openclaw-runtime-git
Manage the openclaw-runtime git repository and its 13 agent workspace submodules. Use when adding a new agent workspace, cloning the runtime repo, updating submodule references, committing changes to the parent repo, or troubleshooting submodule state. Triggers on tasks involving workspace repos, submodule operations, agent onboarding git setup, or any git operations in ~/.openclaw/.
What this skill does
# openclaw-runtime-git Git workflow patterns for the openclaw-runtime parent repo and its agent workspace submodules. ## Repo Structure `~/.openclaw/` is the parent repo (`openclaw-runtime`). Each `workspace*/` directory is a git submodule pointing at its own GitHub repo under `delorenj/agent-oc-*`. ### Submodule Map | Directory | GitHub Repo | |---|---| | `workspace/` | `delorenj/agent-oc-cack` | | `workspace-cack-app/` | `delorenj/agent-oc-lala` | | `workspace-dumpling/` | `delorenj/agent-oc-dumpling` | | `workspace-eng/` | `delorenj/agent-oc-eng` | | `workspace-grolf/` | `delorenj/agent-oc-grolf` | | `workspace-infra/` | `delorenj/agent-oc-infra` | | `workspace-lenoon/` | `delorenj/agent-oc-lenoon` | | `workspace-overworld/` | `delorenj/agent-oc-pepe` | | `workspace-rar/` | `delorenj/agent-oc-rar` | | `workspace-rererere/` | `delorenj/agent-oc-rererere` | | `workspace-svgme/` | `delorenj/agent-oc-momo` | | `workspace-tonny/` | `delorenj/agent-oc-tonny` | | `workspace-wean/` | `delorenj/agent-oc-tongy` | ## Hook Protection A git hook guards workspace paths from accidental staging via `git add`. When adding or committing submodule references in the parent repo, use `command git` to bypass: ```bash command git add workspace-<name> command git commit -m "message" ``` This is safe and expected for submodule pointer commits. The hook exists to prevent accidentally staging workspace *contents* as tracked files in the parent repo. ## Common Workflows ### Clone the Runtime Repo (Fresh Machine) ```bash git clone --recurse-submodules [email protected]:delorenj/<runtime-repo>.git ~/.openclaw ``` Or if already cloned without submodules: ```bash cd ~/.openclaw git submodule update --init --recursive ``` ### Add a New Agent Workspace as a Submodule 1. Create the GitHub repo: ```bash gh repo create delorenj/agent-oc-<name> --private ``` 2. Initialize the workspace if it doesn't have a git repo yet: ```bash cd ~/.openclaw/workspace-<name> git init && git add -A && git commit -m "initial commit" ``` 3. Add the remote and push: ```bash gh repo create delorenj/agent-oc-<name> --private --source=~/.openclaw/workspace-<name> --push ``` Or if the repo already exists: ```bash git remote add origin [email protected]:delorenj/agent-oc-<name>.git git push -u origin main ``` 4. Register as submodule in the parent repo: ```bash cd ~/.openclaw git submodule add [email protected]:delorenj/agent-oc-<name>.git workspace-<name>/ ``` If the directory already exists with a `.git`, git will say "Adding existing repo" which is correct. 5. Commit in the parent: ```bash command git add .gitmodules workspace-<name> command git commit -m "feat: add workspace-<name> as submodule" ``` ### Update a Submodule Reference (After Pushing Changes in a Workspace) When you commit and push inside a workspace, the parent repo sees a dirty submodule pointer. To record the new commit: ```bash cd ~/.openclaw command git add workspace-<name> command git commit -m "chore: update workspace-<name> submodule ref" ``` ### Update All Submodules to Latest Remote ```bash cd ~/.openclaw git submodule update --remote --merge ``` Then commit any updated pointers: ```bash command git add workspace* command git commit -m "chore: update all workspace submodule refs" ``` ### Check Submodule Status ```bash git submodule status # Or more detail: git submodule foreach --quiet 'echo "$sm_path: $(git log --oneline -1)"' ``` ### Remove a Submodule ```bash git submodule deinit -f workspace-<name> rm -rf .git/modules/workspace-<name> git rm -f workspace-<name> git commit -m "chore: remove workspace-<name> submodule" ``` ## Naming Convention - Workspace directory: `workspace-<suffix>/` (suffix matches agent id or is descriptive) - GitHub repo: `delorenj/agent-oc-<persona-name>` (lowercase persona name) - The main workspace (`workspace/`) is an exception with no suffix ## Gotchas - **Never `git add -A` or `git add .` in the parent repo** without checking what you're staging. The hook guards against this, but be aware. - **Submodules track a specific commit, not a branch.** After pushing changes inside a workspace, you must also update and commit the submodule pointer in the parent. - **Detached HEAD in submodules** is normal after `git submodule update`. To work in a submodule, `cd` into it and `git switch main` first. - **`.gitmodules` is the source of truth** for submodule URL mappings. If a remote URL changes, update it here and run `git submodule sync`.
Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.