Scope creep
Fix one issue, then refactor half the project.
STOP THAT SHIT / TASK-BOUNDARY GUARD
Stop That Shit: You asked for one result. Why add SHA-256?
Give coding agents a concrete task boundary. Keep the callers, fixtures, and tests the result truly needs. Stop work that was not requested, has no current evidence, and changes no acceptance outcome.
TASK RECEIPT / HASHSTOP
- REQUEST
- Export result.csv REQUIRED
- EXTRA
- Create result.csv.sha256 UNASKED
- CONSUMER
- No later command reads it NONE
- DECISION
- Stop this action STOP
01 / TASK DRIFT
What does SHIT mean in Stop That Shit?
SHIT is not a single execution mode. It is a mnemonic for four kinds of task drift. Each step can look like good engineering in isolation while the combined work no longer serves the requested result.
Hashing & hardening
Add a digest, guard, or compatibility layer with no consumer.
Intent violation
The user asked for review; the agent edits files anyway.
Task thrashing
Search, test, and audit again after the answer is clear.
02 / STOP LADDER
Do not stop at “avoid overengineering.” Ask four questions.
A vague warning is easy to route around with another hypothetical future. The Stop Ladder pulls the decision back to the request, reachable code, data, deployment state, and acceptance criteria.
- 01
Did the user request it?
- 02
Is it necessary to complete the current result?
- 03
What reachable code, data, user decision, deployment state, or acceptance proves that need?
- 04
Where would the current task fail if we omitted it?
If all four answers are empty, do not promote “might help later” into “build it now.”
03 / BAD CASE + GOOD CASE
The same keyword can require opposite decisions.
Hash every row in two CSV files.
The workflow still compares every row afterwards. The hash replaces no operation and changes no next step.
STOP / UNNECESSARY HASHGenerate the checksum required by a release pipeline.
The release verifier reads the digest and rejects a mismatch. Without it, the current release fails.
ALLOW / hash=allow04 / INSTALL
How do I install the Stop That Shit plugin?
The Codex install is pinned to the public 0.1.0 release. After restart, inspect and trust UserPromptSubmit and PreToolUse under /hooks in the CLI TUI.
CODEX / POWERSHELL
codex plugin marketplace add lennney/stop-that-shit --ref 0.1.0
codex plugin add stop-that-shit@stop-that-shitRequires Node.js 18+. After Hook review, use $stop-that-shit review or $stop-that-shit change in a new task to make authority explicit.
Read the complete install and trust guideOne task boundary, four Host adapters
- 01CodexPlugin + UserPromptSubmit / PreToolUse
- 02Claude CodePlugin + native lifecycle Hooks
- 03OpenCodeGitHub plugin + before-action denial
- 04Hermes Agent CLINative plugin callbacks
05 / FIELD NOTES
Three angles on the same problem.
Recognize an unused SHA-256 artifact, decide when defensive engineering is justified, then connect the Skill, Guard, and task modes to a real workflow.
06 / FAQ
Eight common questions.
01What is Stop That Shit?
It is a task-boundary Skill + Hook Guard for AI coding agents. The Skill applies the semantic Stop Ladder; the Guard checks explicit mode, dependency, hash, file, and subagent boundaries on covered Host action paths.
02Is Stop That Shit a Skill or a plugin?
It is both. The standalone Skill provides the Stop Ladder and task modes such as review and change as advisory guidance. The complete plugin also packages the Guard and Host adapters, which check explicit boundaries on supported Hook paths.
03How do I install the Stop That Shit plugin?
For Codex, pin the marketplace to the public 0.1.0 release and then install the stop-that-shit plugin. It requires Node.js 18+. Restart, inspect UserPromptSubmit and PreToolUse under /hooks in the CLI TUI, then explicitly use review or change in a new task.
04How is Stop That Shit different from AGENTS.md?
AGENTS.md is the right place for durable repository architecture, commands, and conventions. Stop That Shit does not replace that context. It lets the user declare per-task review/change, file, dependency, hash, and subagent boundaries and checks explicit actions on supported Hook paths.
05What does SHIT stand for in Stop That Shit?
SHIT is not one execution mode. It names four kinds of task drift: Scope creep, Hashing and hypothetical hardening, Intent violation, and Task thrashing. The actual task modes include review, answer, monitor, and change.
06What are the limitations of Stop That Shit?
It can inspect only Hook events that the Host exposes with enough input. It is not a security sandbox and does not label every migration, retry, or cache as unnecessary. A returned denial records the Guard response; it is not observation of the Host's final effect.
07Does it ban every hash or checksum?
No. A release checksum or digest that skips an expensive reread has a real consumer and should remain. Version 0.1.0 requires explicit authority for identifiable new hash actions; hash=allow grants it.
08Which AI coding agents are supported?
Version 0.1.0 provides adapters for Codex, Claude Code, OpenCode, and Hermes Agent CLI. Their install, trust, restart, and event-coverage lifecycles are not identical.
SOURCE / CASES
Stopping work still needs evidence.
Inspect the source and 0.1.0 evidence. If a rule allows unnecessary work, file a Bad Case. If it blocks necessary work, file a Good Case.