Skip to content

activeloopai/hivemind / harnesses/openclaw/skills/hivemind-graph

hivemind-graph

Verified

Query the local AST-derived code graph (functions, classes, calls, imports) for structural codebase questions — what calls X, what does Y import, where is Z defined, blast radius of a change. The graph rebuilds automatically after each agent turn; use hivemind_graph_search and hivemind_graph_neighborhood tools (no manual build step).

Hivemind Code Graph (OpenClaw)

A deterministic, AST-derived map of the current repository — every function, class, method, interface, type, enum, const, and module, plus the edges between them (calls, imports, extends, implements, method_of).

The graph builds and refreshes automatically after each turn (gated by rate limit + git diff). You never run a build command — just call the graph tools.

Set plugins.entries.hivemind.config.tuning.HIVEMIND_GRAPH_CWD in ~/.openclaw/openclaw.json to the git root of the project you want indexed when the gateway's working directory is not the repo (then restart the gateway).

Use the graph as a fast INDEX to locate the few files/symbols that matter, then use the host's read/exec tools on the real source. It is not a substitute for reading source files.

When to use this skill

Activate when the user asks a structural / relational question about the code:

  • "What calls pushSnapshot?" / "Who uses this function?"
  • "What does deeplake-pull.ts import?" / "What depends on X?"
  • "Where is GraphSnapshot defined?" / "Find the function that handles Y."
  • "What are the main subsystems / the architecture here?"
  • "If I change this signature, what's affected?"

Tools

  • hivemind_graph_search({ pattern }) — search symbols by substring (or multi-token AND with +, e.g. auth+handler). Returns matches with 1-hop neighbors (callers, callees, imports). Start here.
  • hivemind_graph_neighborhood({ file }) — every symbol in a repo-relative file path plus its cross-file neighbors.

Workflow

  1. Broad structural question? hivemind_graph_search({ pattern: "<symbol>" }).
  2. Know the file? hivemind_graph_neighborhood({ file: "src/hooks/capture.ts" }).
  3. Need the actual code? Open the source_file:line from the tool output with the host read tool — don't answer from the graph alone.

When NOT to use this skill

  • Reading the body of a symbol you already located → use the host read tool.
  • Code that isn't committed/built yet — the graph can lag uncommitted edits.
  • Languages outside TypeScript, JavaScript, and Python — fall back to grep.

Anti-patterns

  • Zero incoming callers does NOT mean dead code. Instance-method dispatch and dynamic calls are not fully resolved.
  • The graph can be stale. Prefer live source for files edited in this session.
  • pattern is lexical, not semantic — try multiple keywords if the first misses.
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 467kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 319kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 319kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 319kUpdated Claude CodeCodexVerifiedInstall