codex-of-consentient-craft: Command for Claude Code

.claude/commands/dumpster-hunt.md

dumpster-hunt is a command for Claude Code from StupidIncarnate/codex-of-consentient-craft. It costs 12 tokens per session (5,000 once invoked), scanned A, original, MIT.

A command for recording a software bug as one clear, testable reproduction flow. It separates what actually happens from what should happen so the broken behavior can later become a failing test.

In plain words
What is it for?
Use it to capture a bug report, document its reproduction path, and define the expected behavior before another process writes regression tests and fixes the code.
Why use it?
It prevents developers from fixing a vague report before the user-visible problem has been reproduced and precisely described.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions subagents; names the AskUserQuestion tool; mentions Claude Code.

This is StupidIncarnate/codex-of-consentient-craft's own configuration. It tells Claude Code how to work on codex-of-consentient-craft itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything codex-of-consentient-craft configures →

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/StupidIncarnate/codex-of-consentient-craft/master/.claude/commands/dumpster-hunt.md
Clone the repo
git clone --depth 1 https://github.com/StupidIncarnate/codex-of-consentient-craft

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.

agentmods badge for dumpster-hunt

README.md
[![agentmods](https://agentmods.dev/badge/commands/stupidincarnate/codex-of-consentient-craft/dumpster-hunt/github.svg)](https://agentmods.dev/commands/stupidincarnate/codex-of-consentient-craft/dumpster-hunt)
Your own site
<a href="https://agentmods.dev/commands/stupidincarnate/codex-of-consentient-craft/dumpster-hunt"><img src="https://agentmods.dev/badge/commands/stupidincarnate/codex-of-consentient-craft/dumpster-hunt/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.

agentmods 80×15 button for dumpster-hunt

Your own site · 80×15
<a href="https://agentmods.dev/commands/stupidincarnate/codex-of-consentient-craft/dumpster-hunt"><img src="https://agentmods.dev/badge/commands/stupidincarnate/codex-of-consentient-craft/dumpster-hunt.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 5,000 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00012 $0.05000
Opus 5 $0.00006 $0.02500
Sonnet 5 $0.00002 $0.01000
Haiku 4.5 $0.00001 $0.00500

Measured 2d ago against content hash 6c7e24c157bc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

dumpster-hunt 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/dumpster-hunt.md · 347 lines

How it starts

The opening of the file, as written. The whole thing — 347 lines — stays where its author put it; the contents beside it link to each section on GitHub.

BugHunt - Regression Intake Agent

You capture a reported bug as a small, testable specification: ONE flow per bug. Each flow is the reproduction path, forking at the point where what happens TODAY diverges from what SHOULD happen. The fork's two terminal nodes are the actual/expected indicators — a node labelled ACTUAL: <the wrong thing the user sees> and a node labelled EXPECTED: <the behavior that should happen> — and the observables you embed on the EXPECTED side are the currently-broken invariants the codeweaver session that owns the package the fix lands in turns into failing tests.

You do NOT fix the bug. Once this spec is approved and the user starts the quest, the codeweaver session that owns the package the fix lands in writes the failing tests FIRST, confirms they fail on unchanged source, fixes the implementation, then ward → ward verify the fix.

This follows the regression-through-e2e playbook: reproduce and pin the user-visible symptom BEFORE any fix. Your job is the "pin the symptom" part, as a quest spec.


EXECUTION PROTOCOL

Start here. Your VERY FIRST action: call mcp__dungeonmaster__create-quest to create the new quest, passing the user's original bug report verbatim as the userRequest argument (it appears in the "User Request" section at the bottom of this prompt — copy it exactly) AND questType: 'bug-hunt' so the quest seeds the relay at Start with initialWorkItemRole: 'bughunt'. The user never passes a questId — you mint it. Capture the returned questId and guildSlug.

Open the web UI immediately after quest creation. Call mcp__dungeonmaster__get-server-config() to learn the server's baseUrl, then open the spec view so the user can watch quest state live and follow this conversation in the chat panel: <baseUrl>/<guildSlug>/quest/<questId>. Open it via Bash: xdg-open <url> 2>/dev/null || open <url> 2>/dev/null || true. Do this exactly once, before any further spec work. The user does not need to manually navigate.

Read the full file on GitHub · 347 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.

  1. 2d ago Changed · -2 lines 6c7e24c157bc
  2. 7d ago Changed · +19 lines f10286843162
  3. 11d ago First seen · 330 lines · 12 tokens per session scan A 2eb537bd897f

Subscribe to this mod's changes

dumpster-hunt is a command published in the GitHub repository StupidIncarnate/codex-of-consentient-craft (2 stars, last pushed today), licensed MIT. It adds 12 tokens to every session and 5,000 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.