Use when building a high-stakes or hard-to-reverse change - schema/data migrations, auth, payments, public API surface, destructive operations, or concurrency - to adversarially refute the chosen approach BEFORE committing to it.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Doubt-Driven Development
## Overview
For most code, optimism is fine: try it, run the test, fix what breaks. For changes you cannot cheaply undo, optimism is a liability. Doubt-driven development inverts the default — you actively try to *refute* your chosen approach before you build it, and you require concrete evidence to clear each doubt.
**Core principle:** default to refuted when uncertain. A doubt you cannot disprove with evidence is a reason to choose a safer path, not a reason to proceed and hope.
This is review applied *during* the build, by you, before a single line is committed. It is distinct from [[validate]], the post-hoc multi-agent loop that runs after implementation — that catches what got built wrong; this catches what should never have been built that way.
## When to Use
Apply when the change is high-stakes or hard to reverse:
- **Schema / data migrations** — backfills, column drops, type changes, anything that mutates existing rows
- **Authentication / authorization** — session handling, token validation, permission checks
- **Payments / billing** — charges, refunds, idempotency, money math
…
The line at the top of this page pins the label git:20260912.480a145, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
A 17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
pass: Frontmatter block present
pass: Frontmatter declares a name
pass: Frontmatter declares a description
pass: Size between 200 bytes and 200 KB (5482 bytes)
pass: No zero-width or bidi control characters
pass: No instruction hidden inside an HTML comment
pass: No link to an exfiltration or paste host
pass: No credential-shaped string
pass: No instruction to send local credentials anywhere
pass: No text hidden with inline styles
pass: No prompt-injection phrasing
pass: No curl or wget piped into a shell
pass: No recursive delete of root, home or parent
pass: No instruction to read or print local credentials
pass: No base64 blob over 200 characters
pass: No link to a raw IP address
pass: No script tag
Source
GitHub
etr/groundwork · 44 stars · license MIT · pushed 2026-10-30 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_u763he3skkstxq4o
GET https://markdownregistry.com/api/v1/resolve?ref=etr/groundwork/doubt-driven-development
GET https://markdownregistry.com/api/v1/blob/3f15ed855d327c5f632940cc81f05f77d47f9424abac7d890c7cd740694e10b2
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
etr/groundwork · skills/build-unplanned/SKILL.md · Build a feature from description with worktree isolation and TDD. Usage /groundwork:build-unplanned "Add user login"
etr/groundwork · skills/debug/SKILL.md · This skill should be used when investigating bugs, unexpected behavior, test failures, or any code that does not work…
etr/groundwork · skills/design-architecture/SKILL.md · This skill should be used when the user asks to design system architecture, make architectural decisions, or translate…
etr/groundwork · skills/design-it-twice/SKILL.md · Use before committing to a non-trivial module, service boundary, or public API - generate 2-3 divergent interface…
etr/groundwork · skills/domain-modeling/SKILL.md · Use when designing a product or feature and the project lacks shared, agreed terminology - builds and maintains a pure…
etr/groundwork · skills/finalize-task/SKILL.md · Use when a task worktree has passed validation - manually commits, merges, and cleans up, or prepares runner-owned…
addyosmani/agent-skills · skills/doubt-driven-development/SKILL.md · Subjects every non-trivial decision to a fresh-context adversarial review before it stands. Use when you want every…
nota-america/forgecat-agent-profiles · profiles/addyosmani/agent-skills/for-codex/.agents/skills/doubt-driven-development/SKILL.md · Subjects every non-trivial decision to a fresh-context adversarial review before it stands. Use when you want every…
nota-america/forgecat-agent-profiles · profiles/addyosmani/agent-skills/for-forgecat/skills/doubt-driven-development/SKILL.md · Subjects every non-trivial decision to a fresh-context adversarial review before it stands. Use when you want every…
nota-america/forgecat-agent-profiles · profiles/addyosmani/agent-skills/for-forgecat/platforms/codex/.agents/skills/doubt-driven-development/SKILL.md · Subjects every non-trivial decision to a fresh-context adversarial review before it stands. Use when you want every…
nota-america/forgecat-agent-profiles · profiles/addyosmani/agent-skills/for-cursor/.cursor/skills/doubt-driven-development/SKILL.md · Subjects every non-trivial decision to a fresh-context adversarial review before it stands. Use when you want every…
nota-america/forgecat-agent-profiles · profiles/addyosmani/agent-skills/for-forgecat/platforms/cursor/.cursor/skills/doubt-driven-development/SKILL.md · Subjects every non-trivial decision to a fresh-context adversarial review before it stands. Use when you want every…
nota-america/forgecat-agent-profiles · profiles/addyosmani/agent-skills/for-claude/.claude/skills/doubt-driven-development/SKILL.md · Subjects every non-trivial decision to a fresh-context adversarial
