Update to Olbrain Alchemist
Snapshot Nov 6, 2026 · 00:13 UTC · version 0.9.11
Collection source: downloaded plugin package.
Instructions updated for build
Full description — Now says: Start building an Olbrain agent with Alchemist from a description. Use only when the user asks to start a build.
Observed in instructions or declared skills. Runtime behavior has not been tested.
Up to 3 plugins free · no card required.
All fields and original values.
Full description
Oct 28, 2026 · 18:06 UTC
Start building an Olbrain agent with Alchemist from a description.
Nov 6, 2026 · 00:13 UTC
Start building an Olbrain agent with Alchemist from a description. Use only when the user asks to start a build.
Skill instructions
Oct 28, 2026 · 18:06 UTC
description. Build an Olbrain agent with Alchemist, following the alchemist skill: check `whoami` first, then pass this request to the `alchemist` tool in the user's words. If the request is empty,
Nov 6, 2026 · 00:13 UTC
description. Use only when the user asks to start a build. allowed-tools: - mcp__plugin_alchemist_alchemist__whoami - mcp__plugin_alchemist_alchemist__alchemist_builds - mcp__plugin_alchemist_alchemist__alchemist_build - mcp__plu...
Compare saved observations
Download comparison JSONSKILL.md text changes
− removed · + added
--- before +++ after @@ -1,13 +1,22 @@ --- name: build -description: Start building an Olbrain agent with Alchemist from a description. +description: Start building an Olbrain agent with Alchemist from a description. Use only when the user asks to start a build. argument-hint: <what the agent should do> disable-model-invocation: true +allowed-tools: + - mcp__plugin_alchemist_alchemist__whoami + - mcp__plugin_alchemist_alchemist__alchemist_builds + - mcp__plugin_alchemist_alchemist__alchemist_build + - mcp__plugin_alchemist_alchemist__alchemist_capabilities + - mcp__plugin_alchemist_alchemist__alchemist_state --- -Build an Olbrain agent with Alchemist, following the alchemist skill: check `whoami` -first, then pass this request to the `alchemist` tool in the user's words. +Build an Olbrain agent with Alchemist, following the alchemist skill: check `whoami` first, +then find or start the build with the `alchemist` tool, passing the request in the user's +words. If `alchemist_state` is in your tool list, call it and follow it; otherwise follow the +`alchemist` tool's turns. Request: $ARGUMENTS -If the request is empty, ask the user what the agent should do before calling any tool. +If the request above is empty, or still reads `$ARGUMENTS`, use what the user asked for in +their message. If there is nothing, ask the user what the agent should do before calling any tool.
Full technical diff · 2 changed fields
changed /description
"Start building an Olbrain agent with Alchemist from a description."
"Start building an Olbrain agent with Alchemist from a description. Use only when the user asks to start a build."
changed /skill_md_contents
"---\nname: build\ndescription: Start building an Olbrain agent with Alchemist from a description.\nargument-hint: <what the agent should do>\ndisable-model-invocation: true\n---\n\nBuild an Olbrain agent with Alchemist, following the alchemist skill: check `whoami`\nfirst, then pass this request to the `alchemist` tool in the user's words.\n\nRequest: $ARGUMENTS\n\nIf the request is empty, ask the user what the agent should do before calling any tool.\n"
"---\nname: build\ndescription: Start building an Olbrain agent with Alchemist from a description. Use only when the user asks to start a build.\nargument-hint: <what the agent should do>\ndisable-model-invocation: true\nallowed-tools:\n - mcp__plugin_alchemist_alchemist__whoami\n - mcp__plugin_alchemist_alchemist__alchemist_builds\n - mcp__plugin_alchemist_alchemist__alchemist_build\n - mcp__plugin_alchemist_alchemist__alchemist_capabilities\n - mcp__plugin_alchemist_alchemist__alchemist_state\n---\n\nBuild an Olbrain agent with Alchemist, following the alchemist skill: check `whoami` first,\nthen find or start the build with the `alchemist` tool, passing the request in the user's\nwords. If `alchemist_state` is in your tool list, call it and follow it; otherwise follow the\n`alchemist` tool's turns.\n\nRequest: $ARGUMENTS\n\nIf the request above is empty, or still reads `$ARGUMENTS`, use what the user asked for in\ntheir message. If there is nothing, ask the user what the agent should do before calling any tool.\n"
Full snapshot data
{
"description": "Start building an Olbrain agent with Alchemist from a description. Use only when the user asks to start a build.",
"included_files": [],
"name": "build",
"skill_md_contents": "---\nname: build\ndescription: Start building an Olbrain agent with Alchemist from a description. Use only when the user asks to start a build.\nargument-hint: <what the agent should do>\ndisable-model-invocation: true\nallowed-tools:\n - mcp__plugin_alchemist_alchemist__whoami\n - mcp__plugin_alchemist_alchemist__alchemist_builds\n - mcp__plugin_alchemist_alchemist__alchemist_build\n - mcp__plugin_alchemist_alchemist__alchemist_capabilities\n - mcp__plugin_alchemist_alchemist__alchemist_state\n---\n\nBuild an Olbrain agent with Alchemist, following the alchemist skill: check `whoami` first,\nthen find or start the build with the `alchemist` tool, passing the request in the user's\nwords. If `alchemist_state` is in your tool list, call it and follow it; otherwise follow the\n`alchemist` tool's turns.\n\nRequest: $ARGUMENTS\n\nIf the request above is empty, or still reads `$ARGUMENTS`, use what the user asked for in\ntheir message. If there is nothing, ask the user what the agent should do before calling any tool.\n"
}SHA-256 of public snapshot: 9249804525a5e892667feb02e583a4c7e1abec91a6a0a4a7fe7d2bdb3bfcb49c