jira-escalation

jira-escalation is a skill for Claude Code from atretyak1985/swarmery. It costs 112 tokens per session (3,745 once invoked), scanned A, original, Apache-2.0.

A Jira escalation workflow that turns work too large for an automated fix run into a phased plan, saves it privately, and posts the plan to the ticket.

In plain words
What is it for?
It helps hand off large features, epics, or unsuccessful fix attempts to a human with a structured plan.
Why use it?
It preserves the diagnosis and partial work instead of abandoning them when a task exceeds the run's limits.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions CLAUDE.md.

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /Users/andriytretiak/.claude/CLAUDE.md.

Part of the jira-pack plugin — 7 skills, 1 command, 1 agent shipped together

Good fit It helps hand off large features, epics, or unsuccessful fix attempts to a human with a structured plan.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add atretyak1985/swarmery
Claude Code
/plugin install jira-pack

Made for: Claude Code.

Or install jira-pack, the plugin that ships this one along with the rest of its 7 skills, 1 command, 1 agent.

Wrote 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.

agentmods badge for jira-escalation

README.md
[![agentmods](https://agentmods.dev/badge/skills/atretyak1985/swarmery/jira-escalation/github.svg)](https://agentmods.dev/skills/atretyak1985/swarmery/jira-escalation)
Your own site
<a href="https://agentmods.dev/skills/atretyak1985/swarmery/jira-escalation"><img src="https://agentmods.dev/badge/skills/atretyak1985/swarmery/jira-escalation/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.

agentmods 80×15 button for jira-escalation

Your own site · 80×15
<a href="https://agentmods.dev/skills/atretyak1985/swarmery/jira-escalation"><img src="https://agentmods.dev/badge/skills/atretyak1985/swarmery/jira-escalation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 112 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,745 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00112 $0.03745
Opus 5 $0.00056 $0.01872
Sonnet 5 $0.00022 $0.00749
Haiku 4.5 $0.00011 $0.00375

Measured 8d ago against content hash aa8c68ff13d3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

jira-escalation 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.

plugins/jira-pack/skills/jira-escalation/SKILL.md · 281 lines

How it starts

The opening of the file, as written. The whole thing — 281 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Purpose

Make "this is bigger than an autonomous /jira-fix run" a soft landing instead of a dead end. When a ticket or a fix attempt outgrows jira.budget, the work already done (evidence, diagnosis, partial fix attempts) is not thrown away — it becomes a phased plan, saved where every other plan in this project lives, with its full text posted back to the ticket so a human can pick it up without needing local filesystem access.

When to use

Called from two places:

  1. jira-triage, before any repro attempt, when a ticket is self-evidently an epic or multi-stage feature (its own early-exit note). No branch exists yet in this path.
  2. jira-delivery, mid-attempt, once one of the budget/verification triggers below fires. A branch and worktree may already exist in this path and must be cleaned up (Step 4).

Triggers (any one of these five fires escalation)

  1. jira.budget.maxFiles exceeded — the executor's diff touches more files than the budget allows, independent of whether verification passed (jira-delivery's own second gate).
  2. jira.budget.maxAttempts exceeded — that many delegate→verify cycles have run without a qualifying PASS.
  3. @debugger returned an escalation under its own stop conditions (fix spiral, 3 failed attempts, ~5 files — plugins/core/agents/debugger.md) before jira.budget.maxAttempts was independently exhausted; treat this the same as trigger 2 rather than waiting for the outer counter to also run out.
  4. @verification-agent returned FAIL and jira.budget.maxAttempts is already exhausted (a FAIL with attempts remaining is not itself a trigger — jira-delivery re-dispatches instead).
  5. jira-triage classified the ticket too-large at triage time, before any reproduction attempt.

Step 1 — brief the planner

@planner (plugins/core/agents/planner.md) handles both scopes: a single defect or small feature that simply exceeded the autonomous budget gets a compact 3-5 phase plan, while a genuinely multi-phase ticket (an epic, a cross-repo migration) gets a full multi-phase plan. State the scope signal in the brief — triage's too-large reason, roughly how long the work looks — so the planner sizes the plan deliberately.

Read the full file on GitHub · 281 lines

Changes

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.

  1. 8d ago First seen · 281 lines · 112 tokens per session scan A aa8c68ff13d3

Subscribe to this mod's changes

jira-escalation is a skill published in the GitHub repository atretyak1985/swarmery (6 stars, last pushed 2d ago), licensed Apache-2.0. It adds 112 tokens to every session and 3,745 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.