- name
SKILL.md
Die Skill-Datei bleibt im Repository des Herausgebers.
Fügen Sie den kopierten Befehl in ein Terminal ein. Er installiert diese SKILL.md in dem jeweiligen Agenten.
npx skills add activeloopai/hivemind --skill hivemind-goals -a cursor -yFügen Sie den kopierten Befehl in ein Terminal ein. Er installiert diese SKILL.md in dem jeweiligen Agenten.
npx skills add activeloopai/hivemind --skill hivemind-goals -a claude-code -yFügen Sie den kopierten Befehl in ein Terminal ein. Er installiert diese SKILL.md in dem jeweiligen Agenten.
npx skills add activeloopai/hivemind --skill hivemind-goals -a codex -yFügen Sie den kopierten Befehl in ein Terminal ein. Er installiert diese SKILL.md in dem jeweiligen Agenten.
npx skills add activeloopai/hivemind --skill hivemind-goals -a grok -ySenden Sie die kopierte Nachricht in einem Grok Bot-Chat. Der Bot ruft diese SKILL.md von GitHub ab und fügt sie den Skills hinzu, die alle Ihre Bots gemeinsam nutzen.
Install this skill: https://github.com/activeloopai/hivemind/tree/HEAD/harnesses/codex/skills/hivemind-goalsVom Herausgeber
Track goals as Markdown files inside the Deeplake virtual filesystem. Each file is one row in a dedicated team-shared table — the path encodes the structural metadata, the file body holds the human-readable description.
Activate when the user expresses any of:
hivemind tasks CLI — there is no separate task store)For "list my goals" → run ls ~/.deeplake/memory/goal/<userName>/opened/ and ls ~/.deeplake/memory/goal/<userName>/in_progress/. If empty, ask the user if they want to create one.
~/.deeplake/memory/goal/<owner>/<status>/<goal_id>.md
<owner> — user identifier (use the userName from hivemind whoami or the credentials)<status> — one of opened, in_progress, closed<goal_id> — UUIDv4 you generate at create timePath encoding is the source of truth. The owner, status, and goal_id come from the path — NOT from the file body. Do NOT write owner/status/goal_id inside the file content.
Goal file body — plain markdown, free form:
ship the goals-graph feature
Notes: route every write through the VFS, no separate CLI.
Due: 2026-05-30.
The first line is the human-readable label (what goal list and the SessionStart banner show). Anything else is free notes.
When the user expresses a new goal:
hivemind whoami (use the userName, e.g. emanuele.fenocchi).uuidgen or node -e 'console.log(crypto.randomUUID())'.~/.deeplake/memory/goal/<owner>/opened/<uuid>.md with the goal description as body.Use this 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". The value is NOT the one-liner — it's storing enough context to resume cold in a future session without the user re-explaining anything.
Write it via the CLI so the row is tagged agent: capture, which separates parked side-tasks from hand-made goals:
hivemind goal add --agent capture "Add rate-limiting to the webhook handler
Start here: add a per-IP token bucket on the handler entry path
Files: src/webhook/handler.ts:120-160, src/webhook/limits.ts
Branch: feat/webhook-hardening
Run: pnpm test webhook
Why: bursty clients hammer the endpoint; agreed to defer until the retry-backoff work lands"
goal list and the SessionStart banner show.Start here / Files / Branch / Run / Why from the live conversation. Include only the lines you can fill; Start here: (the concrete first action) matters most.When the user says "let's work on that task / that goal", "let's start the <X> task", or "pick up the parked <X>", pull its stored context back into the session and continue — the user should NOT have to re-explain anything.
hivemind goal list --mine and match the user's reference to a goal_id. If ambiguous, show the candidates and ask.hivemind goal get <goal_id> prints the full package (Start here / Files / Branch / Run / Why). Read it as your working context — goal list only shows the first line, so always use goal get for the full body.mv ~/.deeplake/memory/goal/<owner>/opened/<uuid>.md ~/.deeplake/memory/goal/<owner>/in_progress/<uuid>.mdFiles:, switch to the Branch: if given, and begin from Start here:. You are resumed — continue as if the context was never lost.ls ~/.deeplake/memory/goal/<owner>/opened/
ls ~/.deeplake/memory/goal/<owner>/in_progress/
Then cat each <uuid>.md to read the body.
# Use Read + Edit (or Write) on the existing file. The VFS handles
# version-bumping — every write produces a fresh row in the
# hivemind_goals table.
mv ~/.deeplake/memory/goal/<owner>/opened/<uuid>.md ~/.deeplake/memory/goal/<owner>/in_progress/<uuid>.md
mv between status folders is an atomic version-bump. The file body carries over unchanged.
Two equivalent ways:
# Explicit mv to closed (recommended — clearest intent)
mv ~/.deeplake/memory/goal/<owner>/in_progress/<uuid>.md ~/.deeplake/memory/goal/<owner>/closed/<uuid>.md
# Or: rm (the VFS interprets rm on a goal path as a soft-close)
rm ~/.deeplake/memory/goal/<owner>/opened/<uuid>.md
Important: rm does NOT actually delete the goal. It is a soft-close — the VFS writes a new version with status=closed. The goal remains in the team-shared table for audit. There is no hard-delete in v1.
mv ~/.deeplake/memory/goal/<old-owner>/<status>/<uuid>.md ~/.deeplake/memory/goal/<new-owner>/<status>/<uuid>.md
Goal ownership lives in the path; the file body carries over unchanged.
owner, status, or goal_id inside the file body. The path is the source of truth — duplicating in the body causes drift.opened, in_progress, closed.mv. The VFS rejects goal_id renames.Every write goes to a team-shared table on Deeplake (hivemind_goals). Other team members see your goals in their SessionStart context and via direct ls / cat on the same paths in their own VFS. No explicit sharing step needed.
Create, track and update team goals via the Deeplake virtual filesystem at memory/goal/. Use whenever the user mentions a goal, objective, target, milestone, or asks to track progress on something mea
---name: hivemind-goalsdescription: Create, track and update team goals via the Deeplake virtual filesystem at memory/goal/. Use whenever the user…---# harnesses/codex/skills/hivemind-goals/SKILL.mdÜbersicht
Create, track and update team goals via the Deeplake virtual filesystem at memory/goal/. 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.
FAQ
Laden Sie harnesses/codex/skills/hivemind-goals/SKILL.md vom Herausgeber herunter oder kopieren Sie den Pfad und öffnen Sie das Repository. PlugMCP listet den Skill und hostet die Datei nicht.
Der Herausgeber pflegt es unter https://github.com/activeloopai/hivemind.
Claude, Cursor, Codex und Grok Build können eine SKILL.md lesen, die Sie aus dem Repository des Herausgebers hinzufügen. Grok Bot installiert sie, wenn Sie den Link zum GitHub-Ordner des Skills in einem Chat senden.