Gaslighting

AI coding agents love to escape.

They start strong, then drift.

They implement three examples and call it done.

They leave TODOs.

They create placeholders.

They say "the rest follows the same pattern."

Gaslighting is a strict project-discipline generator that stops this behavior.

It generates:

• GASLIGHTING.md
• PRD.md
• ASSUMPTIONS.md
• MISSING_INFO.md
• DECISION_LOG.md
• MEMORY.md
• STACK_POLICY.md
• AGENTS.md
• CODEX_PROMPT.md
• .codex/prompts/gaslighting.md
• Codex Skill files

Quick Start

npx gaslighting "I want to build a hospital website."

Short aliases after global install or local link:

gaslighting "I want to build a hospital website."

The default mode is already aggressive:

• hardcore discipline
• full-scope enforcement
• no-TODO escape prevention
• no-shortcut enforcement
• Codex Skill generation
• Codex /gaslighting prompt file generation

What It Does

It turns vague intent into strict AI-readable project discipline.

It tells the agent:

• what the project is
• what the project must not become
• what assumptions are being made
• what information is missing
• what stack to use
• what not to over-engineer
• what fake completion looks like
• what counts as done
• what stable project facts should be remembered

Commands

gaslighting "I want to build a hospital website."
gaslighting init "I want to build a hospital website."
gaslighting generate "Build an ecommerce MVP."
gaslighting update "The hospital is actually an OB-GYN clinic, not dermatology."
gaslighting doctor
gaslighting skill
gaslighting agents

Useful Options

Options are escape hatches. The strict behavior is already the default.

--standard
--allow-partial
--allow-todo
--allow-shortcut
--force
--dry-run
--lang en
--lang ko
--type hospital_homepage
--type ecommerce
--type landing_page
--type admin_dashboard

Why the Name?

Because AI agents often need aggressive reminders.

This project does not manipulate humans.

It disciplines AI coding agents.

Core Rule

Fake completion is worse than honest incompletion.

If the work is not done, say it is not done.

Use with Codex

After generating documents, tell Codex:

Read GASLIGHTING.md, PRD.md, STACK_POLICY.md, MISSING_INFO.md, ASSUMPTIONS.md, DECISION_LOG.md, MEMORY.md, and AGENTS.md.
Do not shrink the scope.
Do not leave TODOs.
Do not fake completion.

Gaslighting also writes .codex/prompts/gaslighting.md. Where your Codex build supports project prompt files, this gives you a /gaslighting-style prompt shortcut. Codex Skills are the stronger supported path, so the CLI also writes .codex/skills/gaslighting/SKILL.md.

Use as Codex Skill

Generate skill files:

gaslighting skill

This creates:

.codex/prompts/gaslighting.md
.codex/skills/gaslighting/SKILL.md
.codex/skills/gaslighting/references/GASLIGHTING_TEMPLATE.md
.codex/skills/gaslighting/references/HARDCORE_DISCIPLINE_TEMPLATE.md
.codex/skills/gaslighting/references/STACK_POLICY_TEMPLATE.md
.codex/skills/gaslighting/references/HOSPITAL_HOMEPAGE_EXAMPLE.md
.codex/skills/gaslighting/scripts/generate-gaslighting-docs.ts

Development

npm install
npm run build
node dist/index.js "I want to build a hospital website." --dry-run
npm test

The MVP is deterministic and template-based. It does not call OpenAI, Anthropic, or any external LLM API.