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-executegit 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-execute)<a href="https://agentmods.dev/skills/decocms/studio/jira-execute"><img src="https://agentmods.dev/badge/skills/decocms/studio/jira-execute/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-execute"><img src="https://agentmods.dev/badge/skills/decocms/studio/jira-execute.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 | $0.00036 | $0.00900 |
| Opus 5.5 | $0.00014 | $0.00360 |
| Sonnet 5.5 | $0.00007 | $0.00180 |
| Haiku 4.5 | $0.00004 | $0.00090 |
Grade A, and why
jira-execute 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
jira-execute — implement the issue and hand over
Insert this into the prompt of the Jira column your team builds in. It is the
first of two runs: this one implements and hands over, and a later column
reviews what it left (jira-review).
It is ordinary text once inserted — read it, cut what does not apply to your team, add what does.
You are implementing a Jira issue. The issue itself is above.
Build it
- Make the change, commit it, push the branch, and open a pull request.
- Change only what the issue needs. Don't refactor around it.
- The change must be REACHABLE from the surface the issue names: edit the component that route actually renders, not one that merely looks like the right place. A change nothing imports is the most common reason work comes back rejected.
- Open the pull request from the branch you were given. Don't move the work to a differently-named one.
Verify it on the deploy preview
Nobody else will. Do not hand over on a green test suite.
- After you push, the deploy bot comments the preview URL on the pull request —
poll
gh pr view <n> --json commentsuntil it appears (it takes a couple of minutes), then open that URL. A first request may wake a hibernating build; retry until you get real HTML. - Exercise the actual behaviour there and MEASURE it. Read the value back from the page rather than inferring it from a name or a spec — a spec that disagrees with production is a finding worth reporting, and it is the kind of thing only this step catches.
- Capture evidence with
qa-screenshot <url> <path>.png [--mobile], on desktop AND mobile, andReadeach file. A screenshot you never opened is not verification, and mobile is not desktop resized.
Report on the ISSUE
There is no card for anyone to read. A final message in this run is not a report — the issue is the only place your work becomes visible.
JIRA_REMOTE_LINK_ADDputs the pull request on the issue as a link (key: "pull-request"), and the deploy preview as another (key: "preview"). Do both — a URL buried in a comment is not something a person clicks.JIRA_COMMENT_ADDposts your report (markdown, tables included). Say what you changed, what you MEASURED on the preview, and what you deliberately left alone. Name anything the issue asked for that you did not do.- To show evidence, write each screenshot to
/app/org/output/<name>.pngand reference it in that comment as— it is uploaded to the issue and rendered inline. A before/after table of two images reads best. JIRA_ISSUE_GETre-reads the issue. Worth doing before you report: a person may have edited the card while you worked.JIRA_ATTACHMENT_DOWNLOADfetches an attachment into the pod by its id, when the card carries a mockup or a log you need.JIRA_ISSUE_TRANSITIONhands the issue over — LAST, after the links and the comment are on the card. Move it to the column where this work gets REVIEWED and no further: that is where the next run picks it up. Landing it in a QA or customer-facing column skips the review entirely and hands unverified work to a person. Then re-read the issue and confirm it actually landed there — a transition's advertised destination is not always where it puts the card, and the failure is silent.
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 b6a605c1e85c
- 29d ago Changed · +5 lines 449e18dec303
- 1mo ago First seen · 71 lines · 36 tokens per session scan A 24939c3a6fcc
jira-execute is a skill published in the GitHub repository decocms/studio (409 stars, last pushed today), licensed MIT. It adds 36 tokens to every session and 900 once invoked, about $0.0001 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 2026-09-16.
Other skills, from other repositories
pod-init
Initialize CocoPlus project bundle in the current directory. Creates .cocoplus/ directory structure, copies all templates, initializes AGENTS.md, project.md, flow.json, and creates the initial git commit. Run this once per project before using any other CocoPlus command.
github-operations
GitHub CLI operations for issues, PRs, milestones, and Projects v2. Covers gh commands, REST API patterns, and automation scripts. Use when managing GitHub issues, PRs, milestones, or Projects with gh.
pn-github-vertical-slices
Break a plan or PRD into tracer-bullet vertical slices and create GitHub Issues via GitHub MCP (official github/github-mcp-server). Dependencies first (AFK/HITL). Use after pn-writing-plans or pn-create-prd when work must ship as Issues.
resolve-publish
Commit the validated fix and follow local-only, workflow-owned, or direct PR publication.
lean-review
CocoLean diff-scoped over-engineering audit — scans uncommitted git diff and applies five classification tags (delete/stdlib/native/yagni/shrink) to identify unnecessary surface area before commit.
map-diff
Analyze the impact of staged git changes against the committed Cortex function knowledge graph — shows which downstream functions are affected before you commit.