메뉴
Graph-aware task triage with bv and br. Use when prioritizing work, finding bottlenecks, tracking dependencies, or managing local issues across projects.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Consult Fable (primary oracle) for expert second opinions; escalate to GPT-5.5-Pro only for extremely important or complex tasks (always paired with Fable). Use for complex decisions, architecture choices, debugging hard problems, or when user says "consult oracles", "ask the experts", or wants a second opinion.
Run iterative oracle + agent hardening loop on any artifact (designs, plans, beads, architecture) until findings converge to near-zero. Combines /swarm-oracle with /swarm-review in alternating rounds. Use for the full hardening cycle, not just a single oracle pass. For oracle-only, use /swarm-oracle. For bead-only hardening, use /swarm-beads-quality.
Run 2x oracle sessions (FOR + AGAINST stances) to validate design decisions, plans, or bead readiness. Default = two Fable subagents; escalate to PAL 2x GPT-Pro (always paired with Fable) for extremely important or complex validations. Use after design rounds, before implementation, or to challenge architecture decisions.
Act as a wise, effective teacher whose goal is to make the human deeply understand the work done in this session (a change, a bug fix, a feature, a design) — i.e. sync the human's mental model up to the agent's. Use when the user says "sync-human", "sync me up", "teach me this session", "make sure I understand", "walk me through what we did", "quiz me on this", or "I want to actually understand this PR/change", or otherwise wants Socratic, gated, incremental teaching with comprehension checks rather than a one-shot summary. Drives understanding at both high level (motivation, impact) and low level (business logic, edge cases) using a running checklist and quizzes.
MCP Agent Mail for multi-agent coordination. Use when agents need file locks, messaging, inboxes, or conflict prevention. Handles macro_start_session, file_reservation_paths, send_message, threading, pre-commit guards.
Retrieve API tokens, keys, and credentials Oystein has stored locally. Use whenever code, scripts, or shell commands need a secret value: GitHub tokens, Cloudflare, HubSpot, Slack, Zendesk, Jira, Sentry, Anthropic, Apify, Browserbase, Google OAuth, Huma. Use BEFORE searching shell history, session logs, dotfiles, or the filesystem — the canonical store is documented here and the values are reachable via two fish helpers. Also use when adding, rotating, or removing a credential.
| name | beads-bv |
| description | Graph-aware task triage with bv and br. Use when prioritizing work, finding bottlenecks, tracking dependencies, or managing local issues across projects. |
Core Insight: Your backlog is a directed graph. PageRank finds what everything depends on. Betweenness finds bottlenecks. The math knows your priorities better than your gut.
bv # WRONG — launches TUI, blocks terminal
bv --robot-triage # CORRECT — JSON output for agents
NEVER run bare bv in agent contexts.
| Command | Returns | Use When |
|---|---|---|
--robot-triage | THE MEGA-COMMAND: recommendations + blockers + health | What should I work on? |
--robot-next | Single top pick + claim command | Just the one thing |
--robot-plan | Parallel execution tracks with unblocks | What can run concurrently? |
--robot-insights | All metrics + cycles + density + k-core + slack | Deep analysis |
--robot-priority | Priority misalignments with confidence | Am I prioritizing wrong? |
| Command | Returns | Use When |
|---|---|---|
--robot-label-health | Per-label: health_level, velocity, staleness | Which domain is struggling? |
--robot-label-flow | Cross-label dependencies, bottleneck_labels | Inter-team blockers |
--robot-label-attention | Attention-ranked labels | Where to focus? |
--robot-alerts | Stale issues, blocking cascades, priority mismatches | What's rotting? |
--robot-suggest | Duplicates, missing deps, cycle breaks | Hygiene |
| Command | Returns | Use When |
|---|---|---|
--robot-history | Bead-to-commit correlations | Change tracking |
--robot-causality <id> | Timeline, blockers, insights | Why did this take so long? |
--robot-related <id> | File/commit overlap, clusters | What's connected? |
--robot-file-beads <path> | Beads that touched a file | Code ownership |
| Command | Returns | Use When |
|---|---|---|
--robot-diff --diff-since <ref> | New/closed/modified since ref | What changed? |
--as-of <ref> | Historical point-in-time | Time-travel |
--robot-search | Search results as JSON | Find beads |
--search-mode hybrid | Text + graph ranking | Smart search |
Full command reference: COMMANDS.md
# 1. What should I work on?
bv --robot-triage | jq '.recommendations[0]'
# 2. Claim it
br update bd-123 --status in_progress
# 3. Do the work...
# 4. Done
br close bd-123 --reason "Implemented in abc123"
# 5. Next
bv --robot-triage
bv --robot-plan --label backend # Scope to label's subgraph
bv --robot-insights --as-of HEAD~30 # Historical point-in-time
bv --recipe actionable --robot-plan # Only unblocked items
bv --recipe high-impact --robot-triage # Top PageRank scores
bv --robot-triage --robot-triage-by-track # Group by parallel streams
bv --robot-triage --robot-triage-by-label # Group by domain
bv --robot-alerts --severity=critical # Filter alerts
| Metric | High Score Means |
|---|---|
| PageRank | Everything depends on this — fix first |
| Betweenness | Bottleneck — blocks multiple paths |
| Cycles | Broken graph — fix immediately |
| K-Core | Structural strength (core membership) |
| Articulation | Cut vertex — removal disconnects graph |
| Pattern | Meaning | Action |
|---|---|---|
| High PageRank + High Betweenness | Critical bottleneck | Drop everything, fix this |
| High PageRank + Low Betweenness | Foundation piece | Important but not blocking |
| Low PageRank + High Betweenness | Unexpected chokepoint | Investigate why |
Full metrics: METRICS.md
br ready --json # What's unblocked?
br create "Title" -d "desc" # New issue
br update bd-123 --status in_progress # Working on this
br close bd-123 --reason "Done" # Done
br dep add bd-123 bd-456 # Add dependency
br dep remove bd-123 bd-456 # Break cycle
| Problem | Cause | Fix |
|---|---|---|
bv hangs | TUI launched | Use --robot-* flags |
| Cycles detected | Circular dependency | br dep remove to break |
| Phase 2 timeout | Large graph (>500 nodes) | Check status field |
| Empty metric maps | Phase 2 still running | Check status flags |
| Inconsistent outputs | Different data | Compare data_hash |
# Tools working?
bv --robot-triage >/dev/null && br list >/dev/null && echo "OK"
# Graph healthy?
bv --robot-insights | jq '{cycles: .Cycles, density: .density}'
# cycles must be [], density < 0.3 is healthy
| Need | Read |
|---|---|
| All robot commands + flags | COMMANDS.md |
| All metrics explained | METRICS.md |
| jq recipes, morning triage | RECIPES.md |