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-access-preflightgit 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-access-preflight)<a href="https://agentmods.dev/skills/atretyak1985/swarmery/jira-access-preflight"><img src="https://agentmods.dev/badge/skills/atretyak1985/swarmery/jira-access-preflight/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-access-preflight"><img src="https://agentmods.dev/badge/skills/atretyak1985/swarmery/jira-access-preflight.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 | $0.00111 | $0.02957 |
| Opus 5 | $0.00056 | $0.01478 |
| Sonnet 5 | $0.00022 | $0.00591 |
| Haiku 4.5 | $0.00011 | $0.00296 |
Grade A, and why
jira-access-preflight 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 — 226 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
Make "can this run actually reach Jira" the first unconditional check of any jira-pack flow,
before jira-tasks reads anything or /jira-fix writes anything. If access is broken, the run
must stop with a report that explains exactly what's missing and how to fix it -- never
proceed on a partial or guessed capability set, and never let a write tool fire when a read
tool already failed.
Why the tool prefix can't be hardcoded
At least two channels can expose the same Atlassian MCP tools, under different prefixes, with identical tool names:
- an officially-installed Atlassian MCP plugin, e.g. tools registered under a
mcp__plugin_atlassian_atlassian__*-shaped prefix - a claude.ai connector for Atlassian/Rovo, e.g. tools registered under a
mcp__claude_ai_Atlassian_Rovo__*-shaped prefix
Those two are illustrative examples of the shape, not the two values this skill expects --
a host may register either one, both at once, neither, or a differently-named channel entirely,
and which channel (if any) is live changes between sessions and between machines. A skill that
hardcodes one prefix will report "no access" against a perfectly reachable Jira the moment the
other channel is the one that's live -- exactly the bug plugins/core/skills/jira-tasks/SKILL.md
carried in its own narrower read-only tool-loading example until Phase 8 de-hardcoded it to the
same by-name resolution this skill uses. This skill never assumes a specific prefix is present;
it resolves by tool name and treats whatever prefix comes back as the answer.
When to use
Run this skill's four steps, in order, as the unconditional first action of any jira-pack
run -- before jira-tasks performs a read and before /jira-fix (Phase 6) attempts any write.
Every step must pass before the run is allowed to touch a real ticket. A step failing at any
point stops the run immediately with the JIRA ACCESS: FAILED report in
Failure report -- there is no partial-access mode.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 226 lines · 111 tokens per session scan A 39a6284f5a9e
jira-access-preflight is a skill published in the GitHub repository atretyak1985/swarmery (5 stars, last pushed yesterday), licensed Apache-2.0. It adds 111 tokens to every session and 2,957 once invoked, about $0.0006 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.