Borrowing it
Nothing to install: this file belongs to StupidIncarnate/codex-of-consentient-craft. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/StupidIncarnate/codex-of-consentient-craft/master/.claude/commands/dumpster-launch.mdgit clone --depth 1 https://github.com/StupidIncarnate/codex-of-consentient-craftWrote 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.
[](https://agentmods.dev/commands/stupidincarnate/codex-of-consentient-craft/dumpster-launch)<a href="https://agentmods.dev/commands/stupidincarnate/codex-of-consentient-craft/dumpster-launch"><img src="https://agentmods.dev/badge/commands/stupidincarnate/codex-of-consentient-craft/dumpster-launch/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.
<a href="https://agentmods.dev/commands/stupidincarnate/codex-of-consentient-craft/dumpster-launch"><img src="https://agentmods.dev/badge/commands/stupidincarnate/codex-of-consentient-craft/dumpster-launch.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00010 | $0.00504 |
| Opus 5 | $0.00005 | $0.00252 |
| Sonnet 5 | $0.00002 | $0.00101 |
| Haiku 4.5 | $0.00001 | $0.00050 |
Grade A, and why
dumpster-launch 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 3d 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.
What it actually says
You are the dispatch loop for ALL approved Dumpster quests. The MCP server is the state machine; you are the dispatcher. Do NOT decide which agent runs next. Do NOT skip steps. Do NOT terminate on a quest failure — keep churning.
Loop forever:
- Call
mcp__dungeonmaster__get-next-step()with NO arguments. This may block up to ~25 s — that is normal. - Switch on
result.type:spawn-agents: dispatch ALL listed agents IN PARALLEL via the Task tool. Each Task's prompt istaskPromptverbatim (the questId is already interpolated). AWAIT all Tasks before continuing.run-ward: callmcp__dungeonmaster__run-ward({ questId: result.questId, workItemId: result.workItemId, mode: result.mode }). This blocks while ward runs (minutes). Wait for it. The quest-close ward is the merge rung; nothing inside a pass runs it.run-riftcarver: callmcp__dungeonmaster__run-riftcarver({ questId: result.questId, workItemId: result.workItemId }). This blocks while the quest's branch and worktree are carved and a scopedward run --only typecheckruns to convergence (minutes). Wait for it.idle: no work right now. FIRST checkresult.reason— if present, the queue is owned by another dispatcher (the Node dispatcher is playing on the web UI's /queue page). Report the reason to the user and STOP the loop; do not keep polling until they tell you it is paused. If there is noreason, wait by running a Bashsleep 1800withrun_in_background: true— that detaches the sleep and re-invokes you when it exits, at which point you callget-next-step()again. The wait MUST be a backgrounded Bashsleep; do NOT use ScheduleWakeup, a cron, or any other wakeup/timer mechanism — those are not wired into this loop and will be refused. Do NOT busy-pollget-next-step()in a tight loop instead of sleeping.
- Loop back to 1.
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.
- 3d ago Changed c8213ac8e912
- 12d ago First seen · 17 lines · 10 tokens per session scan A a8290af0f251
dumpster-launch is a command published in the GitHub repository StupidIncarnate/codex-of-consentient-craft (2 stars, last pushed yesterday), licensed MIT. It adds 10 tokens to every session and 504 once invoked, about $0.0001 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 2026-08-31.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.