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 prompt-set-qagit 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/prompt-set-qa)<a href="https://agentmods.dev/skills/elvisun/newsjack/prompt-set-qa"><img src="https://agentmods.dev/badge/skills/elvisun/newsjack/prompt-set-qa/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/prompt-set-qa"><img src="https://agentmods.dev/badge/skills/elvisun/newsjack/prompt-set-qa.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- 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 | $0.00056 | $0.01407 |
| Opus 5 | $0.00028 | $0.00704 |
| Sonnet 5 | $0.00011 | $0.00281 |
| Haiku 4.5 | $0.00006 | $0.00141 |
Grade A, and why
prompt-set-qa 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 — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prompt Set QA
Decide pass, revise, quarantine, or reject. Do not quietly repair upstream work.
This skill inherits the ethical floor from skills/ETHICS.md. It enforces anti-hallucination, provenance, blinding, and decay-aware review. Anti-spray and human-send are not applicable.
Inputs
Require:
prompt_universe.json;prompt_architecture.json;- evidence excerpts and source metadata;
- the versioned contamination register;
- deterministic normalization, lexical scan, exact-hash, and similarity-pair results;
- optional blind human decisions.
Reject inputs that include baseline visibility, current rankings, target performance, answer-derived target pages, or selectors' preferred outcomes.
Run deterministic checks first
Check:
- schema and provenance completeness;
- unique IDs and resolved references;
- target, product, domain, people, slogan, proprietary-category, campaign, flattering-claim, and competitor terms;
- forbidden answer-derived fields;
- Unicode normalization, language, length, and one-concept shape;
- exact normalized hashes;
- lexical similarity candidate pairs;
- embedding pairs when a fixed model/version is available;
- architecture coverage, budget, and aided/lane consistency.
Deterministic target or campaign matches are hard failures in unaided core prompts. B0 target aliases pass only through a declared allowed exception. Embedding similarity may nominate a pair; it may never auto-delete.
Review semantically
For each candidate, judge:
- evidence-to-prompt entailment;
- naturalness and role/locale authenticity;
- whether both variants preserve one canonical intent;
- proximity, journey, act, expected-answer, and aided-status consistency;
- commercial leading or recommendation forcing;
- semantic slogan or flattering-claim leakage;
- whether answer-derived language entered core;
- whether a similar prompt changes a material constraint.
Protect differences in locale, persona, material constraint, competitor-aided status, information act, journey, and expected answer. Merge only when the job, journey, constraints, and answer kind are materially the same.
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 · 156 lines · 56 tokens per session scan A f3679f602889
prompt-set-qa is a skill published in the GitHub repository elvisun/newsjack (666 stars, last pushed 8d ago), licensed MIT. It adds 56 tokens to every session and 1,407 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
run-hugging-face-training-smoke
Runs one bounded, private Hugging Face training smoke with immutable inputs, local preflight checks, explicit stop gates, checkpoint verification, and reproducible evidence. Use before spending cloud compute on a longer fine-tuning run.
sdlc-lld-workflow
Use to create or refine LLD for modules, interfaces, state machines, data structures, errors, transactions, and tests.
dev-prompt-evaluation
Use to design, test, compare, version, and validate prompts or LLM behavior with measurable criteria and datasets.
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.
data-quality-frameworks
Implement data quality validation with Great Expectations, dbt tests, and data contracts. Use when building data quality pipelines, implementing validation rules, or establishing data contracts.