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
Run at session start and after every context compression. Do not restate rules from `AGENTS.md`.
Read `.claude/skills/start/INSTRUCTIONS.md` for the full procedure.
The line at the top of this page pins the label git:20260901.484ab7d, 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_nhwu5popqzulxrui
GET https://markdownregistry.com/api/v1/resolve?ref=rergards/mempalace-code/start
GET https://markdownregistry.com/api/v1/blob/c5c3d4dcc6f4c0d293fc6f6b96331c531ab65dd9eadc46b99cfb9ecc4a0bd1ba
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.
rergards/mempalace-code · .claude/skills/entropy-gc/SKILL.md · Scan codebase for AI-generated entropy — duplicated helpers, dead code, spreading anti-patterns. Use on a regular…
rergards/mempalace-code · .claude/skills/status/SKILL.md · Show current project status - recent work, in-progress tasks, and next priorities from backlog
rergards/mempalace-code · .claude/skills/task-plan/SKILL.md · Plan implementation for a backlog task with mode classification and optional Codex review
oliver-kriska/claude-elixir-phoenix · plugins/rewrite/skills/start/SKILL.md · Start or resume an Elixir rewrite of an app in any language (Rails, Django, PHP, Node, Go, Java, .NET, others) and show…
educlopez/ui-craft · .agents/skills/start/SKILL.md · Front door. Reads the current project (framework, tokens, brief, spec, harness) and reports what ui-craft can do right…
striderza/opencodegamestudios · .agents/modules/core/skills/start/SKILL.md · First-time onboarding — asks where you are, then guides you to the right workflow or to pre-workflow exploration. No…
striderza/opencodegamestudios · .agents/skills/start/SKILL.md · First-time onboarding — asks where you are, then guides you to the right workflow or to pre-workflow exploration. No…
striderza/opencodegamestudios · .opencode/modules/core/skills/start/SKILL.md · First-time onboarding — asks where you are, then guides you to the right workflow or to pre-workflow exploration. No…
nota-america/forgecat-agent-profiles · profiles/anthropics/knowledge-work-plugins/anthropics_knowledge-work-plugins_bio-research/for-claude/.claude/skills/start/SKILL.md · Set up your bio-research environment and explore available tools.
haabe/mycelium · plugins/mycelium/skills/start/SKILL.md · One command from "plugin installed" to "running brief on your idea." Combines /mycelium:setup (project-state…
normannoble/goagentic · skills/start/SKILL.md · Start a workspace agent by name and become it for the session. Use /agents:start <name>, /agents:start <name> <topic>…
