This file is byte-identical to the first copy the registry indexed, one of 3 indexed copies. Same content hash, so the same checks give both the same grade.
alpha from conn-castle/agent-layer is an agent skill: a SKILL.md folder an AI agent loads when a task calls for 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.
The line at the top of this page pins the label git:20260805.81f125e, 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_j25wob622xwoqgtb
GET https://markdownregistry.com/api/v1/resolve?ref=conn-castle/agent-layer/alpha
GET https://markdownregistry.com/api/v1/blob/39d3a0072ca81bb2e7e7c8f291de12a9b05be60b22745d34c61049dbaa014eb7
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.
conn-castle/agent-layer · .agent-layer/skills/dogfood/SKILL.md · Explore Agent Layer through real tasks and inventive experiments in disposable projects; investigate failures…
conn-castle/agent-layer · internal/sync/testdata/fixture-repo/.agent-layer/skills/beta/SKILL.md · Second command does something useful for testing wrap lines in codex skills.
conn-castle/agent-layer · internal/sync/testdata/fixture-repo/expected/.agents/skills/beta/SKILL.md · Second command does something useful for testing wrap lines in codex skills.
conn-castle/agent-layer · internal/sync/testdata/fixture-repo/expected/.claude/skills/beta/SKILL.md · Second command does something useful for testing wrap lines in codex skills.
conn-castle/agent-layer · internal/templates/skills-catalog/benchmark/SKILL.md · Run A/B tests of skills, instructions, agents, harnesses, and other coding-agent system changes with Agent Layer's…
conn-castle/agent-layer · internal/templates/skills-catalog/dispatch-agent/SKILL.md · Use Agent Dispatch MCP tools only when the user names an external dispatch target or another skill explicitly requires…
conn-castle/agent-layer · internal/templates/skills-catalog/instruction-sync/SKILL.md · Manage ordered local and Git-backed Agent Layer instructions. Use for known instruction imports, status, diff, pull…
conn-castle/agent-layer · internal/templates/skills-catalog/skill-sync/SKILL.md · Manage local skills backed by known remote Git repositories. Use when the user wants to import, inspect, diff, pull…
athola/claude-night-market · plugins/abstract/tests/fixtures/skill_graph/fixtureplugin/skills/alpha/SKILL.md · Planted skill-graph control. Calls beta and one skill that does not exist.
robium-ai/robium · cli/test/fixtures/skills/alpha/SKILL.md · A folded-scalar description that spans multiple indented lines and should be joined with single spaces. Second sentence…