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 | $0.00026 | $0.00763 |
| Sonnet 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 12d 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.
- 12d 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 (30 stars, last pushed 11d ago), licensed MIT. It adds 51 tokens to every session and 1,525 once invoked, about $0.0003 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 2026-08-30.
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…
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…
style-tells
Scrubs the three surface tells that make prose feel AI-generated, padded, or jargon-heavy. Three targets behind one skill, picked via the --target arg. em-dashes (default off in cold email / memo / Slack, max one per page in op-eds), adverbs (the -ly and intensifier pile), jargon (the Silicon Valley / consultant…
vividness
Pushes a draft from abstract toward concrete at two scales. Noun-level (replaces "dog" with "German shepherd," "customer" with "Sarah at JPMorgan's options-trading desk," "many" with "47 of 100") and scene-level (turns "I was angry" into the body signal, room, and dialogue). Implements Kramon's "specific over…
dealing-with-reporters
Drafts and reviews answers to reporter questions, on-the-record statements, crisis-comms responses, and press-inquiry replies. Implements Andrew Ross Sorkin's 11 rules (taught with Kramon at Stanford GSB) plus AP attribution definitions for off-the-record / background / deep background conversations. Use when a…