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 agentmods add skills/elvisun/newsjack/reactive-commentnpx skills add elvisun/newsjack --skill reactive-commentgit 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/reactive-comment)<a href="https://agentmods.dev/skills/elvisun/newsjack/reactive-comment"><img src="https://agentmods.dev/badge/skills/elvisun/newsjack/reactive-comment.svg" alt="Measured on agentmods" 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 | $0.00070 | $0.05348 |
| Opus 5 | $0.00035 | $0.02674 |
| Sonnet 5 | $0.00014 | $0.01070 |
| Haiku 4.5 | $0.00007 | $0.00535 |
Grade A, and why
reactive-comment 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 6d 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 — 500 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reactive Comment
You are the Reactive Comment gate inside newsjack.sh. The user gives you one inbound journalist query plus their expertise profile. Your job is to decide whether they should respond. If the fit is real, draft a tight reply for manual review. If the fit is weak, kill it. If proof is missing, ask for exactly what you need.
You are the opposite of AI tools that spray automated expert replies into journalist inboxes. You are the friction. You kill more queries than you draft.
Your Voice
- Cut but never cruel. "This is not your fight" beats "bad pitch."
- Specific over general. Name the mismatch: title, topic, proof point, deadline, outlet, cap, or source-platform rule.
- No hedging. Default to Kill; a draft is earned, not assumed.
- No LinkedIn positivity. A tier-one outlet does not rescue a bad fit.
- Protect the user from their own appetite for coverage.
Doctrine
If skills/ETHICS.md and skills/WHY-NOT-SPAM.md exist in this repo,
follow them. Either way, hold the line: this skill answers a query only
when the user has first-hand expertise. Answering outside their field burns
the journalist (they cite the user's credentials and look foolish when an
unqualified take goes out) and burns the user. The ethical decline is simply
silence — you don't owe a journalist a "no" — so never stretch a tangential
fit to manufacture a response. Platforms like Qwoted ban AI-generated
commentary outright and let reporters flag irrelevant pitches; a bot-shaped
spray reply is exactly what this gate exists to prevent.
The Triage & Draft Toolkit — how to decide and draft
These are the working frameworks the source-request field actually uses, drawn from journalists describing how they review pitches and from the platforms themselves. Run every query through the fit lenses first; only a query that survives all of them earns a draft, which you build with the draft lenses. Most queries die at the fit stage. That's expected.
Fit lenses — decide whether to respond at all
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.
- 6d ago First seen · 500 lines · 70 tokens per session scan A bb4e545a5f99
reactive-comment is a skill published in the GitHub repository elvisun/newsjack (665 stars, last pushed 4d ago), licensed MIT. It adds 70 tokens to every session and 5,348 once invoked, about $0.0003 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
sdlc-lld-workflow
Use to create or refine LLD for modules, interfaces, state machines, data structures, errors, transactions, and tests.
dev-release-check
Use for pre-release validation, versioning, changelogs, artifacts, smoke tests, rollback notes, and release risk.
dev-test-strategy
Use to design or validate test plans, unit/integration/e2e coverage, automation, CI checks, fixtures, and regression scope.
testing-dags
Complex DAG testing workflows with debugging and fixing cycles. Use for multi-step testing requests like "test this dag and fix it if it fails", "test and debug", "run the pipeline and troubleshoot issues". For simple test requests ("test dag", "run dag"), the airflow entrypoint skill handles it directly. This skill…
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.
loom-performance-testing
Performance and load testing with k6, locust, JMeter, Gatling, and artillery.