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 terminology-consistency-checkergit 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/terminology-consistency-checker)<a href="https://agentmods.dev/skills/ur-grue/autopunk-media-skills/terminology-consistency-checker"><img src="https://agentmods.dev/badge/skills/ur-grue/autopunk-media-skills/terminology-consistency-checker/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/terminology-consistency-checker"><img src="https://agentmods.dev/badge/skills/ur-grue/autopunk-media-skills/terminology-consistency-checker.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 | $0.00035 | $0.01658 |
| Opus 5 | $0.00017 | $0.00829 |
| Sonnet 5 | $0.00007 | $0.00332 |
| Haiku 4.5 | $0.00003 | $0.00166 |
Grade A, and why
terminology-consistency-checker 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 8d 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 — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Terminology Consistency Checker
What This Skill Does
Scans a text for inconsistent use of key terms, names, titles, and technical vocabulary, then produces a flagged report with recommended corrections.
When To Use This Skill
- Before submitting a long-form article, feature, or investigation for publication
- When multiple writers or sources have contributed to a single piece and terminology may have drifted
- When an editor wants to enforce a house style or field-specific vocabulary standard (e.g., medical, legal, financial)
- When revisiting a draft after a long break and suspect terms have been used interchangeably
What You Need To Provide
Required: The full text to be checked. Optional: A preferred terminology list or house style glossary (e.g., "use 'climate change' not 'global warming'"); names of people or organisations whose styling should be standardised; target publication and its style guide (AP, Guardian, Chicago, etc.).
How the Assistant Approaches This
- Reads the full text and builds an internal inventory of every significant term, name, title, and proper noun it encounters — including all spelling variants and capitalisations.
- Compares each term across its occurrences, flagging pairs or groups where the same referent is expressed differently (e.g., "the Minister" vs. "the minister" vs. "Minister Chen"; "AI" vs. "A.I." vs. "artificial intelligence" used interchangeably).
- Produces a structured report: one entry per inconsistency, showing every variant found, the line-level location (quoted context), and a recommended single form to adopt throughout — with a brief reason where the choice isn't obvious.
Output Format
A structured flagged report, organised into sections by type of inconsistency (names and titles / technical terms / abbreviations and acronyms / capitalisation). Each entry includes: the variants found, quoted context showing where each appears, the recommended standard form, and a one-line rationale. Closes with a summary count of total flags. Tone is editorial and precise — written for a copy editor, not a general reader. Length scales with the number of issues found; a clean text returns a short confirmation with zero flags.
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.
- 8d ago First seen · 132 lines · 35 tokens per session scan A 4d0380867e6a
terminology-consistency-checker is a skill published in the GitHub repository ur-grue/autopunk-media-skills (32 stars, last pushed 12d ago), licensed MIT. It adds 35 tokens to every session and 1,658 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
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…
voice-update
Update context/voice-and-style.md or context/about-me.md from one of three sources. Manual (user dictates a single new rule, sample, or career fact). Memory (batch pull from Claude Code's auto-memory in /.claude/projects/ /memory/). Sent-mail (analyze the last 20-50 sent Gmail messages and propose updates from…
yourself-story
Drafts and critiques bios, LinkedIn About sections, intro slides, "tell me about yourself" interview answers, and personal-essay openers using Adam Bryant's 500-CEO research and Lauren Weinstein's warmth+competence frame. Different from pitch-coach (which is product-shaped) and cold-email-coach (which is…
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…