Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add petar-djukic/writing-skills --skill inject-vernaculargit clone --depth 1 https://github.com/petar-djukic/writing-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/petar-djukic/writing-skills/inject-vernacular)<a href="https://agentmods.dev/skills/petar-djukic/writing-skills/inject-vernacular"><img src="https://agentmods.dev/badge/skills/petar-djukic/writing-skills/inject-vernacular/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/petar-djukic/writing-skills/inject-vernacular"><img src="https://agentmods.dev/badge/skills/petar-djukic/writing-skills/inject-vernacular.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00000 | $0.02340 |
| Opus 5 | $0.00000 | $0.01170 |
| Sonnet 5 | $0.00000 | $0.00468 |
| Haiku 4.5 | $0.00000 | $0.00234 |
Grade A, and why
inject-vernacular scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.
name: inject-vernacular description: >- Terminal, non-generative vernacular stage: apply the deterministic idiolect operators from writing-voice/idiolect.yaml (colon-verdicts, em-dashes, antitheses, connective and hedge swaps, spoken-marker strips, sentence splits) at per-register target rates, plus the substrate calque catalog (zapravo, recimo, ne ide) at site-matched landing spots. Substitution and restoration only — nothing samples, so it may run after every generative stage. Keeps a machine-readable edit log for marker-survival analysis; an optional verifier model judges each edit keep/drop but never writes. Triggers: inject vernacular, terminal stage, idiolect operators, apply my idiolect, restore my markers, vernacular pass.
Inject Vernacular (terminal stage)
Every generative pass regresses text toward the model's distribution center — the Strategy Theatre provenance logs showed match-voice injecting bold lead-ins against instructions, tighten-style inventing a sentence, and a rerun rewriting hand-cleaned prose eight times out of eight. The voice therefore cannot be protected by prompts, and it cannot be restored by another generative pass either. This stage is the answer to the second half: a deterministic operator bank, applied mechanically, as the LAST stage that writes. After it, models read but never write (the humanize pipeline invariant).
What it does
scripts/inject_vernacular.py <draft.md|draft.yaml> discovers
writing-voice/ by walking up from the draft, loads idiolect.yaml, and
applies each marker's operator toward its essay_target (per 1000 words,
±30% tolerance before anything fires — the bank's essay_target_rule).
It refuses to run without the bank: this stage has no defaults, because
the operator bank IS the configuration.
Every edit is a substitution or restoration over text already in the document or a fixed swap from the bank. Nothing samples; nothing is generated. Runs are idempotent — a second pass over its own output makes no edits.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 7d ago Changed · +2 lines e6b4c25cde49
- 12d ago First seen · 164 lines · 0 tokens per session scan A d5dee55629f5
inject-vernacular is a skill published in the GitHub repository petar-djukic/writing-skills (4 stars, last pushed 8d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,340 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
humanizer
Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague…
structural-humanizer
Remove the discourse-level (structural) signs of AI writing that survive surface editing: stated lessons and moral-of-the-story closers, tidy single-track arcs, embodied-emotion performance ("chest tightened"), vague allusions instead of named references, unbroken linear structure, and shape convergence across pieces.…
story-import
A tool for turning an existing novel into a structured writing project. It analyzes the book and organizes its characters, settings, plot plans, chapters, and tracking data for later writing.
story-review
A review workflow for finding story problems from several viewpoints, including issues with structure, characters, wording, and fictional world rules. It can use multiple reviewer agents or work alone.
story-long-analyze
A long-form fiction analysis workflow for breaking down a novel’s opening chapters, characters, pacing, turning points, relationships, and overall structure.
story-deslop
A writing editor for Chinese web novels that detects writing patterns often associated with AI-generated text and makes the prose feel more natural.