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-configgit 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-config)<a href="https://agentmods.dev/skills/atretyak1985/swarmery/jira-config"><img src="https://agentmods.dev/badge/skills/atretyak1985/swarmery/jira-config/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-config"><img src="https://agentmods.dev/badge/skills/atretyak1985/swarmery/jira-config.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 | $0.00054 | $0.01714 |
| Opus 5 | $0.00027 | $0.00857 |
| Sonnet 5 | $0.00011 | $0.00343 |
| Haiku 4.5 | $0.00005 | $0.00171 |
Grade A, and why
jira-config 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 — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
jira-pack runs with autonomy: auto — nobody is watching to answer a clarifying question.
Anything the ticket text doesn't spell out has to come from .claude/project.json, and if it's
missing the run must fail loudly with a fix-it message, never guess. This skill is that gate:
it reads the jira block, validates it, resolves defaults, and resolves which repo the run
operates against — before any other jira-pack skill or agent touches a ticket.
Source of truth
Read ${CLAUDE_PROJECT_DIR}/.claude/project.json, key jira, straight from the file. Never
infer these values from a ticket, a prompt, or a prior run — the schema at
overlays/_schema/project.schema.json (jira property) is the contract; this skill enforces it
at runtime.
Validation
Required: jira.baseUrl, jira.projectKey, jira.qaStatus, jira.repro.test.
If any of these is missing (key absent, empty string, or repro present without test):
stop immediately. Do not call Jira, do not fall back to a guess, do not proceed with a
partial config. Report exactly which keys are missing and hand back a ready-to-paste JSON
fragment for the consumer to drop into .claude/project.json, e.g.:
jira-config: missing required keys — jira.projectKey, jira.qaStatus
Paste this into .claude/project.json (fill in the placeholders):
"jira": {
"baseUrl": "<jira-base-url>",
"projectKey": "<PROJECT-KEY>",
"qaStatus": "QA",
"repro": { "setup": "npm ci", "test": "npm test" },
"budget": { "maxFiles": 5, "maxAttempts": 3 }
}
Only list the keys that are actually missing — don't reprint the whole fragment as if nothing were configured when the config is partially there.
Working-repo resolution
Default: ${CLAUDE_PROJECT_DIR}. If the caller passes --repo <path>, use that path instead,
provided it exists and is a git repository (git -C <path> rev-parse --is-inside-work-tree
or equivalent) — otherwise stop and report the bad path, don't silently fall back to the
default. The resolved root is printed in the skill's own report and is what gets threaded into
the board card's prompt field downstream, so the executor agent operates against the same
repo this skill validated.
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 · 149 lines · 54 tokens per session scan A 0967c810c7df
jira-config is a skill published in the GitHub repository atretyak1985/swarmery (5 stars, last pushed yesterday), licensed Apache-2.0. It adds 54 tokens to every session and 1,714 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 2026-09-03.
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.