Keep coding agents focused on requested and necessary work.
SkillScore96Maintained
Automatic
◆Coding pack
Last verified 9/26/2026
What it changes
Passed 21 of 22 test cases with the skill, and 17 of 22 without it.
Without skill78%
With skill96%
Checks it passed that the model alone missed
Requires a corrected directive to update the contract.
States that unknown directive fields leave the active contract unchanged.
Advises against editing session.py directly because answer mode is read-only.
and 2 more in the full report
4 fixed18 passed either way1 still failing0 broke
Pass-rate lift
+17 pp
Tokens
+70%
Agent turns
0%
Response time
-42%
Model gemini-3.6-flashMeasured 9/26/2026v222 of 23 cases passed with skill · 22 comparable
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 4 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 4
Prompt
An issue triage prompt begins with `$stop-that-shit answer -- Explain why the user session token expires prematurely`. The model identifies a missing expiration check on line 42 of `session.py`. Should the assistant directly edit `session.py` to fix the bug?
What was checked, without and with the skill
Checked
Without skill
With skill
Advises against editing session.py directly because answer mode is read-only.
Missed
Passed
case-15 · gemini-3.6-flash · 9/26/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md161 linessingle file
Stop That Shit
Meet the task's responsibilities in full. Let real needs drive complexity.
This Skill is advisory and works without the Guard hooks. It cannot guarantee
model behavior. When the Guard is installed, the same directives also provide
machine-enforced boundaries on supported host action paths.
Follow the Stop Ladder
Apply this ladder when choosing an implementation, adding a mechanism, or
extending verification. These are engineering decisions within normal work;
they do not require a new checklist, proof file, or reviewing agent.
Understand the current responsibility. Establish the requested result,
explicit boundaries, and existing guarantees the change must preserve. Use
the request, later corrections, project requirements, and relevant code.
Trace affected callers and failure paths before choosing a fix. Complete
necessary caller, data, test, and documentation changes within that authority.
A plan or an easier subset does not fulfill the requested result.
Start with a direct solution. Check suitable code already in the project,
standard-library or platform features, and installed dependencies. Compare
actual behavior, failure handling, and state lifetime. Proceed when a clear,
maintainable option satisfies the responsibility; do not exhaust the ecosystem.
Expand to close a concrete gap. Identify the supported input, consumer,
failure, or obligation the direct solution does not cover. Adapt or implement
that missing behavior at the responsible layer. Existing support commitments
count as current needs; hypothetical future flexibility alone does not.
A larger diff is justified when it completes the affected flow.
Judge defenses by their effect. Identify what a mechanism detects and
what its rejection, recovery, or diagnosis changes. Keep effective protection.
Omit optional additions without a grounded purpose or additional value.
Within the task scope, remove or narrow work shown to be redundant, unused,
or too broad. Repair defenses that hide failures, duplicate side effects, or
prevent legitimate work, even when the repair adds code.
Verify the result and finish. Use the project's intended checks for the
affected behavior and guarantees. Honor explicit acceptance criteria and
mandatory checks. Reuse evidence while it remains valid for the final state.
Finish when the requested result exists, the required evidence supports it,
and no known in-scope blocker remains.