claude

jira

Lean sprint workflow. Nine commands (init/research/plan/execute/review/retro/uat/advisor/triage), eight agents, .jira/ state, GitHub issue + PR integration, Nyquist validation by default.

120 on GitHubby koolamusicMITupdated 29 days agoworkflow
/

Plugin jira from marketplace claudefiles in koolamusic/claudefiles. Commands read from the repo's manifest — 29 days ago.

What it installs

Slash commands (13)

  • /jira:advisor

    Advisory gate for triage or plan decisions. Spawns a second-opinion agent that challenges assumptions, surfaces risks, and proposes alternatives before the decision commits. Based on Anthropic advisor tool pattern.

  • /jira:comment

    Draft or post a GitHub issue/PR comment in stakeholder-readable voice, with proper GitHub autolinks and code permalinks. Default is draft-for-approval; posting is opt-in.

  • /jira:execute

    Execute the active sprint wave-by-wave with parallel jira-executor instances per wave. Then jira-nyquist (test gates), then jira-verifier (goal-backward), then PR. Updates STATE.md throughout.

  • /jira:flow

    Generate FLOW.md — human verification steps for the active sprint's acceptance predicates. Thinks like a tester; where to log in, what to click, which route to visit. Prioritizes predicates machines couldn't sense. Middleware between features/ and warden design.

  • /jira:init

    Bootstrap .jira/ in the current repo. Idempotent. Creates .jira/{.gitignore, README.md, STATE.md, sprints/, CURRENT}.

  • /jira:issue

    Draft a GitHub issue from the active sprint's research, plan, or wave — following the evidence-grounded conventions in templates/issue/GUIDE.md. Saves a draft; push is opt-in.

  • /jira:paper

    Write an evidence-disciplined engineering paper (innovation/discovery/finding) from a freeform description of what happened. Internally rigorous (evidence inventory, claim-strength discipline, adversarial review), lean single-file HTML house style for output. Publish is opt-in.

  • /jira:plan

    Plan the active sprint. jira-planner produces 01-PLAN.md, 02-PLAN.md per wave plus CONTEXT.md; jira-plan-checker audits all plans. Stall detection on revision. Optionally pushes a GitHub issue.

  • /jira:research

    Start a sprint by researching it. Spawns parallel jira-researcher agents (codebase, patterns, external) and synthesizes findings into RESEARCH.md. Updates STATE.md.

  • /jira:retro

    Generate a retrospective for the active sprint, a specific sprint, or a date range. Opt-in — never auto-fires.

  • /jira:review

    Review the diff for the active sprint or a given branch/range. Spawns jira-reviewer; reports findings by severity. Does not fix.

  • /jira:serve

    Build a static HTML review site from all sprints in .jira/sprints/ and serve it on a local port. Default serves every markdown file in every sprint; filter with --only. Extra markdown dirs (RFCs, specs) can be appended as sections with --include.

  • /jira:triage

    Triage the active sprint's plans into independently-grabbable GitHub issues using vertical slices. Adapted from mattpocock's to-issues pattern. Uses caveman lite.

Subagents (9)

  • jira-advisor

    Independent second-opinion agent that challenges triage recommendations or sprint plans. Reads the same artifacts as the planner/triager but approaches from a skeptical stance. Spawned by /jira:advisor.

  • jira-executor

    Executes a single PLAN.md (one wave-plan) with atomic commits. Worktree-aware. Updates EXECUTION.md as it goes. Orchestrator spawns one executor per plan; multiple executors run in parallel within the same wave.

  • jira-nyquist

    Validates that the executed sprint actually meets PLAN.md's Nyquist criteria. Fills coverage gaps by writing tests for any criterion not already covered. Implementation files are READ-ONLY. Spawned by /jira:execute after jira-executor finishes.

  • jira-paper-reviewer

    Adversarial peer reviewer for a drafted engineering paper. Independent of the drafting process — challenges claim strength, evidence quality, and promotional language before publish. Returns a structured verdict for stall detection. Spawned by /jira:paper after the draft is written.

  • jira-plan-checker

    Audits all *-PLAN.md files in a sprint by working backward from the goal. Verifies multi-source coverage matrix, per-plan task budget, parallel-safety, and CONTEXT.md decision implementation. Independent of jira-planner. Returns structured issue list for stall detection. Spawned by /jira:plan after

  • jira-planner

    Reads BRIEF, RESEARCH, CONTEXT and produces one or more numbered PLAN files (01-PLAN.md, 02-PLAN.md, ...) grouped by execution wave. Each plan ≤ 3 tasks. Runs source-coverage audit and schema-push detection. Spawned by /jira:plan.

  • jira-researcher

    One focus area of sprint research. Spawned in parallel with sibling researchers by /jira:research. Reads the sprint BRIEF, investigates a single dimension (codebase, patterns, or external), and returns a focused findings document with confidence-tiered sources.

  • jira-reviewer

    Reviews the diff for the current sprint (or current branch) and reports issues by severity. Doesn't fix — only reports. Spawned by /jira:review.

  • jira-verifier

    Goal-backward post-execution verifier. Asks "does the codebase as it stands now actually deliver the goal?" Distinct from jira-nyquist (test coverage) and jira-reviewer (diff audit). Spawned by /jira:execute after jira-nyquist passes.

View source on GitHub andrewmiracle.com

More from koolamusic/claudefiles

All 5 plugins →

pstack

claude

Rigorous agent workflows ported from Lauren Tan's pstack (github.com/cursor/plugins). /pstack:poteto-mode matches a task to a playbook and routes through how, why, architect, arena, swarm, interrogate, unslop and 24 principle skills.

50 skills · 2 agents

120

ux

claude

Frontend design skill with 17 steering commands for impeccable UI/UX. Based on Impeccable (https://impeccable.style).

1 skill · 7 commands

120

warden

claude

Acceptance test playbook. Three runtimes (bash, hurl, agent-browser), three modes (design, run, triage). Project-coupled, sprint-agnostic. Composes with jira:uat.

6 commands

120

studio

claude

Per-project workflow workspace. Hosts .project/.uat/.jira/.warden state in a private ~/.studio/ repo via symlinks. No consuming-tool modifications.

5 commands

120

Similar plugins

superpowers

claudecodex

Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques

15 skills · hooks

obra/superpowers 316,836

Backend API design, GraphQL architecture, workflow orchestration with Temporal, and test-driven backend development

9 skills · 1 command · 8 agents

wshobson/agents 42,461

beads

claudecodex

AI-supervised issue tracker for coding workflows

1 skill · 1 agent · hooks

gastownhall/beads 28,698

MiniMax AI skills library for frontend, fullstack, Android, iOS, shader, GIF sticker, document, presentation, spreadsheet, and multimodal media workflows

18 skills

MiniMax-AI/skills 13,828

worktrunk

claudecodex

Worktrunk is a CLI for Git worktree management, designed for parallel AI agent workflows. This plugin provides configuration guidance (LLM commit messages, project hooks, worktree paths), automatic activity tracking (🤖/💬 indicators in `wt list` showing active Claude sessions), and a `/wt-diff` pane showing each worktree's changes.

2 skills · hooks

max-sixty/worktrunk 12,481

gsd-core

claude

GSD Core is a meta-prompting, context engineering, and spec-driven development system for AI coding agents.

72 skills · 72 commands · 64 agents · hooks

open-gsd/gsd-core 11,494

Maintain jira?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex plugins5 plugins