A task worker for a shared software project that takes queued issues, claims work without collisions, and either plans or executes tasks based on its assigned worker class.

It is for managing parallel engine and game development tasks, including issue planning, code changes, smoke checks, and resolving selected conflicts.

It gives multiple coding agents a defined way to pick work, avoid overlapping changes, review feedback, and prepare pull requests.

How jakildev/IrredenEngine configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to jakildev/IrredenEngine. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/jakildev/IrredenEngine/master/.claude/commands/role-worker.md

Clone the repo

git clone --depth 1 https://github.com/jakildev/IrredenEngine

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/jakildev/irredenengine/role-worker/github.svg)](https://agentmods.dev/commands/jakildev/irredenengine/role-worker)

Your own site

<a href="https://agentmods.dev/commands/jakildev/irredenengine/role-worker"><img src="https://agentmods.dev/badge/commands/jakildev/irredenengine/role-worker/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.

Your own site · 80×15

<a href="https://agentmods.dev/commands/jakildev/irredenengine/role-worker"><img src="https://agentmods.dev/badge/commands/jakildev/irredenengine/role-worker.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 50 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 6,147 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.

Model	Per session	Once invoked
Fable 5.1	$0.00050	$0.06147
Opus 5.5	$0.00020	$0.02459
Sonnet 5.5	$0.00010	$0.01229
Haiku 4.5	$0.00005	$0.00615

Measured 2d ago against content hash 0efa7a29d8d6, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

role-worker 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.

.claude/commands/role-worker.md · 314 lines

How it starts

The opening of the file, as written. The whole thing — 314 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a worker for the Irreden Engine fleet, dispatched into a shared pool worktree ~/src/IrredenEngine/.claude/worktrees/pool-* (WSL2 Ubuntu or macOS). You execute queued tasks of your class from the engine and game issue queues (fleet-queue-list) and plan the fleet:needs-plan issue the dispatcher assigned you; fleet-claim locks and open-PR cross-checks keep parallel workers from colliding.

Mode (optional argument): $ARGUMENTS

Your class for this iteration

Class is a property of the task. fleet-dispatch-wrap exports it as FLEET_ROLE_MODEL (fable, opus, or sonnet); fleet-claim gates claims on the task's fleet:<class> label (fallback: the body's **Model:** field). "opus+" below means opus or fable.

Step	sonnet class	opus+ classes
1 — feedback tiers	`human:needs-fix` / `human:blocker` / `fleet:needs-fix` / `fleet:has-nits`	those + `fleet:design-unblocked`
1b — cross-host smoke	exit-code half (escalate visual judgment)	judgment half (inspect screenshots)
1c — semantic conflicts	skip	resolve one per iteration
2 — planning	light-plan the assigned `FLEET_PLAN_ISSUE`	plan the assigned `FLEET_PLAN_ISSUE`
3 — task pickup	`model` == `sonnet`	`model` == your class
8 — escalation	re-tag one class up	design-blocked flow / re-tag to fable
10 — optimize	only hot-path changes	almost always

Your assignment for this iteration

One pre-claimed item per launch, its claim already held under your basename; fleet-claim decline is the walk-away — FLEET-RUNTIME.md § "The dispatch target". With FLEET_DISPATCH_TARGET set: run startup steps 0 and 0.5, skip the cache read and steps 4–5, skip every scan in loop steps 1, 1b, 1c, and 3, and jump by kind (for a game target, cd into your game twin worktree first).

`FLEET_DISPATCH_KIND`	go to
`task`	step 4 without its claim (the dispatcher ran `claim`; the reservation has no branch yet, so step 0.5 has nothing to resume): `cd` for a game task, `claim-base`, branch, then step 5
`stack`	step 4 as above; `claim-base` returns the recorded base branch
`feedback`	step 1 for PR #N per FLEET-FEEDBACK-HANDLING.md (its step a re-runs `fleet-pr-claim-feedback`, a no-op re-acquire)
`conflict`	step 1c for PR #N, from step b (skip b′)
`plan`	step 2 (`FLEET_PLAN_ISSUE` is set too)

Read the full file on GitHub · 314 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 · 314 lines · 50 tokens per session scan A 0efa7a29d8d6

Subscribe to this mod's changes

role-worker is a command published in the GitHub repository jakildev/IrredenEngine (10 stars, last pushed today), licensed MIT. It adds 50 tokens to every session and 6,147 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-11-07.

Building agents Project management

role-worker next to 6 commands from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
role-workerjakildev/IrredenEngine	Command	10	today	MIT	A	50	Claude Code
checklistgithub/spec-kit	Command	149k	2d ago	MIT	A	13	Claude Code
clarifygithub/spec-kit	Command	149k	2d ago	MIT	A	27	Claude Code
specifygithub/spec-kit	Command	149k	2d ago	MIT	A	13	Claude Code
analyzegithub/spec-kit	Command	149k	2d ago	MIT	A	26	Claude Code
convergegithub/spec-kit	Command	149k	2d ago	MIT	A	35	Claude Code
implementgithub/spec-kit	Command	149k	2d ago	MIT	A	14	Claude Code

IrredenEngine: Command for Claude Code