beads-operations
Use when running, maintaining, or troubleshooting beads (`bd`) day-to-day — deciding bd vs TodoWrite, Joe's shared-server conventions (`bd init…
Skill by joeblackwaslike
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/joeblackwaslike-beads-operations
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: backend, productivity
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/beads-operations
What's inside
- Skill name
beads-operations- Description
- Use when running, maintaining, or troubleshooting beads (`bd`) day-to-day — deciding bd vs TodoWrite, Joe's shared-server conventions (`bd init --shared-server --skip-agents`, the shared Dolt server on port 3308), the ready→claim→note→close workflow, compaction recovery, recovering from broken/nasty beads states (stale ports, orphan/duplicate Dolt servers, db-name mismatch, "database is locked"), and taming the `bd prime` session-start injection (the workflow preamble, `PRIME.md` customization, neutralizing the conservative git policy). Invoke on "beads is broken", "bd won't start", "set up beads in this project", "how do I track this", "bd prime is noisy", "change the session-start beads text", or any beads failure. For the raw CLI reference, use `working-with-beads`.
- License
- MIT
- Metadata
- last_updated: 2026-06-22
- Instructions
- 35 lines in SKILL.md · view on GitHub
Files (6)
- SKILL.md
- conventions.md · references/
- long-term-maintenance.md · references/
- prime-customization.md · references/
- troubleshooting.md · references/
- workflows.md · references/
SKILL.md (first lines)
# Beads operations Opinionated guidance for *running* beads the way Joe does, plus a troubleshooting/maintenance runbook. For the exhaustive command reference, use the `working-with-beads` skill. > **Precedence:** This skill **supersedes the conventions in the bundled third-party `beads` plugin skill.** Where they differ (especially server setup), follow this skill. The plugin is kept for its lifecycle hooks, commands, and task-agent — not its convention guidance. ## Decision: bd vs TodoWrite Ask "will I need this context in 2 weeks / across sessions?" — **yes → `bd`** (durable, dependency-aware, survives compaction); **no → TodoWrite** (this-hour working copy). They layer: read a bead → spin up TodoWrite items for the current hour → update the bead's notes → TodoWrite is discarded, the bead persists. ## Reference map - [`references/conventions.md`](references/conventions.md) — the **mandatory** setup: `--shared-server`, the shared Dolt server, port 3308, `--skip-agents`, env vars, the `bd` shell wrapper. - [`references/workflows.md`](references/workflows.md) — the core loop, compaction recovery, discovered-from side-quests. - [`references/troubleshooting.md`](references/troubleshooting.md) — symptom → diagnosis → recovery for the nasty states. - [`references/long-term-maintenance.md`](references/long-term-maintenance.md) — version pin/bump, server lifecycle, backup/export, db hygiene, compaction. - [`references/prime-customization.md`](references/prime-customization.md) — what `bd prime` injects, how `bd setup claude` wires the SessionStart/PreCompact hooks, the flag/config matrix, the `PRIME.md` override + resolution order, git-state modes, Joe's neutral PRIME.md, and the un-gunkify runbook. ## BeadBoard (the dashboard on top of `bd`) When `bd` work is coordinated through **BeadBoard** (Joe's multi-agent dashboard): the agent-side operating contract — the Iron Law, the session lifecycle, mail, evidence — is the `beadboard-driver` skill. Running its macOS launchd services (the `:3000` dashboard, the daemon), the dashboard HTTP API, the Dolt↔JSONL sync, and the `verify-sync.sh` diagnostic is the `beadboard-operations` skill. Neither replaces this skill's `bd` conventions; they layer on top. ## When beads is broken Go straight to [`references/troubleshooting.md`](references/troubleshooting.md). Do **not** improvise schema/server fixes — beads' shared-server states have specific recoveries, and guessing makes them worse. ## Taming `bd prime` The session-start "Beads Workflow Context / SESSION CLOSE PROTOCOL" preamble is emitted by `bd prime`, wired as a SessionStart (and PreCompact) hook by `bd setup claude` — **not** `bd hooks install`. It ships a conservative "don't push without explicit authority" git policy and is easily duplicated across project + global `settings.json`. To change the wording, neutralize the policy, dedupe the hooks, or understand the flags / `PRIME.md` override and its resolution order, see [`references/prime-customization.md`](references/prime-customization.md). ## Niche features Chemistry/molecules, async gates, worktrees, swarm, federation — not duplicated here. See `working-with-beads/references/cli/` (`mol.md`, `gate.md`, `worktree.md`, `swarm.md`, `federation.md`).
From joeblackwaslike/agent-skills, MIT.
More from joeblackwaslike/agent-skills
- 0.592score
devcontainers
joeblackwaslike
Use when building, modifying, using, or distributing Dev Containers — creating or editing devcontainer.json from scratch, adding devcontainer features…
SkillAFreshness: A★ 1Claude Code +9 - 0.592score
developing-for-github
joeblackwaslike
Use when building software that integrates with GitHub — GitHub Apps, OAuth apps, webhook consumers, bots, CI checks, and automation built on the GitHub API.
SkillAFreshness: A★ 1Claude Code +9 - 0.592score
docusaurus-docs-builder
joeblackwaslike
Use when creating, redesigning, rewriting, or improving a Docusaurus documentation site, docs portal, developer docs, product docs, API docs, guide site…
SkillAFreshness: A★ 1Claude Code +9 - 0.552score
recovering-session-context
joeblackwaslike
Reconstruct what happened in prior agent sessions from their transcripts and surface everything raised but never resolved — unanswered questions, work…
SkillBFreshness: B★ 1Claude Code +9 - 0.552score
best-practices-for-agentic-development
joeblackwaslike
Use when designing, building, reviewing, testing, or improving agents, agentic workflows, agent skills, MCP servers, tool interfaces, subagent systems, or…
SkillBFreshness: B★ 1Claude Code +9 - 0.548score
agent-instructions
joeblackwaslike
Use whenever creating OR editing CLAUDE.md, AGENTS.md, GEMINI.md, a SKILL.md, or any other file whose job is to instruct an AI coding agent, at any scope…
SkillBFreshness: B★ 1Claude Code +9 - 0.548score
autonomous-agent-operations
joeblackwaslike
Use when operating solo on a task handed off without the user available for interactive check-ins — ask every clarifying question up front, decide and file a…
SkillBFreshness: B★ 1Claude Code +9 - 0.548score
authoring-agent-skills
joeblackwaslike
Use when creating, adding, or maintaining a skill in this agent-skills repo — especially a "working-with-X" skill that wraps external/official docs by…
SkillBFreshness: B★ 1Claude Code +9 - 0.544score
senior-engineering-best-practices
joeblackwaslike
Use in any development session that benefits from a senior engineer's accumulated judgment, methodology, and runbooks — broader than any single category, most…
SkillBFreshness: B★ 1Claude Code +9 - 0.540score
git-github-workflows
joeblackwaslike
Git and GitHub workflow router.
SkillBFreshness: B★ 1Claude Code +9 - 0.502score
github-readme-overhaul
joeblackwaslike
Use when writing, rewriting, branding, visually overhauling, or optimizing a GitHub README.md for installs, downloads, stars, marketplace conversion, OSS…
SkillCFreshness: C★ 1Claude Code +9 - 0.502score
multi-provider-plugins
joeblackwaslike
Use when making a Claude Code plugin compatible with other AI coding assistants (Codex, OpenCode, Cursor, Gemini CLI), designing multi-provider plugin…
SkillCFreshness: C★ 1Claude Code +9
Signals
- Stars
- 1
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Oct 10, 2026 (18 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/joeblackwaslike/agent-skills
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from joeblackwaslike
- 0.592score
docusaurus-docs-builder
joeblackwaslike
Use when creating, redesigning, rewriting, or improving a Docusaurus documentation site, docs portal, developer docs, product docs, API docs, guide site…
SkillAFreshness: A★ 1Claude Code +9 - 0.592score
developing-for-github
joeblackwaslike
Use when building software that integrates with GitHub — GitHub Apps, OAuth apps, webhook consumers, bots, CI checks, and automation built on the GitHub API.
SkillAFreshness: A★ 1Claude Code +9 - 0.592score
devcontainers
joeblackwaslike
Use when building, modifying, using, or distributing Dev Containers — creating or editing devcontainer.json from scratch, adding devcontainer features…
SkillAFreshness: A★ 1Claude Code +9 - 0.552score
best-practices-for-agentic-development
joeblackwaslike
Use when designing, building, reviewing, testing, or improving agents, agentic workflows, agent skills, MCP servers, tool interfaces, subagent systems, or…
SkillBFreshness: B★ 1Claude Code +9 - 0.552score
recovering-session-context
joeblackwaslike
Reconstruct what happened in prior agent sessions from their transcripts and surface everything raised but never resolved — unanswered questions, work…
SkillBFreshness: B★ 1Claude Code +9 - 0.548score
autonomous-agent-operations
joeblackwaslike
Use when operating solo on a task handed off without the user available for interactive check-ins — ask every clarifying question up front, decide and file a…
SkillBFreshness: B★ 1Claude Code +9
Cite this page
beads-operations skill. Agent Mart. https://agentmart.dev/skills/joeblackwaslike-beads-operations (last updated 2026-10-24)