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 holding-statement-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/holding-statement-writer)<a href="https://agentmods.dev/skills/ur-grue/autopunk-media-skills/holding-statement-writer"><img src="https://agentmods.dev/badge/skills/ur-grue/autopunk-media-skills/holding-statement-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/holding-statement-writer"><img src="https://agentmods.dev/badge/skills/ur-grue/autopunk-media-skills/holding-statement-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 | $0.00039 | $0.01036 |
| Opus 5 | $0.00019 | $0.00518 |
| Sonnet 5 | $0.00008 | $0.00207 |
| Haiku 4.5 | $0.00004 | $0.00104 |
Grade A, and why
holding-statement-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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Holding Statement Writer
What This Skill Does
Writes a brief holding statement for an organisation that is under media pressure but does not yet have all the facts — buying time without going silent and without making premature commitments.
When To Use This Skill
- A story is breaking and media are calling, but the internal investigation is not yet complete
- You need to say something on record before the "organisation declined to comment" line appears in the article
- Legal, executive, or regulatory constraints prevent you from making a full statement right now
- You have a holding statement from a previous incident that is no longer appropriate and needs a new one written fast
What You Need To Provide
Required: What the media is asking about (the allegation, incident, or story); the organisation's name; what you are and are not able to confirm right now; approximately when a full statement will be available (even a rough time — "by end of day" is better than nothing).
Optional: A specific spokesperson name; the channel (responding to press directly, posting to website, issuing to wire); any facts that are confirmed and safe to include; any specific phrases or framings that legal has approved or prohibited.
How the Assistant Approaches This
- Writes a statement that is short enough to deliver in one breath but substantive enough that journalists cannot report it as a non-answer.
- Acknowledges the subject of the inquiry directly — does not pretend the question has not been asked.
- States clearly and without elaborate explanation that the organisation is in the process of gathering information.
- Gives a specific or approximate timeframe for when more information will follow.
- Closes with a single concrete commitment — an update time, a point of contact, or both.
Output Format
50–120 words. One to three short paragraphs, or one single paragraph. Written in first person plural ("We") for the organisation. Present tense. Tone: calm, composed, not defensive, not evasive. No waffle, no "we take this very seriously" without substance behind it. No marketing language. Suitable for reading aloud to a journalist on the phone, posting to a website, or issuing to wire.
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 · 71 lines · 39 tokens per session scan A 7c068d9e302c
holding-statement-writer is a skill published in the GitHub repository ur-grue/autopunk-media-skills (32 stars, last pushed 11d ago), licensed MIT. It adds 39 tokens to every session and 1,036 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
xiaoyuzhou-podcast-notes
A workflow that turns a public Xiaoyuzhou FM podcast episode into structured Markdown notes and a saved transcript. Xiaoyuzhou FM is a Chinese podcast platform.
c-research
Summarize web URLs, PDFs, YouTube videos, and podcasts using the summarize CLI. Instantly extract key points from any content type without manual reading. Useful for research, link digests, and media review.
transcript-ingestion
Transcript ingestion authority — capture, normalize, and prioritize transcripts from YouTube videos, podcast pages, captions, show notes, and transcript-like page content for persona systems, RAG pipelines, and grounded synthesis.
correlation-crisis
Correlation breakdown during crises, tail risk measurement (VaR, CVaR, fat tails), regime-dependent correlation matrices, hedging strategies by volatility regime, and stress testing protocols. Use for correlation crisis, tail risk, VaR, CVaR, hedging strategy, stress test, or any correlation/tail-risk analysis.
youtube-seo-channel
Advanced channel-level YouTube SEO: identity, about, channel keywords, topical authority, playlist session chains, bingeable series structure, channel trailer, community tab strategy, translated metadata, and premiere/upload cadence planning. Use when user says "channel branding", "YouTube about page", "playlists"…
youtube-seo-competitor
Advanced YouTube competitor intelligence. Detects direct competitors, extracts winning title/thumbnail/hook patterns from transcripts, infers retention strategies from pacing, correlates posting cadence with performance, and identifies format-market-fit gaps. Use when user says "YouTube competitor analysis", "what are…