agent-environment-retr…
Use when a completed session needs an agent-environment retrospective. Not for an engineering retrospective from telemetry: use…
Use when the user runs /workspace-unfreeze on a frozen path to make it editable again. Not for automated or unattended runs: requires explicit human invocation.
Claude Code
$ npx -y skills add OutlineDriven/odin-claude-plugin --skill workspace-unfreeze --agent claude-code
Codex
$ npx skills add OutlineDriven/odin-claude-plugin --skill workspace-unfreeze -a codex -y
Cursor
$ npx skills add OutlineDriven/odin-claude-plugin --skill workspace-unfreeze -a cursor -y
Gemini CLI
$ npx skills add OutlineDriven/odin-claude-plugin --skill workspace-unfreeze -a gemini-cli -y
GitHub Copilot
$ npx skills add OutlineDriven/odin-claude-plugin --skill workspace-unfreeze -a github-copilot -y
OpenCode
$ npx skills add OutlineDriven/odin-claude-plugin --skill workspace-unfreeze -a opencode -y
Windsurf
$ npx skills add OutlineDriven/odin-claude-plugin --skill workspace-unfreeze -a windsurf -y
name: workspace-unfreeze description: 'Use when the user runs /workspace-unfreeze on a frozen path to make it editable again. Not for automated or unattended runs: requires explicit human invocation.' disable-model-invocation: true
| Field | Bound contract | |---|---| | Trigger | The user runs /workspace-unfreeze on a frozen path | | Authority | Human-gated: requires explicit human invocation, previews the target marker file and the deletion consequence, and asks before deleting the freeze lock marker file; otherwise reversible local: deletes only the freeze lock marker file; rollback is recreating the marker file. No remote mutation. | | Side effect | Deletes the freeze lock marker file for the named path. The deletion is unrecoverable, but the marker is re-creatable by re-creating the `<path>.freeze-lock` file beside the path with content naming the target path | | Done | The named path is editable again (no freeze lock marker present for it) |
1. Receive the path argument from the explicit /workspace-unfreeze invocation. Do not act on any model-generated or inferred path. Done when: the path argument is confirmed as human-supplied. 2. Resolve the marker path from the invocation: accept an explicit marker path from the human, or derive it from the freeze convention: a marker file named `<path>.freeze-lock` beside the frozen path, whose content names the target path. Verify the resolved file exists and names the target path. If it does not, treat as Marker not found. Never glob or scan for candidate markers. Done when: the marker file path is resolved and verified, or the path is confirmed already editable. 3. Before deleting, preview the marker file path and state the consequence: the `<path>.freeze-lock` marker on that path will be removed and the path will become editable. Obtain explicit human confirmation. Done when: the human has seen the preview and the consequence and confirmed deletion. 4. After human confirmation, delete only that single marker file. Do not delete any other file, do not edit the protected path's contents, and do not touch any other freeze marker. Done when: the single marker file is deleted. 5. Confirm the marker file is gone and the named path is editable again. Done when: the marker file is absent and the path is editable.
Terminal report naming the unfrozen path (or stating it was already editable) and confirming the freeze lock marker is absent.
Formerly the ODIN Claude Plugin. The repository URL is unchanged. Outline-Driven Development, nicknamed ODIN, is a highly opinionated code-agent skill library: principles-first engineering, surgical editing, and workflow automation, published as installable
Use when a completed session needs an agent-environment retrospective. Not for an engineering retrospective from telemetry: use…
Use when a repo needs agent setup, AGENTS.md added or made lean, CLAUDE.md audited, or agent instructions scored or pruned. Not…
Use when a human explicitly asks for a full repository agent-compatibility pass returning a scored report with prioritized fixes.…
Use when setting up a project, auditing agent command permissions, or asking which read-only bash commands and domains to allow.…
Use when asked to build or review a CLI intended for coding agents and return flag-driven, pipeline-safe, idempotent design…
Use when the user asks to make the skills framework work in a new harness, IDE, or CLI. Not for remote, credential, publish,…
You MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or…
Ask which skill or flow fits your situation. A router over the skills in this repo.