Rules for creating and editing vibecosystem agent definitions.
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
# Agent Development Rules
## Agent File Format
Each agent is a Markdown file with YAML frontmatter:
```yaml
---
name: agent-name
description: One-line description of what the agent does
tools: [Read, Write, Edit, Bash, Grep, Glob]
---
```
Followed by the agent's system prompt in Markdown.
## Naming Conventions
- Filename: `kebab-case.md` (e.g., `code-reviewer.md`)
- Name field: same as filename without extension
- Description: starts with a verb (e.g., "Reviews code for...")
## Agent Categories
- Core Dev: frontend-dev, backend-dev, kraken, spark, devops
- Review & QA: code-reviewer, security-reviewer, verifier, qa-engineer
- Domain Experts: graphql-expert, kubernetes-expert, ddd-expert
- Architecture: architect, planner, clean-arch-expert
- Testing: tdd-guide, e2e-runner, arbiter, mocksmith
- Analysis: scout, sleuth, data-analyst, profiler
## Quality Rules
- Every agent must have a clear, specific purpose
- Avoid overlapping responsibilities between agents
- Keep system prompts focused and actionable
- Include specific output format expectations
The line at the top of this page pins the label git:20260330.cd5da78, 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.
GET https://markdownregistry.com/api/v1/artifacts/art_zjwnb3aydfkez7xq
GET https://markdownregistry.com/api/v1/resolve?ref=vibeeval/vibecosystem/.cursor/rules/agent-development.mdc
GET https://markdownregistry.com/api/v1/blob/bf72891afd960efdf740e0b6926a918eecf71ea83d81385928f7b1f02c69db9d
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.
vibeeval/vibecosystem · skills/achievements/SKILL.md · Steam-style achievement system with XP, levels, streaks, and skill trees. Gamifies the development workflow. 25…
vibeeval/vibecosystem · skills/agent-benchmark/SKILL.md · Framework for measuring and tracking agent response quality over time. Detects regressions before they reach…
anthropics/claude-plugins-official · plugins/plugin-dev/skills/agent-development/SKILL.md · This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent…
nota-america/forgecat-agent-profiles · profiles/anthropics/claude-plugins-official/anthropics_claude-plugins-official_plugin-dev/for-codex/.agents/skills/agent-development/SKILL.md · This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent…
nota-america/forgecat-agent-profiles · profiles/anthropics/claude-plugins-official/anthropics_claude-plugins-official_plugin-dev/for-claude/.claude/skills/agent-development/SKILL.md · This skill should be used when the user asks to "create an agent",
nota-america/forgecat-agent-profiles · profiles/anthropics/claude-plugins-official/anthropics_claude-plugins-official_plugin-dev/for-forgecat/platforms/codex/.agents/skills/agent-development/SKILL.md · This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent…
nota-america/forgecat-agent-profiles · profiles/anthropics/claude-plugins-official/anthropics_claude-plugins-official_plugin-dev/for-forgecat/platforms/cursor/.cursor/skills/agent-development/SKILL.md · This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent…
nota-america/forgecat-agent-profiles · profiles/anthropics/claude-plugins-official/anthropics_claude-plugins-official_plugin-dev/for-cursor/.cursor/skills/agent-development/SKILL.md · This skill should be used when the user asks to "create an agent",
nota-america/forgecat-agent-profiles · profiles/anthropics/claude-plugins-official/anthropics_claude-plugins-official_plugin-dev/for-forgecat/skills/agent-development/SKILL.md · This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent…