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-harmonizergit 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-harmonizer)<a href="https://agentmods.dev/skills/ur-grue/autopunk-media-skills/multi-author-harmonizer"><img src="https://agentmods.dev/badge/skills/ur-grue/autopunk-media-skills/multi-author-harmonizer/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-harmonizer"><img src="https://agentmods.dev/badge/skills/ur-grue/autopunk-media-skills/multi-author-harmonizer.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 | $0.00047 | $0.02507 |
| Opus 5 | $0.00023 | $0.01254 |
| Sonnet 5 | $0.00009 | $0.00501 |
| Haiku 4.5 | $0.00005 | $0.00251 |
Grade A, and why
multi-author-harmonizer 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 — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Multi-Author Harmonizer
What This Skill Does
Reviews a text written or assembled by multiple authors and produces a detailed inconsistency report — flagging voice shifts, terminology mismatches, tonal clashes, and formatting discrepancies — with specific harmonisation recommendations for each.
When To Use This Skill
- Multiple reporters contributed sections to a single article or special report and the result reads like a patchwork
- A roundtable, panel response, or collaborative opinion piece needs to read as one coherent document
- An editor has merged content from different writers into a single feature and needs to identify where the seams show
- A publication's annual report, special issue, or series compilation needs voice consistency across contributor sections
What You Need To Provide
Required: The full combined text, with sections attributed to different authors if possible (e.g., "Section 1 by Author A, Section 2 by Author B"). If author boundaries are unknown, the skill will attempt to detect voice shifts.
Optional: The target voice or style to harmonise toward (e.g., "match the tone of Section 1," "align to our house style," or "aim for formal analytical register"); the publication type; any specific concerns (e.g., "the middle section feels more casual than the rest").
How the Assistant Approaches This
-
Profiles each voice. Reads the full text and identifies distinct stylistic signatures: sentence length patterns, formality level, use of first person vs. third person, degree of hedging, attribution style, punctuation habits (em dashes, semicolons, parentheticals), and vocabulary register. If author boundaries are labelled, profiles each author's section. If not, identifies where the voice shifts.
-
Flags inconsistencies. Produces a categorised list of discrepancies:
- Terminology mismatches — the same concept called different things in different sections (e.g., "participants" in one section, "subjects" in another, "respondents" in a third)
- Tone shifts — passages that are noticeably more formal, casual, academic, or conversational than the surrounding text
- Structural format differences — one section uses subheadings while another does not; one uses bullet points while another uses running prose; attribution styles differ
- Register clashes — mixing of registers within the same piece (e.g., academic hedging in one section alongside assertive opinion-writing in another)
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.
- 7d ago First seen · 142 lines · 47 tokens per session scan A a65c1a26ce01
multi-author-harmonizer is a skill published in the GitHub repository ur-grue/autopunk-media-skills (30 stars, last pushed 11d ago), licensed MIT. It adds 47 tokens to every session and 2,507 once invoked, about $0.0002 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 2026-09-04.
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…
anti-slop
Eliminate AI-sounding patterns from any written output. Applies editorial rules synthesized from the best open-source anti-slop tools: banned phrases, structural pattern detection, false agency checks, and a scoring rubric. Use as a quality gate for ANY content — blog posts, social media, emails, documentation…
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…