A setup command that creates a .jira folder in a Git repository for tracking project state and sprints. A Git repository stores a project's history and branches; sprints are planned work periods.

Use it to start a Jira-style workspace with a project state file, sprint folders, a current-work file, documentation, and ignore rules.

It gives a repository a consistent place for project notes and current work without replacing an existing setup.

init — Command by koolamusic

Install

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.

agentmods

npx agentmods add commands/koolamusic/claudefiles/init

Clone the repo

git clone --depth 1 https://github.com/koolamusic/claudefiles

Per session 32 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 828 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

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.

Model	Per session	Once invoked
Fable 5	$0.00032	$0.00828
Opus 5	$0.00016	$0.00414
Sonnet 5	$0.00006	$0.00166
Haiku 4.5	$0.00003	$0.00083

Measured 2d ago against content hash 7342e279edb6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

init 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 2d 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/commands/init.md · 74 lines

How it starts

The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Bootstrap a jira workspace in the current git repository.

Steps

Verify git repo. Run git rev-parse --show-toplevel. If not a git repo, stop and tell the user to git init first — jira is built around branches, worktrees, and PRs.
Move to repo root. All paths below are relative to git rev-parse --show-toplevel.
Check for existing .jira/. If it exists with a STATE.md file, report it and exit — do not overwrite. (CURRENT may exist or not depending on whether a sprint is active.)

Create the layout:

.jira/
├── .gitignore
├── README.md
├── STATE.md         (project-wide state)
├── CURRENT          (empty — populated by /jira:research)
└── sprints/         (empty directory)

Copy the gitignore template from ${CLAUDE_PLUGIN_ROOT}/templates/gitignore to .jira/.gitignore.
Copy the STATE.md template from ${CLAUDE_PLUGIN_ROOT}/templates/STATE.md to .jira/STATE.md. Substitute frontmatter placeholders:
- {{project_name}} → basename of the repo root
- {{date}} (twice — created and last_activity) → today's date in YYYY-MM-DD
- {{none_or_slug}} → empty string

Write .jira/README.md with a 12-line explanation of the convention. Keep it short:

# .jira/

Sprint state for the [jira](https://github.com/koolamusic/claudefiles/tree/main/plugins/jira) workflow.

- `STATE.md` — project-wide state: sprint list, decisions log, blockers
- `CURRENT` — slug of the active sprint
- `sprints/YYYY-MM-DD-<slug>/` — one sprint per directory:
  - `BRIEF.md` (problem statement)
  - `RESEARCH.md` (parallel researcher synthesis)
  - `CONTEXT.md` (locked decisions D-XX, deferred ideas, canonical refs)
  - `features/*.feature` (acceptance predicates, `@req:<ID>` tagged — the sprint's goal set)
  - `01-PLAN.md`, `02-PLAN.md`, ... (one per wave-plan, ≤3 tasks each; claim predicates via `effects:`)
  - `EXECUTION.md` (commits, deviations, results)
  - `VERIFICATION.md` (goal-backward post-execution audit)
  - `RETRO.md` (opt-in)

All files inside sprints are committed.
Run `/jira:research <prompt>` or `/jira:research --issue N` to start a sprint.

Stage and commit (do NOT push):
```
git add .jira/
git commit -m "chore: bootstrap jira workspace (.jira/)"
```
If git add fails because .jira/ is gitignored at a parent level, surface that and stop.

Report:

.jira/ bootstrapped. Next: /jira:research <your-prompt> or /jira:research --issue <N>

Read the full file on GitHub · 74 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.

2d ago First seen · 74 lines · 32 tokens per session scan A 7342e279edb6

Subscribe to this mod's changes

init is a command published in the GitHub repository koolamusic/claudefiles (132 stars, last pushed 3d ago), licensed MIT. It adds 32 tokens to every session and 828 once invoked, about $0.0002 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 2026-08-30.

Git and workflow Project management Writing and docs

init

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Steps

What this file has done since we first saw it

Other commands, from other repositories

guide

pm-review

new

card

linear-bulk

deep-audit.skeleton