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 journalist-fit-checkgit 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/journalist-fit-check)<a href="https://agentmods.dev/skills/elvisun/newsjack/journalist-fit-check"><img src="https://agentmods.dev/badge/skills/elvisun/newsjack/journalist-fit-check/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/journalist-fit-check"><img src="https://agentmods.dev/badge/skills/elvisun/newsjack/journalist-fit-check.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk warn
- NVIDIA SkillSpector warn
SkillSpector: 2 findings, 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 150 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.
- high Anti-Refusal · line 158 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 | $0.00088 | $0.05584 |
| Opus 5 | $0.00044 | $0.02792 |
| Sonnet 5 | $0.00018 | $0.01117 |
| Haiku 4.5 | $0.00009 | $0.00558 |
Grade A, and why
journalist-fit-check 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 12d 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 — 299 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Journalist Fit Check
This is the Journalist Fit Check skill inside newsjack.sh. It is the gatekeeper. It exists because too many pitches go to the wrong people: irrelevant stories, stale contacts, and mail-merge "personalization" sent to journalists who never asked for it.
It checks one journalist and one pitch at a time, and gives you one of four answers:
- Fit — pitch this person, the match is real.
- Soft-fit — close, but the pitch needs a few specific edits first.
- No-fit — wrong person, do not pitch.
- Unknown — not enough solid evidence to say yes or no.
Every Fit, Soft-fit, or No-fit answer must point to a real, dated, recent article (a "byline" — a piece with this journalist's name on it) published in the last 90 days. No real recent piece, no confident answer.
This skill is blunt on purpose. It will not soften a no or pad a maybe. A clear, specific answer beats a polite one.
Boundaries
- Do not build media lists.
- Do not rank journalists against each other.
- Do not send anything.
- Do not keep or trust a contact database.
- Do not call something a fit based on an outlet's category, a database tag, a bio, or a vibe.
- Do not make up articles, dates, titles, links, outlets, or social posts.
- Do not say Soft-fit when the honest answer is Unknown.
If you ask about 20 or 50 journalists, this skill checks them one at a time. Stopping the mass-blast is someone else's job; this skill will never be the thing that greases a batch send.
Required Inputs
Accept one journalist identifier:
- name + outlet
- profile URL
- recent byline URL
- a beat description (the topic area they cover) is useful context only; a beat on its own cannot identify a specific journalist and cannot produce an answer
Accept one pitch:
- full pitch text
- subject line if present
- body text as written
Accept context:
current_time_iso(today's date and time) is required. Never guess what "now" is from memory.client_or_subject(who or what the pitch is about) is optional.decay_stageis optional; it carries over from breaking-news workflows to flag how fast a story is moving.
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.
- 12d ago First seen · 299 lines · 88 tokens per session scan A b68f02fe9174
journalist-fit-check is a skill published in the GitHub repository elvisun/newsjack (666 stars, last pushed 9d ago), licensed MIT. It adds 88 tokens to every session and 5,584 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
obsidian-bases
Create and edit Obsidian Bases (.base files) with views, filters, formulas, and summaries. Use when working with .base files, creating database-like views of notes, or when the user mentions Bases, table views, card views, filters, or formulas in Obsidian.
warehouse-init
Initialize warehouse schema discovery. Generates .astro/warehouse.md with all table metadata for instant lookups. Run once per project, refresh when schema changes. Use when user says "/astronomer-data:warehouse-init" or asks to set up data discovery.
aws-cloudformation-rds
Provides AWS CloudFormation patterns for Amazon RDS databases. Use when creating RDS instances (MySQL, PostgreSQL, Aurora), DB clusters, multi-AZ deployments, parameter groups, subnet groups, and implementing template structure with Parameters, Outputs, Mappings, Conditions, and cross-stack references.
aws-sdk-java-v2-dynamodb
Provides Amazon DynamoDB patterns using AWS SDK for Java 2.x. Use when creating, querying, scanning, or performing CRUD operations on DynamoDB tables, working with indexes, batch operations, transactions, or integrating with Spring Boot applications.
spring-data-neo4j
Provides Spring Data Neo4j integration patterns for Spring Boot applications. Use when you need to work with a graph database, Neo4j nodes and relationships, Cypher queries, or Spring Data Neo4j. Creates node entities with @Node annotation, defines relationships with @Relationship, writes Cypher queries using @Query…
aws-sdk-java-v2-rds
Provides AWS RDS (Relational Database Service) management patterns using AWS SDK for Java 2.x. Use when creating, modifying, monitoring, or managing Amazon RDS database instances, snapshots, parameter groups, and configurations.