habits, paragraph variance, recurring phrasing: measured, not guessed)
- create_style_from_dials: build a style from explicit formality/warmth/directness and mechanical dials instead of samples
- update_style: rename a trained voice or adjust its dials in place
- fork_style: copy a preset's dials and guide into a new trained voice you can retrain or hand-tune, or fork another installer's style once they've published it publicly on the hosted gallery (addressed ashandle/slug, e.g.jpleblanc/blunt-memo, the same address shown on its public page atetincel.ai/v/handle/slug); a public-style fork also carries over its mechanical dials and any dictionary/instructions the source installer set specifically for that style (never their private, account-wide ones), and makes one network call toetincel.aito fetch it, while a preset fork never leaves this install
- delete_style: permanently remove a trained voice
- set_default_style: remember which style to use without repeating yourself
- check_voice_match: compare a draft's measured rhythm against a trained voice's baseline. A rhythm/mechanics check, not an authorship or AI-detection check, and low-confidence on short input
- check_self_repetition: compare a draft against a voice's own recent training samples for habits, not AI tells: the same opener, or a phrase, recurring across several past pieces ("you've opened this way in 4 of your last 6 pieces"). Local install only for now
- audit_text: a deterministic, rules-based scan for AI tells, returning a tier, specific findings with severity, and a strengths signal (specificity, concrete-vs-abstract ratio, sentence-rhythm variation) so fixes don't flatten the prose. Takes an optionalregister(email/blog/memo/essay/social/docs/general/personal, defaultgeneral) to calibrate strictness against the kind of text it is:docssuppresses Markdown-structure false positives (headings, bolded terms) and recalibrates rhythm/vocabulary detection against long-form reference prose instead of punchier short-form copy.personalis scaffolded (accepted, suppresses nothing extra yet) but not yet calibrated: no term suppressions, rhythm weight, or labeled corpus of its own until one is measured. Also takes an optionalsourceFacts(details elicited from the user, never generated): checks how many actually made it into the draft, flaggingelicited-material-unusedbelow a quota of two used and at least one in a sentence that isn't proving a qualification
- second_read: a single model call that reads a draft and reports what a careful human editor would notice, unscored and untiered, never a rewrite. Hosted only: this install always fails with a clear explanation, since a model call needs an account, a pinned model, and a billing surface this install doesn't have.audit_textremains fully available, no account needed
- add_banned_word/remove_banned_word: maintain your own banned-vocabulary list, checked byaudit_textalongside the built-in corpus
- add_custom_word/remove_custom_word: maintain a "never flag this" list: an org's own acronyms or house terms, the corporate-dictionary case
- list_dictionary: see a scope's banned/custom words, and (for a style) what actually applies once merged with the global list
- set_style_instructions/clear_style_instructions/get_style_instructions: save, remove, or read free-text drafting rules for a scope (required elements, forbidden topics, format constraints), merged intoget_style_guidethe same way dictionaries merge intoaudit_text

Trained voices, dictionaries, and your default style live locally in~/.etincel/: nothing is sent anywhere.audit_textis plain deterministic code (string analysis + a curated corpus of AI-writing tells), not a model call. The one exception is forking apublicstyle viafork_style, which fetches (never sends) that style's guide frometincel.ai's public gallery; forking a preset, or anything else in this list, still touches the network not at all.

Beyond the built-in AI-tell corpus, you can maintain your own banned and "always allowed" word lists: just tell Claude (or any MCP client) things like "add[word]to my banned words list" or "add[word]to my custom words list, it's one of ours." Each list lives at ascope:global(applies everywhere, the default when no style is named) or a specific style id, whose list is merged on top ofglobalwhen you audit against that style.list_dictionaryshows what's saved for a scope, plus the effective merged list for a style. Editing the global list is already the way to keep a word in sync across every style: it's merged in automatically, live, every timeaudit_textorlist_dictionaryruns.

npm install npm test # run the engine/tools test suite (node:test via tsx) npm run dev # run the MCP server over stdio via tsx, for local testing npm run build # compile to dist/

The mcpscore badge audits the hosted remote server (etincel.ai/api/mcp), not the local/stdio engine in this repo; the two expose the same tools but run as separate deployments.

- The audit corpus insrc/data/is a curated subset, not exhaustive. Seesrc/data/SOURCES.mdfor provenance and what isn't ported yet. The full corpus is ataistoryhub.co/corpus.
- email(AUC 0.540) andgeneral(0.748) are uncalibrated.socialhas no labeled corpus at all and isn't tracked.
- check_voice_matchis a rhythm-and-mechanics check, not authorship detection, and it's low-confidence on short input.
- check_self_repetitionis local-install only for now.
- AI tells are a moving target: OpenAI patched ChatGPT's em-dash habit in November 2025. That's why efficacy is measured rather than claimed: when a tell stops being a tell, the AUC moves and the regression check catches it.

Sync Calendars, Scheduling Links, AI Executive Scheduling Assistant, Unified Calendar