---
name: hivemind-goals
description: Create, track, and read team goals via Hivemind from openclaw. Use whenever the user mentions a goal, objective, target, milestone, or asks to track progress on something measurable. ALSO use when the user says "task", "todo", "work item", "remind me to", "fix X", or any actionable work item — the goal system replaced the legacy `hivemind tasks` CLI and now covers both objectives and tasks.
allowed-tools: hivemind_search, hivemind_read, hivemind_index, hivemind_goal_add
---

# Hivemind Goals (openclaw)

OpenClaw exposes purpose-built tools for goals. Use them directly — do NOT try to write files via the host filesystem.

## Tools

- `hivemind_goal_add({ text })` — create a new goal. Returns `goal_id` (UUID). Status starts at `opened`.
- `hivemind_search({ query })` — search Hivemind shared memory (summaries + sessions). Use this when the user asks "what's already there" before creating a duplicate.
- `hivemind_read({ path })` — read the full content of a specific Hivemind path.
- `hivemind_index({})` — list everything in memory.

## Workflow when the user expresses a goal

1. (Optional) `hivemind_search` first to surface any existing related goal.
2. `hivemind_goal_add({ text: "<short description>" })` — capture the returned `goal_id`.
3. Confirm to the user with the goal_id and that the goal is team-visible.

## Capture a task for later (with resumable context)

When the user **parks a tangential task** mid-session — "save this for later", "remind me to …", "don't let me forget …", "let's do X later" — store enough **context to resume cold** later, not just a one-liner. Put the full package in the `text` of `hivemind_goal_add`:

```
hivemind_goal_add({ text:
  "Add rate-limiting to the webhook handler\n\n" +
  "Start here: add a per-IP token bucket on the handler entry path\n" +
  "Files: src/webhook/handler.ts:120-160, src/webhook/limits.ts\n" +
  "Branch: feat/webhook-hardening\n" +
  "Run: pnpm test webhook\n" +
  "Why: bursty clients hammer the endpoint; defer until retry-backoff lands" })
```

Line 1 is the label. Fill `Start here / Files / Branch / Run / Why` from the conversation; `Start here:` (the concrete first action) matters most. (OpenClaw's `hivemind_goal_add` has no provenance flag, so the row is tagged `manual` — that's fine; the context is what matters.)

## Resume a parked task (automatic context transfer)

When the user says "let's work on that task / goal" or "pick up the `<X>` task":

1. `hivemind_search({ query: "<topic>" })` or `hivemind_index({})` to locate the parked goal, then `hivemind_read({ path: "memory/goal/<owner>/opened/<goal_id>.md" })` to pull the **full** context package back.
2. Read it as your working context and begin from `Start here:` using the `Files` / `Branch` / `Run` lines — continue as if the context was never lost.

(Status-move tools aren't exposed on OpenClaw, so leave the goal where it is and just resume the work.)

## What NOT to do

- Do NOT write files anywhere under `~/.deeplake/memory/`. OpenClaw's runtime does not route filesystem writes to the Deeplake tables — only the `hivemind_*` tools above do.
- Do NOT use `hivemind_search` to *create* anything — it's read-only.

---
name: hivemind-graph
description: 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).
allowed-tools: hivemind_graph_search, hivemind_graph_neighborhood
---

# 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.