一键导入
beads-br
Beads Rust issue tracker (br). Use when tracking tasks, managing dependencies, finding ready work, or syncing issues to git via JSONL.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
Beads Rust issue tracker (br). Use when tracking tasks, managing dependencies, finding ready work, or syncing issues to git via JSONL.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | beads-br |
| description | Beads Rust issue tracker (br). Use when tracking tasks, managing dependencies, finding ready work, or syncing issues to git via JSONL. |
Non-invasive: br NEVER runs git commands. Sync and commit are YOUR responsibility.
| Rule | Why |
|---|---|
ALWAYS use --json | Structured output for parsing |
NEVER run bare bv | Blocks session in TUI mode |
| Sync is EXPLICIT | br sync --flush-only after changes |
| Git is YOUR job | br only touches .beads/ directory |
| No cycles allowed | br dep cycles must return empty |
# 1. Find work
br ready --json
# NOTE (br 0.1.8): `br ready` is currently broken in some workspaces due to an
# internal SQL bug. Workaround: use `bv --recipe actionable --robot-plan` (or
# `bv --robot-triage`) + `br list --json`.
# 2. Claim it
br update <id> --status in_progress
# 3. Do work...
# 4. Complete
br close <id> --reason "Implemented X"
# 5. Sync to git (EXPLICIT!)
br sync --flush-only
git add .beads/ && git commit -m "feat: X (<id>)"
# Lifecycle
br init # Initialize .beads/
br create "Title" -p 1 -t task # Create (priority 0-4)
br update <id> --status in_progress # Claim work
br close <id> --reason "Done" # Complete
br reopen <id> # Reopen if needed
# Querying (always use --json for agents)
br ready --json # Actionable work (not blocked)
br list --json # All issues
br blocked --json # What's blocked
br search "keyword" # Full-text search
br show <id> --json # Issue details
# Dependencies
br dep add <child> <parent> # child depends on parent
br dep cycles # MUST be empty!
br dep tree <id> # Visualize dependencies
# Sync (EXPLICIT - never automatic)
br sync --flush-only # DB → JSONL (before git commit)
br sync --import-only # JSONL → DB (after git pull)
# Skills sync status (canonical vs global skills)
br skills sync-status --json # JSON summary of drift
br skills sync-status --verbose # Per-skill details
# System
br doctor # Health check
br config list # Show configuration
| Priority | Meaning |
|---|---|
| 0 | Critical |
| 1 | High |
| 2 | Medium (default) |
| 3 | Low |
| 4 | Backlog |
CRITICAL: Never run bare bv — it launches interactive TUI and blocks.
# Always use --robot-* flags:
bv --robot-next # Single top pick
bv --robot-triage # Full triage
bv --robot-plan # Parallel execution tracks
bv --robot-insights | jq '.Cycles' # Check graph health
Use bead ID as thread_id for multi-agent coordination:
file_reservation_paths(..., reason="br-123")
send_message(..., thread_id="br-123", subject="[br-123] Starting...")
# Work...
br close br-123 --reason "Completed"
release_file_reservations(...)
git pull --rebase
br sync --flush-only
git add .beads/ && git commit -m "Update issues"
git push
git status # Verify clean
br sync without --flush-only or --import-onlybv.beads/
├── beads.db # SQLite (primary)
├── issues.jsonl # Git-friendly export
└── config.yaml # Optional config
br doctor # Full diagnostics
br dep cycles # Must be empty
br config list # Check settings
Worktree error ('main' is already checked out):
git branch beads-sync main
br config set sync-branch beads-sync
| Topic | File |
|---|---|
| Full command reference | COMMANDS.md |
| Configuration details | CONFIG.md |
| Troubleshooting guide | TROUBLESHOOTING.md |
| Multi-agent patterns | INTEGRATION.md |
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.