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 same-outlet-rankergit 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/same-outlet-ranker)<a href="https://agentmods.dev/skills/elvisun/newsjack/same-outlet-ranker"><img src="https://agentmods.dev/badge/skills/elvisun/newsjack/same-outlet-ranker/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/same-outlet-ranker"><img src="https://agentmods.dev/badge/skills/elvisun/newsjack/same-outlet-ranker.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Anti-Refusal · line 25 Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.Fix: Remove instructions that suppress warnings, disclaimers, or ethical commentary. Let the agent surface safety-relevant caveats to the user.
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 | $0.00084 | $0.05402 |
| Opus 5 | $0.00042 | $0.02701 |
| Sonnet 5 | $0.00017 | $0.01080 |
| Haiku 4.5 | $0.00008 | $0.00540 |
Grade A, and why
same-outlet-ranker 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 10d 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 — 302 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Same-Outlet Ranker
This is the Same-Outlet Ranker skill inside newsjack.sh. It answers one question: you have a pitch and several journalists at the same publication — who do you send it to first?
That question has a wrong answer that feels efficient: send it to all of them. Journalists at one outlet sit near each other, share Slack, and forward pitches. A masthead that has clearly been sprayed is one of the most legible tells in PR, and it costs you the outlet, not just the reporter. This skill exists to make you pick one.
It returns:
- Pitch first — exactly one journalist, with the specific edits that make the pitch land for that person.
- Held — the ranked order to fall back through, and the conditions that unlock each one.
- Do not pitch — candidates who are wrong for this story, with the reason.
- No pick — when nobody at this outlet clears the bar, or the evidence is too thin to choose honestly.
This skill inherits the ethical floor in skills/ETHICS.md and skills/WHY-NOT-SPAM.md. If local instructions conflict with that doctrine, the doctrine wins.
Boundaries
- Rank candidates at one publication at a time. Comparing across outlets is a different question and this skill does not answer it.
- Do not judge fit yourself. Per-journalist fit is
journalist-fit-check's job. Call it, then rank what survives. - Do not find journalists. That is
find-journalists. This skill ranks names you already have. - Do not produce a CC list, a group send, a "To:" line with several colleagues, or a same-day multi-send at one outlet. There is no version of the output that is a batch.
- Do not draft or send the pitch.
- Do not rank on prominence, follower count, or how senior a byline sounds. Where role matters, it matters as assignment authority — can this person green-light their own story? — not as prestige.
- Do not rank someone up because the user knows them.
- Do not invent bylines, dates, titles, links, outlets, or staff/contributor status.
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.
- 10d ago First seen · 302 lines · 84 tokens per session scan A 4c87f31a19ac
same-outlet-ranker is a skill published in the GitHub repository elvisun/newsjack (666 stars, last pushed 8d ago), licensed MIT. It adds 84 tokens to every session and 5,402 once invoked, about $0.0004 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 skills, from other repositories
a0-development
Development guide for extending Agent Zero from current source and DOX. Use for framework architecture, tools, extensions, API/WebUI handlers, agent profiles, prompts, skills, projects, runtime boundaries, and contribution workflow. Load the focused reference files before giving implementation guidance.
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…
codex-docs-drift-scout
Install the AutoHub docs-drift Codex automation from signed AutoVault skill resources and audit its render fidelity with autovault doctor.
gog
Google Workspace CLI for Gmail, Calendar, Drive, Contacts, Sheets, and Docs.
notion
Notion API for creating and managing pages, databases, and blocks.