What is role-smoke-worker?

A worker that builds and runs smoke tests for Irreden Engine pull requests. Smoke tests are short checks that confirm the main path still starts or works after a change.

Use it to claim labelled engine or game pull requests, run the repository's cross-host smoke procedure, post the result, and release the work item.

It provides a focused pass-or-fail check without taking on feature work, code review, commits, or other tasks.

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

Your own site

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

Per session 46 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 2,808 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	$0.00046	$0.02808
Opus 5.5	$0.00018	$0.01123
Sonnet 5.5	$0.00009	$0.00562
Haiku 4.5	$0.00005	$0.00281

Measured 2d ago against content hash 8f35901c3223, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

role-smoke-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-smoke-worker.md · 152 lines

How it starts

The opening of the file, as written. The whole thing — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a smoke-only fleet worker for the Irreden Engine, dispatched into a shared pool worktree ~/src/IrredenEngine/.claude/worktrees/pool-*. You pick up fleet:needs-<host>-smoke on approved engine and game PRs, run the cross-host smoke protocol, post a verdict, and exit.

Mode (optional argument): $ARGUMENTS

Shared protocol

Bash tool rules, hard rules: CLAUDE-BASELINE.md.
Fleet state cache: FLEET-CACHE.md.
Heartbeat, exit protocol (transient one-shot, natural exit on the final turn, no looping, no kill -TERM $PPID), per-iteration shutdown, end-of-iteration feedback (~/.fleet/feedback/smoke-worker.md — keyed by role, not pane; worth surfacing: a label that persists across iterations, a systematic build failure, a missing label): FLEET-RUNTIME.md.
The smoke protocol and its labels: FLEET-CROSS-HOST-SMOKE.md.

Role constraints

Smoke-only: never pick queue tasks, open PRs, commit, or review logic; review-pr, commit-and-push, and simplify are off-limits.
Both repos. Every step below is written for an engine PR; a game PR (repo == "game" in the slice record / FLEET_DISPATCH_REPO=game) substitutes the per-repo table in FLEET-CROSS-HOST-SMOKE.md § "Author side" — --repo jakildev/irreden on gh, --repo game before the fleet-claim subcommand, cd into the game twin worktree (~/src/IrredenEngine/creations/game/.claude/worktrees/<basename>) as its own Bash call, IRGame via the dedicated build-game dir, and the game scratch-branch reset.
An environment failure is not a PR failure (same doc, "Environment failure is not a PR failure"): a failed dedicated configure, a build break in code the PR did not touch, or a run that logs Discovered 0 display monitors and never reaches the auto-screenshot exit is ENV-FAIL — no verdict, no label change, comment + decline.
Sonnet-tier smoke (exit code + log); no screenshot inspection, no render-debug-loop. Compile warnings in a zero-exit run escalate to Opus (step 5a), never a clean verdict.
fleet:needs-windows-smoke is polled only by a dispatch on the native-Windows fleet (host key windows); elsewhere platform-catchup is the manual fallback.

Read the full file on GitHub · 152 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 · 152 lines · 46 tokens per session scan A 8f35901c3223

Subscribe to this mod's changes

role-smoke-worker is a command published in the GitHub repository jakildev/IrredenEngine (10 stars, last pushed today), licensed MIT. It adds 46 tokens to every session and 2,808 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.

Code review Testing

role-smoke-worker next to 6 commands from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
role-smoke-workerjakildev/IrredenEngine	Command	10	today	MIT	A	46	Claude Code
diff-reviewcoco-research/coco	Command	629	yesterday	Apache-2.0	A	11	Claude Code
review-branchdamusix/atomic-claude	Command	116	7d ago	MIT	A	35	Claude Code
initazrtydxb/procoder	Command	212	2d ago	Apache-2.0	A	16	Claude Code
refactorRchGrav/claudebox	Command	1.2k	1mo ago	MIT	A	9	Claude Code
spec-trace-requirementsrjmurillo/ai-agents	Command	49	yesterday	MIT	A	0	GitHub Copilot
merge-conflict-analysisrjmurillo/ai-agents	Command	49	yesterday	MIT	A	0	GitHub Copilot

IrredenEngine: Command for Claude Code