question-the-premise

question-the-premise is a skill for Claude Code from Fergius-Engineering/instincts. It costs 28 tokens per session (454 once invoked), scanned A, original, MIT.

A debugging rule for reconsidering your original explanation when several sensible fixes fail or a symptom seems impossible.

In plain words
What is it for?
Use it after two or three failed fixes, when the same code behaves differently in different paths, or before committing to a large rewrite.
Why use it?
It prevents repeated changes to the wrong part of a system and directs attention to layers, evidence, or assumptions that may have been overlooked.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the instincts plugin — 20 skills, 2 hooks shipped together

Good fit Use it after two or three failed fixes, when the same code…

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/fergius-engineering/instincts/question-the-premise
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add Fergius-Engineering/instincts --skill question-the-premise
Clone the repo
git clone --depth 1 https://github.com/Fergius-Engineering/instincts

Made for: Claude Code.

Or install instincts, the plugin that ships this one along with the rest of its 20 skills, 2 hooks.

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 question-the-premise

README.md
[![agentmods](https://agentmods.dev/badge/skills/fergius-engineering/instincts/question-the-premise.svg)](https://agentmods.dev/skills/fergius-engineering/instincts/question-the-premise)
Your own site
<a href="https://agentmods.dev/skills/fergius-engineering/instincts/question-the-premise"><img src="https://agentmods.dev/badge/skills/fergius-engineering/instincts/question-the-premise.svg" alt="Measured on agentmods" height="20"></a>
Per session 28 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 454 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 $0.00028 $0.00454
Opus 5 $0.00014 $0.00227
Sonnet 5 $0.00006 $0.00091
Haiku 4.5 $0.00003 $0.00045

Measured 6d ago against content hash 2c5fb6d2c0d9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

question-the-premise 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 6d 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.

skills/question-the-premise/SKILL.md · 39 lines

What it actually says

The rule

Working by hypothesis, test, confirm only helps inside the right frame. If two or three well-reasoned fixes all fail, the likely problem is your premise, not your next fix. Stop and ask: have I actually confirmed the bug is in the layer I'm attacking?

This sharpens superpowers' systematic-debugging: that skill runs the loop; this one says when to stop looping and suspect the frame itself.

Fires when

Two or three fixes on the same hypothesis have all failed. A symptom that looks impossible — works in one path, fails in another that shares the same code. You're about to do a big rewrite or a deep dive to force the current theory to work.

How to apply

After about two or three failed fixes, treat the premise as the suspect, not the code. Get an outside view from someone or something that sees the whole story and has no stake in your theory.

Chase the impossible-looking discrepancy. It points at the layer you're not looking at.

If your evidence for the premise is a missing log line, load logging-for-remote-diagnosis first: absence is not proof.

Worked example

A test is flaky. You add a retry, still flaky. You add a sleep, still flaky. You mock the clock, still flaky. Three reasoned fixes, all failed.

The premise was wrong. Another test in the suite mutates a shared global, and the run order decides the outcome. Every timing fix was reading the wrong layer entirely.

The tell was right there the whole time: it passed alone but failed in the suite. That impossible-looking symptom was pointing at the real layer.

Red flags

Thought Reality
"Just one more fix and it'll work" after 2–3 have failed Suspect the premise instead.
"The data confirms my theory" Data read inside a wrong frame confirms the frame. Check the layer.
"I'll just rewrite this module" Before you've confirmed the bug is even in that module.
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. 6d ago First seen · 39 lines · 28 tokens per session scan A 2c5fb6d2c0d9

Subscribe to this mod's changes

question-the-premise is a skill published in the GitHub repository Fergius-Engineering/instincts (2 stars, last pushed 12d ago), licensed MIT. It adds 28 tokens to every session and 454 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.

Related

Other skills, from other repositories

hns-lsel-curator

Local Self-Evolution Loop (LSEL) curator — the CLUSTER + drain engine for the GOOS-local PROPOSE→APPLY seam closure (SPEC-LSEL-LOCAL-EVOLUTION-001). Companion-offset drain of .moai/lessons-inbox.jsonl with a drain-side severity filter that drops the 65% Bash-timeout/sandbox noise, eventkey clustering with a frequency…

modu-ai/moai-adk · 135 tokens

moai-workflow-ddd

Domain-Driven Development workflow specialist using ANALYZE-PRESERVE-IMPROVE cycle for behavior-preserving code transformation. Use when refactoring legacy code or reducing technical debt safely.

modu-ai/moai-adk · 44 tokens

memstack-development-performance-audit

Use this skill when the user says 'performance audit', 'why is it slow', 'optimize performance', 'page speed', 'Core Web Vitals', 'lighthouse', 'load time', or needs to diagnose and fix frontend or backend performance issues. Do NOT use for code reviews or security audits.

cwinvestments/memstack · 69 tokens

moai-workflow-loop

Ralph Engine - Automated feedback loop with LSP diagnostics and AST-grep integration for continuous code quality improvement. Use when implementing error-driven development, automated fixing, or continuous quality validation workflows.

modu-ai/moai-adk · 44 tokens

moai-workflow-testing

Use when writing tests, measuring coverage, or running characterization, performance, or PR-review QA. Comprehensive specialist combining DDD testing, characterization tests, performance profiling, and TRUST 5 quality-assurance validation.

modu-ai/moai-adk · 47 tokens

eval-hooks

Audit Claude Code hooks defined in settings.json files for validity, performance safety, and correctness. Resolves each command against the filesystem, checks exit-code strategy for blocking hooks, flags missing timeouts, and reviews interactive vs async patterns. Use when setting up hooks for the first time…

FlorianBruniaux/claude-code-ultimate-guide · 78 tokens