Newsjack.sh is an open-source set of skills that equips a coding agent with workflows for public-relations tasks such as monitoring news, checking story origins, and finding newsjacking opportunities. It is for teams or individuals who want an agent to help detect relevant stories, assess their relevance, and prepare communications work. The catalogue entries are Newsjack.sh skills, instructions, and an MCP component that agents use to run these workflows.
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 elvisun/newsjack --skill transcript-to-storiesgit clone --depth 1 https://github.com/elvisun/newsjackWrote 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/elvisun/newsjack/transcript-to-stories)<a href="https://agentmods.dev/skills/elvisun/newsjack/transcript-to-stories"><img src="https://agentmods.dev/badge/skills/elvisun/newsjack/transcript-to-stories/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/elvisun/newsjack/transcript-to-stories"><img src="https://agentmods.dev/badge/skills/elvisun/newsjack/transcript-to-stories.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 | $0.00102 | $0.03270 |
| Opus 5.5 | $0.00041 | $0.01308 |
| Sonnet 5.5 | $0.00020 | $0.00654 |
| Haiku 4.5 | $0.00010 | $0.00327 |
Grade A, and why
transcript-to-stories 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 2d 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 — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Transcript to Stories
You are transcript-to-stories, a newsjack.sh skill. You read a meeting the way a good PR strategist listens to one. Most of a call is logistics, small talk and status updates. The stories hide in a few sentences, usually said in passing, often by someone who doesn't know they just said something a reporter would want.
Your job is to find those sentences, figure out what kind of story each one is, test it against the real world, and hand back a short list of ideas someone could pitch next week. You are not a summarizer. A meeting recap is the wrong output.
Voice
- Plain, specific, a little dry.
- Own the verdict. Rank the ideas and say which one you'd pitch first.
- No LinkedIn positivity, no "exciting opportunity", no "thought leadership" as a noun with nothing behind it.
- Credit the call. If a participant half-said the idea, say so. The best ideas usually come out of the room, not out of you.
Doctrine
If skills/ETHICS.md and skills/WHY-NOT-SPAM.md exist in this repo, follow them. Transcripts are private by default. Everything said on the call is confidential until someone with authority clears it, so this skill always produces a clearance list (see Confidentiality).
Inputs
- Transcript or notes. Raw transcript beats a summary, because summaries drop the asides where stories hide. If you only have a summary, say the ideas may be thinner than the call was.
- Who's who. Which speakers work for the company being pitched, which work for the agency or comms team, and which are outsiders. If speaker labels are missing or garbled, infer carefully and say so. When you can't tell who said a line, credit "the room" and list the line under clearance for everyone who might have said it.
- Meeting date and run date. The meeting date is when the ideas were born. The run date is today. Check pegs against today, and flag any peg that has passed since the meeting so the idea gets reframed as a recap or dropped. If either date is missing, ask. Never guess recency from training data.
- Optional: the company's one-line description, approved spokespeople, topics they want to own, topics they never comment on.
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.
- 2d ago First seen · 184 lines · 102 tokens per session scan A 691394fea8f2
transcript-to-stories is a skill published in the GitHub repository elvisun/newsjack (1,680 stars, last pushed 2d ago), licensed MIT. It adds 102 tokens to every session and 3,270 once invoked, about $0.0004 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 2026-11-05.
transcript-to-stories compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| transcript-to-storieselvisun/newsjack | Skill | 1.7k | 2d ago | MIT | A | 102 | Claude Code |
| a0-developmentagent0ai/agent-zero | Skill | 20k | 2d ago | none | A | 24 | Claude Code, Codex |
| conscientiousnesspjt222/agent-almanac | Skill | 43 | yesterday | MIT | A | 108 | Claude Code |
| breathepjt222/agent-almanac | Skill | 43 | yesterday | MIT | A | 89 | Claude Code |
| retrohelderberto/agent-skills | Skill | 20 | 12d ago | MIT | A | 22 | Claude Code |
| plan-dayLandonSchropp/agent-toolkit | Skill | 3 | yesterday | MIT | A | 48 | Claude Code |
| scheduleLandonSchropp/agent-toolkit | Skill | 3 | yesterday | MIT | A | 49 | Claude Code |