Hivemind Graph

What it does

When your agent uses it

• The user asks structural questions about the codebase — what calls X?
• What does Y import?
• Where is Z defined?
• What is the architecture / which subsystems exist?

Example prompts

• “what calls X?”
• “what does Y import?”
• “where is Z defined?”
• “/hivemind-graph”

Requirements

• Pre-approved tools (allowed-tools): Bash

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

1. 1Broad? Start at index.md to see subsystems and the biggest files.
2. 2Looking for a symbol? find/ (or query/) → pick the handle.
3. 3Want relationships? show/ / neighborhood/ → callers/callees, imports.
4. 4Tracing a flow? path//. Change impact? impact/.
5. 5Need the actual code? Take the source_file:line and Read it — don't answer from the graph alone.

What it can do on your machine

Read from SKILL.md and the folder at commit e054fb1. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves these tools, so the agent can use them without asking each time:

  • Bash

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  No scripts in the folder and no shell commands in SKILL.md (its code samples are bash).

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Hivemind Graph loads about 1.2k tokens when it runs. Until then it costs about 104 tokens; SKILL.md has 446 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~104

When it runs · the whole SKILL.md, loaded when a task matches

~1.2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

• NotePre-approves every shell command (allowed-tools: Bash)SKILL.md

  allowed-tools: Bash

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from activeloopai/hivemind at commit e054fb1, republished under its Apache-2.0 licence (© activeloopai). 446 words, ~1,208 tokens.

name

hivemind-graph

description

Query the local code graph (functions, classes, calls, imports) through the Deeplake mount at memory/graph/. Use when the user asks structural questions about the codebase — "what calls X?", "what does Y import?", "where is Z defined?", "what is the architecture / which subsystems exist?". The graph is an AST-derived map of the repo, queried as files (no build needed — it rebuilds automatically).

allowed-tools

Bash

cat ~/.deeplake/memory/graph/index.md
#   Overview: node/edge counts, kind breakdown, top files by node count.

cat ~/.deeplake/memory/graph/query/<pattern>   # START HERE (the 2-in-1)
#   Search + expand the top matches with their 1-hop neighbors (callers,
#   callees, imports, heritage). Multi-token AND: query/<a>+<b>.

cat ~/.deeplake/memory/graph/find/<pattern>
#   Case-insensitive substring search on node id + label (max 50 hits).
#   Prints numbered handles [1] [2] ... saved for this worktree.

cat ~/.deeplake/memory/graph/show/<handle-or-pattern>
#   <handle>: a digit from a prior find/ (e.g. 3).
#   <pattern>: a substring → unique node detail, or a candidate list.
#   Output: the node + its 1-hop neighbors grouped by edge relation.

cat ~/.deeplake/memory/graph/neighborhood/<file>
#   Every symbol in a file + its cross-file neighbors (callers/callees/imports).

cat ~/.deeplake/memory/graph/impact/<pattern>
#   Transitive dependents — the blast radius of changing a symbol.

cat ~/.deeplake/memory/graph/path/<from>/<to>
#   Shortest dependency path between two symbol patterns (trace a flow across files).

cat ~/.deeplake/memory/graph/layers      # architectural layers / subsystems
cat ~/.deeplake/memory/graph/tour        # deterministic guided walkthrough

© activeloopai, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in harnesses/codex/skills/hivemind-graph of activeloopai/hivemind.

Open the folder on GitHubat commit e054fb1