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 award-submission-writergit 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/award-submission-writer)<a href="https://agentmods.dev/skills/ur-grue/autopunk-media-skills/award-submission-writer"><img src="https://agentmods.dev/badge/skills/ur-grue/autopunk-media-skills/award-submission-writer/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/award-submission-writer"><img src="https://agentmods.dev/badge/skills/ur-grue/autopunk-media-skills/award-submission-writer.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 | $0.00038 | $0.01795 |
| Opus 5 | $0.00019 | $0.00898 |
| Sonnet 5 | $0.00008 | $0.00359 |
| Haiku 4.5 | $0.00004 | $0.00179 |
Grade A, and why
award-submission-writer 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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Award Submission Writer
What This Skill Does
Writes a compelling award or competition submission that frames a media project's significance, craft, and impact for a judging panel — structured to score well against standard evaluation criteria.
When To Use This Skill
- You are entering a documentary, podcast, article, or video project into an industry award
- You need to write a "project description" or "statement of purpose" field for a submission form
- You want to reframe a completed project for a judging panel that knows nothing about it
- You are submitting to multiple awards and need to adapt the core narrative for different criteria
What You Need To Provide
Required:
- The project title and format (documentary, podcast series, article, YouTube series, etc.)
- A summary of what the project is about (subject, scope, approach)
- The award or competition name and category (so the assistant can calibrate the framing)
- The key achievement or impact you want the judges to notice
Optional:
- Specific award criteria or judging rubric (if publicly available)
- Audience reach or measurable impact data (viewership, downloads, policy change, community response)
- Production challenges that were overcome (access difficulties, sensitive subjects, technical innovation)
- Word count or character limit for the submission field
- Whether this is a self-nomination or a third-party nomination
How the Assistant Approaches This
-
Leads with the story, not the credits. Judges read dozens of submissions. The assistant opens with the human dimension of the project — the question it asked, the world it revealed, or the stakes involved — before describing the craft. This creates a reason to care before a reason to admire.
-
Maps the submission to the award's values. Different awards prize different things: editorial rigour, visual innovation, social impact, audience engagement, investigative courage. The assistant identifies what the specific award values (from the criteria you provide or from the award category's implicit priorities) and ensures those elements are prominent, not buried.
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 · 98 lines · 38 tokens per session scan A 0e110dca76cd
award-submission-writer is a skill published in the GitHub repository ur-grue/autopunk-media-skills (32 stars, last pushed 12d ago), licensed MIT. It adds 38 tokens to every session and 1,795 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
Gun Jumping Clean Team Checklist
Use when merger parties between signing and closing are planning integration, sharing information, or proposing joint conduct — aligning pricing, joint customer calls, a co-branded announcement before the waiting period ends — to produce a draft covenant inventory, conduct-vs-covenant deviation log…
Merger Antitrust Issue Spotter
Use when a contemplated or signed acquisition, merger, JV, or minority investment needs first-pass antitrust issue-spotting — an LOI with a competitor, diligence underway, the board asking where filings may be needed — to produce draft horizontal-overlap and vertical-relationship matrices, filing-question and…
Trade Association Meeting Review
Use when trade-association participation needs antitrust screening — an upcoming agenda to vet, minutes or notes from a past meeting, a benchmarking or statistics program, a question whether a working group is safe to join — to produce a draft attendee map, per-agenda-item risk matrix, output-product inventory, and…
Antitrust Compliance Policy Review
Use when a company's antitrust compliance policy, competition code-of-conduct section, or training program needs a gap review — after an incident, an acquisition, a regulatory development, or as a periodic refresh — to produce a draft topic-coverage and jurisdiction-coverage matrix, training/reporting and dawn-raid…
Antitrust Risk Intake
Use when facts with possible competition-law exposure first arrive — a sales email about a competitor contact, a proposed collaboration, a pricing move, a hotline report, or an agency inquiry — to produce a draft conduct inventory and triage matrix that buckets each item, flags any time-critical track, and routes each…
Competitor Collaboration Review
Use when a proposed JV, co-development, co-marketing, joint purchasing, joint bidding, benchmarking, or standard-setting arrangement between actual or potential competitors needs antitrust screening, to produce a draft hardcore-restraint flag list, information-flow matrix, ancillarity questions, and per-jurisdiction…