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 atretyak1985/swarmery --skill jira-writebackgit clone --depth 1 https://github.com/atretyak1985/swarmeryWrote 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/atretyak1985/swarmery/jira-writeback)<a href="https://agentmods.dev/skills/atretyak1985/swarmery/jira-writeback"><img src="https://agentmods.dev/badge/skills/atretyak1985/swarmery/jira-writeback/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/atretyak1985/swarmery/jira-writeback"><img src="https://agentmods.dev/badge/skills/atretyak1985/swarmery/jira-writeback.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 | $0.00094 | $0.03723 |
| Opus 5 | $0.00047 | $0.01861 |
| Sonnet 5 | $0.00019 | $0.00745 |
| Haiku 4.5 | $0.00009 | $0.00372 |
Grade A, and why
jira-writeback 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 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.
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 — 294 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
The only skill in jira-pack that calls addCommentToJiraIssue or
transitionJiraIssue. It takes jira-triage's verdict and evidence bundle,
renders the matching template from plugins/jira-pack/templates/, posts it,
and — only when the caller says the verdict allows it — attempts the QA
transition. It never decides the verdict itself and never touches the board
card.
Inputs (from the caller, @jira-task-runner)
verdict— one ofalready-fixed,cannot-reproduce,needs-info,needs-fix(Phase 7) — never called fortoo-large, which Phase 7'sjira-escalationhandles on its own.class—defectorchange, fromjira-triage. It selects the template forneeds-fix(see Templates) and is recorded in the idempotency marker. Aneeds-fixcall that arrives without a class is a caller bug: stop and report it rather than defaulting todefect, which would post a root-cause comment on a feature ticket.- The evidence bundle from
jira-triage(command, exit code, output fragment, commit/test reference, or the specific questions forneeds-info) — used to fill the chosen template's placeholders. attemptTransition: yes | no—noonly forneeds-info;yesfor every other verdict this skill is called with.cloudId,issueIdOrKey, and the pinned Atlassian MCP tool prefix, all resolved byjira-access-preflight.- A run tag (the board card's
externalId, or a timestamp-less tag if the board is unavailable) for the idempotency marker.
Step 1 — resolve the transition, before composing the comment
Call getTransitionsForJiraIssue (a read, always allowed, even in
--dry-run, even when attemptTransition: no — see the note at the end of
this section). Search for a transition whose target status is an exact
match against jira.qaStatus from the config: case-insensitive, leading/
trailing whitespace trimmed, and nothing fuzzier than that. The config exists
precisely so this skill never has to guess which status is "the QA one" —
a partial or fuzzy match would silently pick the wrong transition on a
workflow with several similarly-named statuses.
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 First seen · 294 lines · 94 tokens per session scan A dcef1f1bd345
jira-writeback is a skill published in the GitHub repository atretyak1985/swarmery (6 stars, last pushed 2d ago), licensed Apache-2.0. It adds 94 tokens to every session and 3,723 once invoked, about $0.0005 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 2026-09-03.
Other skills, from other repositories
execute
Execute phase — wave-based crew dispatch with critic gates and evidence-based verification.
recipe-block-focus-time
Create recurring focus time blocks on Google Calendar to protect deep work hours.
recipe-post-mortem-setup
Create a Google Docs post-mortem, schedule a Google Calendar review, and notify via Chat.
recipe-batch-invite-to-event
Add a list of attendees to an existing Google Calendar event and send notifications.
recipe-create-shared-drive
Create a Google Shared Drive and add members with appropriate roles.
recipe-find-free-time
Query Google Calendar free/busy status for multiple users to find a meeting slot.