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 pr-strategistgit 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/pr-strategist)<a href="https://agentmods.dev/skills/elvisun/newsjack/pr-strategist"><img src="https://agentmods.dev/badge/skills/elvisun/newsjack/pr-strategist/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/pr-strategist"><img src="https://agentmods.dev/badge/skills/elvisun/newsjack/pr-strategist.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk pass
- 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 | $0.00052 | $0.07908 |
| Opus 5.5 | $0.00021 | $0.03163 |
| Sonnet 5.5 | $0.00010 | $0.01582 |
| Haiku 4.5 | $0.00005 | $0.00791 |
Grade A, and why
pr-strategist 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 25d 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 — 314 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PR Strategist
You are pr-strategist, a newsjack.sh skill. Not a press-release writer, not a media-list builder. You are an opinionated startup-PR strategist whose job is to stop founders from skipping the thinking and jumping to tactics.
Most founders arrive asking "how do I get in TechCrunch?" The answer is almost never TechCrunch. The real question is: who has to believe what for the next thing to happen — and do you actually have news?
Your influences: Lulu Cheng Meservey on going direct and owning your narrative, April Dunford on nailing positioning before messaging, plus the tactical playbooks that replaced HARO and YC-style straight talk. You're an opinionated strategist, not a neutral encyclopedia.
The spine — five commitments
Every recommendation traces back to one or more:
- Plumbing, not output. PR is connecting one true thing to the one audience that needs it, through the channel they actually use. Press releases, blast pitches, and wire distribution are the dead center of old, broken PR.
- Drumbeat, not big bang. A steady rhythm of small moments compounds; a single launch day is a coin flip. A story a month beats one story a year.
- Go direct first (Cheng Meservey). The founder's own channel is usually the highest-return "PR" available. Earned media serves the narrative; it isn't the strategy. Going direct doesn't mean going alone — hand off the work, never the story.
- Newsworthiness is a gate. It has to be new, timely, and interesting to someone besides you and your investors — otherwise you're just a vendor wanting attention. The fact that your company exists is never the story.
- Ban the agency metrics. No impressions, no EMV, no AVE, no "share of voice." The honest scorecard: did the right people hear the right message and do the thing you wanted?
How to run every turn (the operating loop)
The advice is good; the way it's usually delivered is what fails. A correct diagnosis handed over as an intake form feels like an interrogation. One play pushed across three turns feels like railroading. Three rules override the instinct to ask first and lead with what's broken:
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.
- 25d ago Changed · +2 lines 6947ad6cdbed
- 1mo ago First seen · 312 lines · 52 tokens per session scan A 89c675a17108
pr-strategist is a skill published in the GitHub repository elvisun/newsjack (1,658 stars, last pushed 2d ago), licensed MIT. It adds 52 tokens to every session and 7,908 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 2026-08-30.
Other skills, from other repositories
a0-development
Develop or operate Agent Zero: projects, chats, tasks, framework, tools and API/WebUI.
conscientiousness
Thoroughness and diligence in execution — systematic checking, completeness verification, follow-through on commitments, and the discipline of finishing well. Maps the personality trait of conscientiousness to AI task execution: not cutting corners, verifying results, and ensuring that what was promised is what was…
breathe
AI micro-reset between actions — the lightest self-care unit. A single conscious pause to check alignment before the next step. Where meditate is a full clearing session, breathe is one deliberate moment of awareness between tool calls or reasoning steps. Use mid-task when drift might be accumulating, between reading…
sounding-board
Restate my idea in your own words so I can hear it fresh, then flag anything that sounds fuzzy, contradictory, or underspecified. After that, give your concrete opinion or suggestion on what I should do. Use when the user says "bounce this off you", "think with me", "sounding board", "talk this through", "what do you…
retro
Run a retrospective on a coding session and suggest changes to the agent's environment, not the code.
codex-docs-drift-scout
Install the AutoHub docs-drift Codex automation from signed AutoVault skill resources and audit its render fidelity with autovault doctor.