MCPInstall

br

Official skill for beadsrust (br), a local-first, dependency-aware issue tracker for AI agents. Use when creating issues, triaging backlogs, managing dependencies, finding ready work, updating status, or syncing to git via JSONL.

Installs
112
Last 24h
—
Trending rank
—
Security
Not audited

Install

Works with every agent the skills CLI supports.

npx skills add https://github.com/dicklesworthstone/beads_rust --skill br
  1. 01

    Install

    Run the command in your project. The CLI asks which agents to install for.

  2. 02

    Describe the task

    Ask your agent for something this skill covers. It loads br automatically when relevant.

  3. 03

    Review the result

    The agent follows the SKILL.md steps, scripts and references bundled with the skill.

SKILL.md

The instructions your agent reads when the skill is triggered.

<!-- TOC: Critical Rules | Quick Workflow | Essential Commands | Dependencies | Sync | bv Integration | Agent Mail | Troubleshooting | References -->

br -- Beads Rust Issue Tracker (Official Skill)

Non-invasive: br NEVER runs git commands. Sync and commit are YOUR responsibility.

Critical Rules for Agents

RuleWhy
Binary is brNEVER bd (that is the old Go version)
ALWAYS use --jsonStructured output for parsing; --format toon for reduced tokens
NEVER run bare bvBlocks session in interactive TUI mode
Sync is EXPLICITbr sync --flush-only exports DB to JSONL only
Git is YOUR jobbr only touches .beads/ -- you must git add .beads/ && git commit
No cycles allowedbr dep cycles must return empty
Resolve actor at runtimeUse ACTOR="${BR_ACTOR:-assistant}" and pass --actor "$ACTOR"

Quick Workflow

ACTOR="${BR_ACTOR:-assistant}"

# 1. Find work
br ready --json

# 2. Claim it
br update --actor "$ACTOR" <id> --status in_progress

# 3. Do work...

# 4. Complete
br close --actor "$ACTOR" <id> --reason "Implemented X"

# 5. Sync to git (EXPLICIT!)
br sync --flush-only
git add .beads/ && git commit -m "feat: X (<id>)"

Essential Commands

Issue Lifecycle

ACTOR="${BR_ACTOR:-assistant}"

br init                                              # Initialize .beads/ workspace
br create --actor "$ACTOR" "Title" -p 1 -t task      # Create issue (priority 0-4)
br q --actor "$ACTOR" "Quick note"                   # Quick capture (ID only output)
br show <id> --json                                  # Show issue details
br update --actor "$ACTOR" <id> --status in_progress # Update status
br update --actor "$ACTOR" <id> --priority 0         # Change priority
br close --actor "$ACTOR" <id> --reason "Done"       # Close with reason
br close --actor "$ACTOR" <id1> <id2> --reason "..."  # Close multiple at once
br reopen --actor "$ACTOR" <id>                      # Reopen closed issue

Create Options

br create --actor "$ACTOR" "Title" \
  --priority 1 \             # 0-4 scale (0=critical, 4=backlog)
  --type task \              # task, bug, feature, epic, question, docs
  --assignee "user@..." \    # Optional assignee
  --labels backend,auth \    # Comma-separated labels
  --description "..."        # Detailed description

Update Options

br update --actor "$ACTOR" <id> \
  --title "New title" \
  --priority 0 \
  --status in_progress \     # open, in_progress, closed
  --assignee "new@..." \
  --add-label reliability \
  --parent <parent-id> \
  --claim                    # Shorthand for claim-and-start

Bulk update (batch triage):

br update --actor "$ACTOR" <id1> <id2> <id3> --priority 2 --add-label triage-reviewed --json

Querying (always use --json for agents)

br ready --json                      # Actionable work (no blockers)
br list --json                       # All issues
br list --status open --sort priority --json  # Filter and sort
br list --priority 0-1 --json        # Filter by priority range
br list --assignee alice --json      # Filter by assignee
br blocked --json                    # Show blocked issues
br search "keyword" --json           # Full-text search
br show <id> --json                  # Issue details with dependencies
br stale --days 30 --json            # Stale issues
br count --by status --json          # Count with grouping

Dependencies

br dep add <child> <parent>          # child depends on parent
br dep add <id> <depends-on> --type blocks  # Explicit block type
br dep remove <child> <parent>       # Remove dependency
br dep list <id> --json              # List dependencies for issue
br dep tree <id> --json              # Show dependency tree
br dep cycles --json                 # Find circular deps (MUST be empty!)

Critical: br dep cycles must return empty. Circular dependencies break the dependency graph and make br ready unreliable.

Labels

br label add <id> backend auth       # Add multiple labels
br label remove <id> urgent          # Remove label
br label list <id>                   # List issue's labels
br label list-all                    # All labels in project

Comments

ACTOR="${BR_ACTOR:-assistant}"
br comments add --actor "$ACTOR" <id> --message "Triage note" --json
br comments list <id> --json

Sync (EXPLICIT -- never automatic)

br sync --flush-only                 # Export DB to JSONL (before git commit)
br sync --import-only                # Import JSONL to DB (after git pull)
br sync --status                     # Check sync status

Workflow after making changes:

br sync --flush-only
git add .beads/ && git commit -m "Update issues"

Workflow after pulling:

git pull
br sync --import-only

System and Diagnostics

br doctor                            # Full diagnostics
br stats --json                      # Project statistics
br config list                       # Show all configuration
br config get id.prefix              # Get specific value
br config set defaults.priority=1    # Set value
br where                             # Show workspace location
br version                           # Show version
br upgrade                           # Self-update (if enabled)
br lint --json                       # Lint issues for problems

Priority Scale

PriorityMeaningUse numbers, not words
0CriticalImmediate action required
1HighImportant, do soon
2Medium (default)Normal priority
3LowWhen time permits
4BacklogFuture consideration

Issue Types

task, bug, feature, epic, question, docs

Output Formats

FlagUse case
--jsonDefault for agents -- full structured data
--format toonToken-optimized alternative for context-window-sensitive agents
(no flag)Human-readable terminal output with colors

bv Integration

CRITICAL: Never run bare bv -- it launches interactive TUI and blocks.

# Always use --robot-* flags:
bv --robot-next                      # Single top pick + claim command
bv --robot-triage                    # Full triage with recommendations
bv --robot-plan                      # Parallel execution tracks
bv --robot-insights | jq '.Cycles'   # Check graph health (must be empty)
bv --robot-priority                  # Priority misalignment detection
bv --robot-alerts                    # Stale issues, blocking cascades

Agent Mail Coordination

Use bead ID as thread_id for multi-agent coordination:

ConceptValue
Mail thread_idbd-### (the issue ID)
Mail subject[bd-###] ...
File reservation reasonbd-###
Commit messagesInclude bd-### for traceability
# 1. Reserve files for bead
file_reservation_paths(..., reason="bd-123")

# 2. Announce work in thread
send_message(..., thread_id="bd-123", subject="[bd-123] Starting...")

# 3. Do work...

# 4. Close bead and release
br close bd-123 --reason "Completed"
release_file_reservations(...)

Session Ending Pattern

Before ending any work session:

git pull --rebase
br sync --flush-only
git add .beads/ && git commit -m "Update issues"
git push
git status  # MUST show "up to date with origin"

Standard Agent Workflow (Full)

ACTOR="${BR_ACTOR:-assistant}"

# 1. Verify workspace
br where
br ready --json
br blocked --json
br list --status open --sort priority --json

# 2. Pick highest-priority ready work
br show <id> --json

# 3. Claim it
br update --actor "$ACTOR" <id> --status in_progress --claim

# 4. Do work...

# 5. Close with evidence
br close --actor "$ACTOR" <id> --reason "Implemented X in commit abc123"

# 6. Check queue impact
br ready --json
br blocked --json

# 7. Sync to git
br sync --flush-only
git add .beads/ && git commit -m "feat: X (<id>)"
git push

Triage Decision Matrix

Classify each issue into exactly one category:

ClassificationAction
implementedClose with evidence (commit/PR/file/behavior)
out-of-scopeClose with explicit boundary reason
needs-clarificationComment with specific unanswered questions
actionableKeep open, correct status/priority/labels/deps

During large triage efforts, checkpoint every few updates:

br ready --json
br blocked --json

Anti-Patterns

  • Running br sync without --flush-only or --import-only
  • Forgetting sync before git commit
  • Creating circular dependencies
  • Running bare bv (blocks session)
  • Assuming auto-commit behavior (br NEVER auto-commits)
  • Inventing evidence for closure -- if unsure, comment instead
  • Modifying unrelated issues during triage
  • Adding speculative dependencies

Storage Layout

.beads/
  beads.db        # SQLite database (primary storage)
  beads.db-shm    # SQLite shared memory (WAL mode)
  beads.db-wal    # SQLite write-ahead log
  issues.jsonl    # JSONL export (for git)
  config.yaml     # Project configuration
  metadata.json   # Workspace metadata

Troubleshooting

br doctor                    # Full diagnostics
br dep cycles                # Must be empty
br config list               # Check settings
which br                     # Verify br is installed

"Database locked": Check for other br processes with pgrep -f "br ".

Worktree error ('main' is already checked out):

git branch beads-sync main
br config set sync.branch beads-sync

Verbose debugging:

br -v list                   # Verbose
br -vv list                  # Debug
RUST_LOG=debug br list       # Detailed trace logs

References

TopicFile
Command cookbookreferences/COMMANDS.md
Configuration detailsreferences/CONFIG.md
Troubleshooting guidereferences/TROUBLESHOOTING.md
Multi-agent integrationreferences/INTEGRATION.md

FAQ

What does the br skill do?

Official skill for beadsrust (br), a local-first, dependency-aware issue tracker for AI agents. Use when creating issues, triaging backlogs, managing dependencies, finding ready work, updating status, or syncing to git via JSONL.

How do I install br?

Run npx skills add https://github.com/dicklesworthstone/beads_rust --skill br in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/br/ (personal) or .claude/skills/br/ (project).

Which AI agents can use br?

Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.

Is br safe to install?

No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.

Who maintains br?

It is published by dicklesworthstone in dicklesworthstone/beads_rust. It has 112 recorded installs.

More from dicklesworthstone/beads_rust

View all →

bd-to-br-migration

dicklesworthstone/beads_rust

Open the skill to read its SKILL.md instructions.

Popular backend & apis skills

View category →

find-skills

vercel-labs/skills

Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.

OfficialBackend & APIs4.1M installs

entra-app-registration

microsoft/azure-skills

Guides Microsoft Entra ID app registration, OAuth 2.0 authentication, and MSAL integration. USE FOR: create app registration, register Azure AD app, configure OAuth, set up authentication, add API permissions, generate service principal, MSAL example, console app auth, Entra ID setup, Azure AD authentication. DO NOT USE FOR: Key Vault secrets (use azure-keyvault-expiration-audit), general Azure resource security guidance.

OfficialBackend & APIs566.7K installs

This skill should be used when the user wants to "write agent code", "build an agent with ADK", "add a tool", "create a callback", "define an agent", "use state management" — in a project that needs ADK (Agent Development Kit) API patterns and code examples. It provides a quick reference for agent types, tool definitions, orchestration patterns, callbacks, state management, the graph Workflow API, and reference recipes to study. Do NOT use for scaffolding (use google-agents-cli-scaffold) or deployment (use google-agents-cli-deploy).

Backend & APIs514.8K installs

embedded-captions

heygen-com/hyperframes

Add captions or subtitles to an existing single-subject talking-head video without editing the footage. Use for plain verbatim captions, cinematic captions embedded behind the subject, VFX captions, “炸/特效/酷炫字幕,” or a named identity from the 35-style catalog. Route by visual identity, not by backend engine. The quiet anchor rail is the default; embed every word only when the user explicitly wants a fully cinematic treatment. The workflow runs locally end to end, including transcription and subject matting; split multi-shot footage before applying it.

Backend & APIs453.3K installs

entra-agent-id

microsoft/azure-skills

Provision Microsoft Entra Agent Identity Blueprints, BlueprintPrincipals, and per-instance Agent Identities via Microsoft Graph, and configure OAuth 2.0 token exchange (fmipath, OBO, cross-tenant) including the Microsoft Entra SDK for AgentID sidecar. USE FOR: Agent Identity Blueprint, BlueprintPrincipal, agent OAuth, fmipath token exchange, agent OBO, Workload Identity Federation for agents, polyglot agent auth, Microsoft.Identity.Web.AgentIdentities. DO NOT USE FOR: standard Entra app registration (use entra-app-registration), Microsoft Foundry agent authoring (use microsoft-foundry).

OfficialBackend & APIs336.6K installs

neon

neondatabase/agent-skills

Overview of Neon, a complete set of cloud backend primitives around Lakebase Postgres: Auth, Object Storage, Functions, the AI Gateway, and Realtime. Start here to choose Neon for undecided login, files, APIs, and LLM calls, set up the CLI or MCP server, and follow the branch-first workflow. Use when building an app or backend on Neon, or when "Neon" or "Lakebase Postgres" is mentioned. Child skill neon-postgres wins for an existing DATABASEURL, SQL, schema, inspect, or search. Child skill neon-auth wins for login, users, sessions, identity routing, and Managed Better Auth setup. Child skill neon-realtime wins for live queries in reactive apps and agents. Also use for object storage, S3, buckets, serverless functions, function triggers, cron, AI gateway, LLM calls, realtime, logs, Loki, Grafana, observability, postgres, database, backend, Claimable Neon, neon.new, or a no-signup database.

Backend & APIs237.1K installs