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 ur-grue/autopunk-media-skills --skill multi-author-harmonisergit clone --depth 1 https://github.com/ur-grue/autopunk-media-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/ur-grue/autopunk-media-skills/multi-author-harmoniser)<a href="https://agentmods.dev/skills/ur-grue/autopunk-media-skills/multi-author-harmoniser"><img src="https://agentmods.dev/badge/skills/ur-grue/autopunk-media-skills/multi-author-harmoniser/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/ur-grue/autopunk-media-skills/multi-author-harmoniser"><img src="https://agentmods.dev/badge/skills/ur-grue/autopunk-media-skills/multi-author-harmoniser.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00051 | $0.01525 |
| Opus 5.5 | $0.00020 | $0.00610 |
| Sonnet 5.5 | $0.00010 | $0.00305 |
| Haiku 4.5 | $0.00005 | $0.00153 |
Grade A, and why
multi-author-harmoniser 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 1mo 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Multi-Author Harmoniser
What This Skill Does
Takes a draft written by two or more contributors and rewrites it as a single, consistent voice — smoothing over clashing tones, register shifts, and stylistic inconsistencies while preserving every author's factual content and reported material.
When To Use This Skill
- When two reporters have jointly written a news feature and their sections read noticeably differently
- When a freelance contribution has been stitched into a staff-written piece and the seams are visible
- When a multi-part investigation has been written by different team members over several months
- When translated content from different translators has been combined into one article
- Before a long-form piece goes to a senior editor and the multiple-author origin would be obvious
What You Need To Provide
Required: The full draft text to be harmonised. Optional: A target house style or reference publication (e.g., "write in the style of a quality broadsheet news feature — authoritative, direct, no first person"); the preferred tense (past or present); whether to preserve each author's section roughly intact or allow restructuring for flow; any passages that must not be changed (confirmed quotes, legal-approved text, translated sections).
How the Assistant Approaches This
- Reads the full draft and maps the stylistic variation: identifies shifts in sentence length, vocabulary register, use of first or second person, punctuation habits, tonal warmth or distance, and paragraph structure — noting roughly where each style shift occurs.
- Establishes a target voice for the harmonised version, either from explicit instructions provided, or — if none are given — by averaging toward the more formal or more consistent of the styles present in the draft.
- Rewrites the full text in the target voice, preserving all factual claims, quotes, and reported information. Where restructuring would help flow, it does so conservatively — keeping the original sequencing unless a clear improvement is available. Returns the harmonised draft in full, followed by a brief editor's note listing the main changes made and any passages that were left as-is (e.g., direct quotes, confirmed legally approved text).
What ships with it
1 file 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.
- 1mo ago First seen · 84 lines · 51 tokens per session scan A 6e3d6762ed7d
multi-author-harmoniser is a skill published in the GitHub repository ur-grue/autopunk-media-skills (38 stars, last pushed 1mo ago), licensed MIT. It adds 51 tokens to every session and 1,525 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-08-30.
Other skills, from other repositories
cinematic-script-writer
Create professional cinematic scripts for AI video generation with character consistency and cinematography knowledge. Use when the user wants to write a cinematic script, create story contexts with characters, generate image prompts for AI video tools (Midjourney, Sora, Veo), or needs cinematography guidance (camera…
design-dna
Use when a design has won and its look must survive: codify it into a permanent style skill with measured ratios, bans and tests that can fail, then build new pieces in that exact look. Fires on 'turn this into a skill', 'keep the same style', 'my output drifted'. NOT finding the winner (that is design-loop), NOT the…
amazon-alexa
Integracao completa com Amazon Alexa para criar skills de voz inteligentes, transformar Alexa em assistente com Claude como cerebro (projeto Auri) e integrar com AWS ecosystem (Lambda, DynamoDB, Polly, Transcribe, Lex, Smart Home).
brand
Use when brand voice, visual identity, messaging frameworks, asset management, brand consistency. Activate for branded content, tone of voice, marketing assets, brand compliance, style guides.
ai-media
Use when generating AI media, avatar videos, AI marketing videos with Google Flow, producing AI podcasts, product photography, social media content, voice cloning, photo books, or editing videos with editorial judgment, clip selection, B-roll sourcing, motion direction and standalone story-driven motion films.
compression
Cuts a draft to a target word count without losing substance. Two modes behind one skill. target-count hits a specific number (200 for a cold email, 500 for an op-ed, 6 for a product summary). redundancy catches the specific failure where a phrase says what the verb or context already implied — "going forward" after a…