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 jargon-flaggergit 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/jargon-flagger)<a href="https://agentmods.dev/skills/ur-grue/autopunk-media-skills/jargon-flagger"><img src="https://agentmods.dev/badge/skills/ur-grue/autopunk-media-skills/jargon-flagger/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/jargon-flagger"><img src="https://agentmods.dev/badge/skills/ur-grue/autopunk-media-skills/jargon-flagger.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 | $0.00044 | $0.02233 |
| Opus 5 | $0.00022 | $0.01117 |
| Sonnet 5 | $0.00009 | $0.00447 |
| Haiku 4.5 | $0.00004 | $0.00223 |
Grade A, and why
jargon-flagger 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 — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Jargon Flagger
What This Skill Does
Scans a draft and flags every instance of technical jargon, unexplained acronyms, and insider language that a general-audience reader would not understand — with a plain-language alternative for each.
When To Use This Skill
- You are editing a piece written by a subject-matter expert and need to check it for accessibility before publication
- A draft covers a technical topic (finance, medicine, law, technology, policy) and is aimed at a general readership
- You want to verify that a piece meets plain-language standards before sending it to an editor
- You are adapting a specialist report or press release into a consumer-facing article
What You Need To Provide
Required: The draft text to be reviewed.
Optional: The target audience's assumed knowledge level (e.g., "general newspaper reader," "informed but non-specialist," "industry audience who knows the basics"); the subject domain (helps calibrate what counts as jargon vs. common knowledge in that field); any terms you have already decided to keep and do not want flagged.
How the Assistant Approaches This
-
Establishes the knowledge baseline. Determines what a reader of the stated audience would reasonably be expected to understand. For a general newspaper reader, terms like "GDP" or "DNA" are assumed known; "quantitative easing" or "epigenetics" are not. For an informed-but-non-specialist audience, the threshold is higher. If no audience is specified, defaults to a general magazine reader.
-
Scans for three categories. Flags items in three tiers:
- Jargon — technical terms from a specific field used without definition (e.g., "amortisation," "comorbidity," "arbitrage")
- Unexplained acronyms — acronyms used before being spelled out, or never spelled out at all (e.g., "EBITDA," "RCT," "FOIA")
- Insider language — phrases that are not technically jargon but assume familiarity with a specific world (e.g., "above the fold," "the C-suite," "discovery phase")
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 · 158 lines · 44 tokens per session scan A 870ea08d35f7
jargon-flagger is a skill published in the GitHub repository ur-grue/autopunk-media-skills (30 stars, last pushed 11d ago), licensed MIT. It adds 44 tokens to every session and 2,233 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
clarity-and-concision
Teaches techniques for achieving relentless clarity and ruthless concision in business writing, including the 20-word sentence rule, concrete detail over abstraction, word economy tactics, and the reader's perspective test. Features extensive before/after examples demonstrating how bloated corporate prose can be cut…
dialogue-gym
A dialogue coach that teaches dialogue craft framed by the writer's stated intent and level, sets a targeted drill, has the writer write it, then evaluates and ranks the attempt against dialogue criteria and assigns the next drill. Use it when a writer wants to deliberately improve dialogue — subtext, beats, distinct…
prose-rhythm
A prose-rhythm coach that teaches sentence variety, sound, and cadence framed by the writer's intent and level, sets a drill, has the writer write it, then scores and ranks the attempt against rhythm criteria and assigns the next drill. Use it when a writer wants to tune the music of their prose — sentence length…
concrete-language-rewriter
Rewrite abstract, theoretical, or jargon-heavy passages into sensory, schema-based language the audience can already picture — using three named techniques (schema tap, high-concept pitch, generative analogy). Use this skill whenever a draft sounds abstract, strategy-level, or theoretical and the user wants it…
curse-of-knowledge-detector
Diagnose a draft for the Curse of Knowledge — the expert blind spot that makes insiders write copy full of unexplained jargon, buried assumptions, strategy-level abstractions, and tacit shared context that lose non-expert audiences. Use this skill whenever reviewing a pitch, announcement, explainer, landing page…
accessibility
Audit and improve web accessibility following WCAG 2.2 guidelines. Use when asked to "improve accessibility", "a11y audit", "WCAG compliance", "screen reader support", "keyboard navigation", or "make accessible".