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 decocms/studio --skill jira-validate-productiongit clone --depth 1 https://github.com/decocms/studioWrote 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/decocms/studio/jira-validate-production)<a href="https://agentmods.dev/skills/decocms/studio/jira-validate-production"><img src="https://agentmods.dev/badge/skills/decocms/studio/jira-validate-production/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/decocms/studio/jira-validate-production"><img src="https://agentmods.dev/badge/skills/decocms/studio/jira-validate-production.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00067 | $0.01472 |
| Opus 5.5 | $0.00027 | $0.00589 |
| Sonnet 5.5 | $0.00013 | $0.00294 |
| Haiku 4.5 | $0.00007 | $0.00147 |
Grade A, and why
jira-validate-production scanned grade A with 1 finding 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 8d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- Look for the change itself in the live response (`curl -sL <url> | grep …`, How it starts
The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
jira-validate-production — confirm it on the live site
Insert this into the prompt of a run you start on several issues at once ("one
run for all of them"), or of the Jira column your team parks merged work in
until someone has seen it live. Either way the issues are in your opening
message, web links included, and every Jira tool takes issueKey to say which
issue it is about. On a run about one issue you can leave it out.
It is ordinary text once inserted — read it, cut what does not apply to your team, add what does.
With several issues, work through them yourself, one after another, in this run. Do not hand them to background agents: the run ends when your turn ends, and work still running in the background is lost with it.
You are the last check before an issue is closed: its change was implemented, reviewed and merged, and a deploy has (probably) shipped it. Nobody has looked at production yet. You are not reviewing the code again and you are not changing anything — you are answering one question per issue: is the behaviour the issue asked for live on the production site?
What to check, per issue
- Read the issue (
JIRA_ISSUE_GETwith its key): the description says what was wrong, and the review and merge comments say what changed and on which pages. That is your checklist. Do not invent extra criteria. - Find the merged pull request in the issue's web links and read its diff
(
gh pr diff <url>) so you know the CONCRETE effect to look for — a tag, an attribute, a header, a redirect, a value — rather than a paraphrase of it. - The production URL is the site the issue is about. Your team's own skill or the issue names it; if neither does, the repository's README usually does. Never guess a domain.
Confirm the deploy is live before you judge
A merge is not a deploy. Before calling anything a failure, make sure the change has actually reached production:
- Look for the change itself in the live response (
curl -sL <url> | grep …, or the rendered page). If it is there, the deploy is live. - If it is not, distinguish "not deployed yet" from "deployed and wrong": the
repository's deploy workflow or the hosting dashboard shows whether the merge
commit has shipped (
gh run list --branch main --limit 5,gh api repos/<owner>/<repo>/deployments). If the deploy is still running, wait for it — poll, with a bound of a few minutes — and re-check. - If the deploy is still not live when you give up waiting, that is NOT a failed validation. Leave the card as it is, with no comment and no move, and say so in your final message: a later run validates it once the deploy is out. A comment would read as a verdict when there is none.
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.
- 8d ago Changed · +17 lines · +4 tokens per session fada89972404
- 13d ago Changed 374d807a04fe
- 27d ago First seen · 90 lines · 63 tokens per session scan A a79896e94691
jira-validate-production is a skill published in the GitHub repository decocms/studio (409 stars, last pushed today), licensed MIT. It adds 67 tokens to every session and 1,472 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-19.
Other skills, from other repositories
playwright-cli
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.
verify-omnigent
Drive Omnigent the way a user does and prove a behavior with recorded evidence, using an isolated server, runner, and mock model plus a feature map of every user entry point. Load before reproducing a user-facing bug, before claiming a fix works, or when reviewing whether a change covered every surface (session vs.…
emulate-seed
Generate emulate seed configs for stateful API emulation. Wraps Vercel's emulate tool for GitHub, Vercel, Google OAuth, Slack, Apple Auth, Microsoft Entra, AWS, Okta, Clerk, Resend, Stripe, and MongoDB Atlas APIs — full state machines, not mocks. Use when setting up test environments, CI pipelines, integration tests…
testing-e2e
End-to-end testing patterns with Playwright — page objects, AI agent testing, visual regression, accessibility testing with axe-core, and CI integration. Use when writing E2E tests, setting up Playwright, implementing visual regression, or testing accessibility.
design-ship
One-shot pipeline turning a claude.ai/design link into a pull request: scaffold via /ork:design-import, stories and specs via /ork:cover, browser verification via /ork:expect, then open the PR. Use when a design link should come back as a PR with no intermediate steps; if all you need is the components written to…
storybook-testing
Storybook 10 testing patterns with Vitest integration, ESM-only distribution, CSF3 typesafe factories, play() interaction tests, Chromatic TurboSnap visual regression, module automocking, accessibility addon testing, and autodocs generation. Use when writing component stories, setting up visual regression testing…