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
# Code Simplification
## Trigger
- Keywords: simplify, clean up code, remove duplication, simplify code
## When NOT to Use
- New feature development (use `/feature-dev`)
- Document refactoring (use `/doc-refactor`)
- Full multi-target refactoring (use `/refactor`)
## Agent Dispatch
### Primary: Code Simplification
```
Agent({
description: "Simplify code, eliminate duplication, preserve behavior",
subagent_type: "code-simplifier",
prompt: `Simplify the code at: $ARGUMENTS
Follow the task steps and constraints defined in this skill.`
})
```
### Secondary: Refactoring Risk Review
After simplification, dispatch risk assessment:
```
Agent({
description: "Review refactoring risk and verify behavior preservation",
subagent_type: "refactor-reviewer",
prompt: `Review the refactoring changes just applied.
Check behavior preservation, dependency impact, test coverage, and rollback risk.`
})
```
## Task
For `$ARGUMENTS`:
1. **Run tests first** (establish baseline)
2. **Refactor**
- Dead code removal
- Extract duplicates (3+ repeats)
- Simplify nesting (> 3 levels)
3. **Run tests again** (confirm nothing broken)
## Output
```markdown
## Refactoring Summary
…
The line at the top of this page pins the label git:20260404.1c6641c, 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 (1562 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
sd0xdev/sd0x-harness · 194 stars · license MIT · pushed 2026-10-08 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_q5btsker33q54xfo
GET https://markdownregistry.com/api/v1/resolve?ref=sd0xdev/sd0x-harness/simplify
GET https://markdownregistry.com/api/v1/blob/9562bed1330ad38367d4f8f67c8a366a01e9a26bed5bedf76fda8434bcab7eae
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.
sd0xdev/sd0x-harness · skills/adr/SKILL.md · Write an Architecture Decision Record (ADR) for a feature — Context / Decision / Status / Consequences / Alternatives…
sd0xdev/sd0x-harness · skills/agentctl-setup/SKILL.md · Install and set up the optional agentctl mod (task scope, refusal before execution, evidence that goes stale…
sd0xdev/sd0x-harness · skills/ask/SKILL.md · Context-aware Q&A with auto context gathering. Use when: user has a quick question about codebase, git history, rules…
sd0xdev/sd0x-harness · skills/bump-version/SKILL.md · Bump package and plugin version in sync. Updates package.json, .claude-plugin/plugin.json, and install-state manifest…
sd0xdev/sd0x-harness · skills/check-coverage/SKILL.md · Comprehensive assessment of Unit / Integration / E2E three-layer test coverage, identify gaps and provide actionable…
sd0xdev/sd0x-harness · skills/code-investigate/SKILL.md · Dual-perspective code investigation. Use when: deep code analysis needing both Claude and Codex perspectives. Not for…
fcakyon/claude-codex-settings · plugins/simplify/skills/simplify/SKILL.md · This skill should be used when the user asks to "simplify", "clean up the diff", "run simplify", "simplify the…
cowork-os/cowork-os · resources/skills/simplify/SKILL.md · Improve existing work with focused simplification passes across code, writing, research, operations, or general tasks.
genai-io/san · .san/personas/software-engineer/skills/simplify/SKILL.md · Review changed code for reuse, quality, and efficiency, then clean up what you find — duplicated logic that could reuse…
haacked/dotfiles · ai/codex/skills/simplify/SKILL.md · Simplify recently changed code for clarity, consistency, and maintainability while preserving behavior. Use after…
maquina-app/rails-claude-code · rails-simplifier/skills/simplify/SKILL.md · Simplifies and refines Ruby on Rails code following 37signals patterns and the One Person Framework philosophy, while…
