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 humanizegit 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/humanize)<a href="https://agentmods.dev/skills/petar-djukic/writing-skills/humanize"><img src="https://agentmods.dev/badge/skills/petar-djukic/writing-skills/humanize/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/humanize"><img src="https://agentmods.dev/badge/skills/petar-djukic/writing-skills/humanize.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 | $0.00192 | $0.09737 |
| Opus 5 | $0.00096 | $0.04869 |
| Sonnet 5 | $0.00038 | $0.01947 |
| Haiku 4.5 | $0.00019 | $0.00974 |
Grade A, and why
humanize 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 — 757 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Humanize (the laundering chain)
One generative pass over a draft: semantic cleanup, a seeded diction rewrite, word recovery, optional accent, then the deterministic terminal stage. The chain is a pure function — structurally diverged draft in, laundered draft plus a measurement report out. It runs once per invocation. Structure, review, author edits, and the decision to run the chain again belong to the caller (GH-208): a workflow command invokes match-outline before this chain when the form needs changing, runs the read-only instruments after it, and reads this chain's seed-reach report to decide whether another cycle would pay.
The verified effect on a fresh AI draft (2026-07-29, working gate) is 100% AI -> Mixed: 23.8% AI / 76.2% AI-assisted, mean window 0.993 -> 0.576. On well-edited prose the gain is real but small — see the calibration data at the end.
The chain
| stage | what it does | what happens without it |
|---|---|---|
| filter-tells semantic cleanup | collapse antithesis pairs, remove CoT leakage, cut recap ballast, fix banned words | Pangram score stays at 100% AI even after match-voice, because the rhetorical patterns survive diction changes |
| seeded match-voice | one anchored Cohere seed pass, then iterate --no-anchors only while the score falls (GH-194) | unseeded, the rewriter substitutes its own diction instead of stripping the old fingerprint: measured 0.609 gated, against 0.370 seeded, on the same article |
| burstiness (optional) | raises sentence-length variance through the rewrite transport, behind the same gate | CV stays put; on a plain stylometric model dispersion is one of the two discriminative features |
| tighten-style | gives back the words the rewrite costs, through the second model family, without giving back the score | the draft reads leisurely (2,378 -> 2,502 words on the worktrees run) |
| accent-dial (optional) | dials a gated, ranked fraction of EN->SR->EN round-trip edits into structurally clean text | the strongest single Pangram move recorded on strategy-theatre (0.708 -> 0.150) is left on the table |
| inject-vernacular (terminal) | deterministic idiolect operators restore the author's markers; nothing samples | the author's signature constructions stay at machine rates |
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 · -47 lines · +23 tokens per session 64ddf01ee78a
- 12d ago First seen · 804 lines · 169 tokens per session scan A d242f0c2fcb2
humanize is a skill published in the GitHub repository petar-djukic/writing-skills (4 stars, last pushed 8d ago), licensed MIT. It adds 192 tokens to every session and 9,737 once invoked, about $0.0010 per session on Opus 5. 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.