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 version-comparatorgit 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/version-comparator)<a href="https://agentmods.dev/skills/ur-grue/autopunk-media-skills/version-comparator"><img src="https://agentmods.dev/badge/skills/ur-grue/autopunk-media-skills/version-comparator/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/version-comparator"><img src="https://agentmods.dev/badge/skills/ur-grue/autopunk-media-skills/version-comparator.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 | $0.00050 | $0.02344 |
| Opus 5.5 | $0.00020 | $0.00938 |
| Sonnet 5.5 | $0.00010 | $0.00469 |
| Haiku 4.5 | $0.00005 | $0.00234 |
Grade A, and why
version-comparator 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 — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Version Comparator
What This Skill Does
Compares two versions of an article and produces a structured change report — highlighting substantive edits, additions, deletions, and tone shifts — so the editor or writer can quickly understand what changed and assess whether the revisions improved the piece.
When To Use This Skill
- A writer has submitted a revised draft and you need to see what actually changed before approving it
- You want to compare your own first and second drafts to track your revision patterns
- An article has been through an editorial pass and you want to verify that no meaning was altered unintentionally
- Legal or compliance review requires documentation of what changed between versions
What You Need To Provide
Required: Version A (the earlier draft) and Version B (the later draft), clearly labelled.
Optional: The type of comparison you want (substantive changes only, all changes including minor wording, or a specific focus such as "check whether any factual claims were altered"); any context about what the revision was supposed to address (e.g., "the editor asked for a stronger opening and shorter middle section").
How the Assistant Approaches This
-
Aligns the two versions. Maps Version A paragraphs to their corresponding paragraphs in Version B, accounting for reordering, merging, splitting, and deletion. Identifies new paragraphs in Version B that have no counterpart in Version A.
-
Classifies every change. Categorises each difference into one of five types:
- Substantive edit — meaning, emphasis, or factual content was changed
- Addition — new material not present in Version A
- Deletion — material from Version A removed in Version B
- Reordering — content moved to a different position
- Cosmetic edit — wording changed but meaning preserved (tightening, style adjustment, grammar fix)
-
Assesses impact. For substantive edits, additions, and deletions, notes whether the change strengthens, weakens, or neutrally alters the piece. This assessment is brief and specific — not a general opinion but a targeted observation (e.g., "Removing the third source weakens the evidence base for the central claim").
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 · 154 lines · 50 tokens per session scan A f4209a407b3a
version-comparator is a skill published in the GitHub repository ur-grue/autopunk-media-skills (38 stars, last pushed 1mo ago), licensed MIT. It adds 50 tokens to every session and 2,344 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 2026-09-04.
Other skills, from other repositories
klauselinhalt-und-verbote-pruefen
Prüft eine AGB-Klausel anhand von Kontrollfähigkeit, gesetzlichen Klauselverboten und Interessenabwägung. Für B2C und B2B; liefert ein Klauselvotum mit Leitbild, Gegenposition und konkreter Rechtsfolge.
write-outreach-outreach-qa
Step of the write-outreach playbook: the checks a finished outreach pack and send file must pass before delivery, covering facts, proof, compliance, length, asks and tone. Run write-outreach instead; not for direct use.
delay-analysis
Analyze construction schedule delays for claims and recovery. Perform time impact analysis, identify delay causes, calculate damages, and document for disputes.
wcag
Expert WCAG (Web Content Accessibility Guidelines) advisor covering WCAG 2.0, 2.1, and 2.2 — the W3C international accessibility standards. Use this skill whenever a user asks about WCAG success criteria, conformance levels (A/AA/AAA), accessibility audits, POUR principles, accessibility statements, ARIA patterns…
compliance-checker
Audits a codebase or business process for regulatory compliance across GDPR, HIPAA, SOC2, CCPA, and PCI-DSS. Scans for PII handling, data retention, encryption, access controls, audit logging, consent management, and data transfer issues. Generates a structured compliance report with findings, gap analysis…
cease-desist-bossmann007
Draft uma notificação extrajudicial (modo envio) ou faça a triagem de uma recebida (modo recebimento). Use para fazer valer direitos contra um infrator com carta de cobrança calibrada à postura de enforcement, ou quando uma notificação recebida precisa virar memorando estruturado de opções com recomendação.