Borrowing it
Nothing to install: this file belongs to ur-grue/autopunk-media-skills. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/ur-grue/autopunk-media-skills/main/CLAUDE.mdgit 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/instructions/ur-grue/autopunk-media-skills/claude-md)<a href="https://agentmods.dev/instructions/ur-grue/autopunk-media-skills/claude-md"><img src="https://agentmods.dev/badge/instructions/ur-grue/autopunk-media-skills/claude-md/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/instructions/ur-grue/autopunk-media-skills/claude-md"><img src="https://agentmods.dev/badge/instructions/ur-grue/autopunk-media-skills/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.04869 | $0.04869 |
| Opus 5 | $0.02434 | $0.02434 |
| Sonnet 5 | $0.00974 | $0.00974 |
| Haiku 4.5 | $0.00487 | $0.00487 |
Grade A, and why
autopunk-media-skills CLAUDE.md 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 11d 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 — 424 lines — stays where its author put it; the contents beside it link to each section on GitHub.
autopunk-media-skills
The most comprehensive Claude skill library for media professionals.
GitHub: https://github.com/ur-grue/autopunk-media-skills · License: MIT
What This Project Is
A curated, quality-tested library of Claude skills for journalists, documentary filmmakers, YouTube creators, podcast producers, and visual content creators.
Not a coding library. Every skill helps media professionals produce better content faster — treatments, scripts, headlines, image prompts, show notes, and more.
Target users: Media professionals who may have no technical background. Everything they see must be immediately understandable without reading documentation.
For full vision and roadmap → see ROADMAP.md
For contribution rules → see CONTRIBUTING.md
For skill format → see SKILL_TEMPLATE.md
For testing protocol → see tests/EVAL_FRAMEWORK.md
Language Rule
All repository content is in English. Skills, README, docs, commit messages, issue templates — everything. Target audience is the international media community.
Anonymity Rule
Never reference the maintainer's employer, specific productions, or identifiable real-world projects in any file. All examples must be generic, professional, and untraceable. The maintainer identity is Ur-grue only.
Repository Structure
autopunk-media-skills/
│
├── CLAUDE.md ← This file. Read first, every session.
├── README.md ← Public landing page (non-technical audience)
├── CONTRIBUTING.md ← How to contribute a skill
├── SKILL_TEMPLATE.md ← Exact format every skill must follow
├── ROADMAP.md ← All ~229 skills: status, priorities
├── CHANGELOG.md ← Version history
├── LICENSE ← MIT
│
├── .github/
│ ├── ISSUE_TEMPLATE/
│ │ ├── skill-request.md ← "I want a skill for X"
│ │ ├── quality-report.md ← "This skill gave me a bad result"
│ │ └── bug-report.md ← "This skill doesn't work at all"
│ └── pull_request_template.md
│
├── skills/
│ ├── tv-documentary/
│ │ ├── development/ ← pitch-treatment-writer, series-bible-generator,
│ │ │ logline-creator, character-arc-planner
│ │ ├── scripting/ ← scene-breakdown-writer, commentary-writer,
│ │ │ interview-question-generator, narrator-voice-adapter
│ │ ├── post-production/ ← rough-cut-notes, subtitles-rewriter,
│ │ │ press-kit-generator
│ │ ├── localization/ ← dubbing-script-adapter, festival-synopsis-writer
│ │ ├── pre-production/ ← shoot-schedule-builder, location-brief-writer,
│ │ │ release-form-checklist, equipment-list-generator
│ │ └── business/ ← co-production-brief, broadcaster-one-pager,
│ │ funding-application-writer
│ │
│ ├── magazine-journalism/
│ │ ├── ideation/ ← story-angle-finder, headline-generator,
│ │ │ research-brief-creator
│ │ ├── writing/ ← reportage-structure, column-voice-adapter,
│ │ │ interview-transcript-editor, sidebar-fact-box-writer
│ │ ├── editing/ ← copy-editor-assistant, fact-check-prompt,
│ │ │ house-style-enforcer
│ │ ├── distribution/ ← newsletter-teaser-writer, social-media-excerpt
│ │ ├── investigation/ ← source-contact-tracker, document-analysis-brief,
│ │ │ foia-request-writer, tipsheet-summarizer
│ │ ├── fact-checking/ ← claim-verification-checklist, source-credibility-scorer,
│ │ │ correction-notice-writer
│ │ └── legal/ ← defamation-risk-checker, privacy-law-brief,
│ │ rights-clearance-checklist
│ │
│ ├── youtube/
│ │ ├── pre-production/ ← niche-video-idea-generator, seo-title-optimizer,
│ │ │ thumbnail-concept-brief, hook-generator
│ │ ├── scripting/ ← full-script-writer, b-roll-shot-list,
│ │ │ call-to-action-generator, shorts-script-adapter
│ │ ├── post-production/ ← description-seo-writer, chapter-timestamps,
│ │ │ community-post-generator
│ │ ├── channel-strategy/ ← content-calendar-planner, audience-persona-builder
│ │ ├── business/ ← sponsorship-pitch-writer, media-kit-generator,
│ │ │ brand-deal-rate-card
│ │ └── analytics/ ← performance-report-summarizer, ab-title-tester,
│ │ audience-retention-analyzer
│ │
│ ├── podcast/
│ │ ├── pre-production/ ← episode-concept-generator, guest-research-brief,
│ │ │ interview-question-builder
│ │ ├── scripting/ ← solo-episode-script, intro-outro-writer,
│ │ │ ad-read-script
│ │ ├── post-production/ ← show-notes-generator, transcript-cleanup,
│ │ │ episode-summary-writer
│ │ └── business/ ← podcast-media-kit, listener-sponsorship-pitch,
│ │ network-submission-brief
│ │
│ ├── image-prompting/
│ │ ├── midjourney/ ← style-reference-prompt, character-consistency-prompt,
│ │ │ cinematic-shot-prompt
│ │ ├── flux/ ← editorial-photo-prompt, dark-aesthetic-prompt
│ │ ├── art-direction/ ← mood-board-brief, color-palette-brief,
│ │ │ visual-identity-prompt
│ │ └── workflows/ ← cover-image-pipeline, social-media-visual-batch
│ │
│ ├── media-business/
│ │ ├── pitching/ ← investor-deck-writer, executive-summary-generator,
│ │ │ elevator-pitch-builder, cold-email-writer
│ │ ├── distribution/ ← festival-submission-brief, distributor-one-pager,
│ │ │ press-release-writer, platform-pitch-adapter
│ │ ├── funding/ ← grant-application-writer, crowdfunding-copy-writer,
│ │ │ budget-narrative-generator
│ │ └── legal/ ← contract-summary-explainer, rights-audit-checklist,
│ │ talent-agreement-brief
│ │
│ ├── social-media/
│ │ ├── content/ ← caption-writer, thread-writer,
│ │ │ carousel-script-writer, short-form-video-brief,
│ │ │ push-notification-writer, seo-meta-description-writer
│ │ └── strategy/ ← platform-strategy-brief, hashtag-strategy-writer,
│ │ cross-promotion-pitch, tag-keyword-generator,
│ │ ab-social-post-tester
│ │
│ ├── radio-audio/
│ │ ├── scripting/ ← bulletin-script-writer, presenter-link-writer,
│ │ │ documentary-narration-writer, interview-cue-sheet-writer,
│ │ │ stand-up-script-writer
│ │ ├── news-packages/ ← package-script-writer, clip-selection-brief,
│ │ │ two-way-brief-writer
│ │ ├── production/ ← running-order-builder, programme-brief-writer
│ │ └── strategy/ ← podcast-to-radio-adapter, pitch-to-broadcaster
│ │
│ ├── newsletter/
│ │ ├── writing/ ← edition-writer, subject-line-writer,
│ │ │ welcome-email-writer, re-engagement-email-writer,
│ │ │ reader-response-writer
│ │ ├── strategy/ ← content-arc-planner, niche-positioning-brief,
│ │ │ audience-feedback-summarizer, newsletter-audience-segmenter
│ │ ├── growth/ ← referral-copy-writer, landing-page-copy-writer
│ │ └── monetization/ ← paid-tier-pitch-writer, sponsorship-rate-card
│ │
│ ├── pr-communications/
│ │ ├── press-office/ ← press-release-writer, media-alert-writer,
│ │ │ boilerplate-writer
│ │ ├── crisis-comms/ ← crisis-statement-writer, holding-statement-writer,
│ │ │ faq-document-writer
│ │ ├── media-relations/ ← journalist-pitch-email, spokesperson-briefing-note,
│ │ │ follow-up-email-writer, thank-you-email-writer
│ │ └── content/ ← op-ed-writer, speech-writer, internal-memo-writer
│ │
│ ├── screenwriting/
│ │ ├── development/ ← logline-writer, treatment-writer,
│ │ │ beat-sheet-builder, character-profile-writer
│ │ ├── scripting/ ← scene-writer, dialogue-polisher
│ │ ├── revision/ ← coverage-report-writer, script-notes-writer
│ │ └── production/ ← one-pager-writer
│ │
│ ├── data-journalism/
│ │ ├── analysis/ ← data-story-finder, statistics-explainer,
│ │ │ polling-analysis-writer, dataset-summary-brief,
│ │ │ basic-statistics-calculator
│ │ ├── visualization/ ← chart-description-writer, infographic-brief,
│ │ │ data-table-formatter
│ │ ├── investigation/ ← foi-data-request, scraper-brief,
│ │ │ data-cleaning-brief, pdf-table-extractor-brief
│ │ └── publishing/ ← methodology-explainer, data-corrections-writer,
│ │ data-footnote-writer
│ │
│ ├── research/
│ │ ├── people/ ← person-biography-brief, publication-history-finder,
│ │ │ press-office-finder, policy-decision-maker-mapper
│ │ ├── background/ ← legislative-history-brief, debate-state-summary,
│ │ │ historical-precedent-finder, corporate-structure-brief,
│ │ │ funding-source-investigator
│ │ ├── fact-checking/ ← legal-framework-brief, claim-origin-tracer
│ │ ├── academic/ ← scientific-paper-summarizer, scientific-consensus-brief,
│ │ │ study-methodology-evaluator, jargon-translator
│ │ ├── media/ ← coverage-review-brief, press-roundup-writer
│ │ └── logistics/ ← travel-logistics-brief
│ │
│ ├── translation/
│ │ ├── text/ ← article-translator, quote-translator
│ │ ├── institutional/ ← press-release-translator
│ │ ├── digital/ ← social-post-translator
│ │ ├── reference/ ← translation-glossary-builder
│ │ ├── quality/ ← translation-reviewer
│ │ └── localization/ ← regional-variant-adapter
│ │
│ ├── production-support/
│ │ ├── formatting/ ← cms-metadata-writer, asset-description-writer,
│ │ │ manuscript-formatter, web-section-splitter,
│ │ │ author-bio-writer
│ │ └── reference/ ← fact-sheet-compiler, teaser-block-writer
│ │
│ └── locales/
│ ├── es/ ← Spanish localizations (10 skills)
│ └── fr/ ← French localizations (10 skills)
│
└── tests/
├── EVAL_FRAMEWORK.md ← Full G-Eval testing protocol
└── COMMUNITY_REVIEW_CHECKLIST.md ← Plain-language quality checklist for any user
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.
- 11d ago First seen · 424 lines · 4,869 tokens per session scan A 4682c90e6a99
autopunk-media-skills CLAUDE.md is an instructions file published in the GitHub repository ur-grue/autopunk-media-skills (30 stars, last pushed 10d ago), licensed MIT. It adds 4,869 tokens to every session, about $0.0243 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 instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).