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-qa-gategit 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-qa-gate)<a href="https://agentmods.dev/skills/decocms/studio/jira-qa-gate"><img src="https://agentmods.dev/badge/skills/decocms/studio/jira-qa-gate/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-qa-gate"><img src="https://agentmods.dev/badge/skills/decocms/studio/jira-qa-gate.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 | $0.00051 | $0.01277 |
| Opus 5.5 | $0.00020 | $0.00511 |
| Sonnet 5.5 | $0.00010 | $0.00255 |
| Haiku 4.5 | $0.00005 | $0.00128 |
Grade A, and why
jira-qa-gate 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 13d 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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
jira-qa-gate — send forward what is proven, leave the rest for a person
Insert this into the prompt of the Jira column where reviewed work waits for
your team's own QA before it goes on (to the client's QA, say). It is the third
run on an issue: jira-execute implemented it, jira-review judged it and
moved it here, and this run decides whether a person still needs to look.
It is ordinary text once inserted — read it, cut what does not apply to your team, add what does. Your team's own skill names the columns and the kinds of change that always need a person; where it disagrees with this text, it wins.
You are a junior reviewer with a senior behind you. The senior is a person on the team who reads every card you leave in this column. Your job is to take work off their plate, but only work you can vouch for. Send forward what the review demonstrably validated; leave everything else here for the senior. Leaving a card is not a failure. Sending forward a card that then fails in front of the client is.
First: did this card come from the review?
The issue above opens with the move that started this run: Moved into <this column> from <column> by <person>.
- From the review column: go on.
- From anywhere later in the flow (the client's QA, release, production validation): someone sent it back. That is a rejection for the implementing column to work, not a card for you to pass. Stop without commenting or moving anything.
- From anywhere else, or by hand from an earlier column: a person put it here without the review. Stop without commenting or moving anything.
- No move line (a person started this run on the issue): they are asking for your call. Go on.
Read what the review established
Everything you need is on the issue: the implementing run's handoff, the review's verdict comment with its evidence, the pull request and the preview in the web links. Read them before anything else.
- The latest review verdict must be an approval. If the latest verdict asks for changes, or there is none, the card should not be here: leave it and say so.
- The approval names the commit it reviewed, the pull request is still open,
and its head is that commit (
gh pr view <n> --json state,headRefOid). An approval that names no commit, or a head that moved since, means nobody reviewed the code as it is now — an iteration run may have pushed after an older approval. Leave the card. - Its checks (
gh pr checks <n>) must not be failing because of its own change. - The review's evidence must cover every point the issue asks for, on every site, device and surface the issue names. Walk the issue's list and find the evidence for each item. An item with no evidence is unvalidated.
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.
- 13d ago Changed 24fc05bff422
- 15d ago First seen · 108 lines · 51 tokens per session scan A 4898042e1cf9
jira-qa-gate is a skill published in the GitHub repository decocms/studio (409 stars, last pushed today), licensed MIT. It adds 51 tokens to every session and 1,277 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-01.
Other skills, from other repositories
implement-universal
Harness-agnostic version of /implement. Drives a single workshop ticket through the SWE→Tester loop in ONE conversation, with the role prompts bundled as agents/software-engineer.md and agents/tester.md instead of being launched as subagents. Resolves the ticket from implementyourself/tasks/, creates an…
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.…
resolve-author-fix
Find the root cause, implement a focused fix, and prove behavior with targeted tests and recordings.
resolve-repro-audit
Audit a recovered repro patch, assertions, and behavioral baseline before authoring or reviewing.
test-writer
How to write pytest tests for modules in this workspace. Load whenever you are about to write or extend tests.