beads-worker

beads-worker is an agent for Claude Code from vinnie357/claude-skills. It costs 30 tokens per session (1,362 once invoked), scanned A, original, MIT.

An AI task worker for Beads, a distributed issue tracker that stores tasks and their dependencies in Git-backed data.

In plain words
What is it for?
Use it to automate task queues, work through coding tasks on branches, and create pull requests for review.
Why use it?
It removes repetitive queue work by finding ready tasks, executing them, updating their status, and syncing the results.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the beads plugin — 1 skill, 1 agent shipped together

Good fit Use it to automate task queues, work through coding tasks on branches, and create pull requests for review.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/vinnie357/claude-skills/beads-worker
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo
git clone --depth 1 https://github.com/vinnie357/claude-skills

Made for: Claude Code.

Or install beads, the plugin that ships this one along with the rest of its 1 skill, 1 agent.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for beads-worker

README.md
[![agentmods](https://agentmods.dev/badge/agents/vinnie357/claude-skills/beads-worker.svg)](https://agentmods.dev/agents/vinnie357/claude-skills/beads-worker)
Your own site
<a href="https://agentmods.dev/agents/vinnie357/claude-skills/beads-worker"><img src="https://agentmods.dev/badge/agents/vinnie357/claude-skills/beads-worker.svg" alt="Measured on agentmods" height="20"></a>
Per session 30 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,362 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00030 $0.01362
Opus 5 $0.00015 $0.00681
Sonnet 5 $0.00006 $0.00272
Haiku 4.5 $0.00003 $0.00136

Measured 4d ago against content hash 55b5bd3ffaaf, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

beads-worker scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/tools/beads/skills/beads/agents/beads-worker.md · 210 lines

How it starts

The opening of the file, as written. The whole thing — 210 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a task queue worker for beads-managed workflows. Process tasks from the queue, execute work, and sync results.

Workflow Modes

PR Workflow (Recommended for Code Changes)

Use when changes require human review before merging.

Session Start
git checkout main && git pull    # Start fresh
bd ready                         # Find available tasks
bd show <id>                     # Read task requirements
Task Execution
git checkout -b feature/<name>   # Create feature branch
bd update <id> --status in_progress  # Claim task

# Execute work (see "Execute Work" section below)

bd close <id>                    # Complete task
git add <files>                  # Stage changes
git commit -m "type(scope): description"  # Commit (use /core:gcms for suggestions)
PR Creation
git push -u origin <branch>
gh pr create --title "type(scope): description" --body "- Change one
- Change two"

Notify user: "PR created: <url>"

Then STOP and report the PR URL. Merge only under a deployment merge policy that authorizes it; the default authorizes none. Never queue an automatic or deferred merge.

After Merge (When User Returns)
gh pr view --json state -q '.state'  # Check if "MERGED"
git checkout main && git pull && git branch -d <branch>
bd ready                         # Find next task
PR Workflow Principles
  1. One task = one branch = one PR
  2. Claim before working: bd update --status in_progress
  3. Minimal PRs: Title + bullets only
  4. Report, do not merge: The default merge policy authorizes no agent merge; never assume approval
  5. Clean up: Delete local branch after merge

Automated Workflow (Direct Commits)

Use for non-code tasks or when PRs aren't required.

1. Poll Ready Tasks
bd ready --json

Select the first task. If none available, report "No ready tasks" and exit.

2. Get Task Details
bd show <task_id> --json

Extract: title, description, labels, comments.

Read the full file on GitHub · 210 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 4d ago Changed 55b5bd3ffaaf
  2. 5d ago First seen · 210 lines · 30 tokens per session scan A 56c82ba58044

Subscribe to this mod's changes

beads-worker is an agent published in the GitHub repository vinnie357/claude-skills (25 stars, last pushed 2d ago), licensed MIT. It adds 30 tokens to every session and 1,362 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Related

Other agents, from other repositories

committer

Agent that first generates the result report for a verified TASK and then performs git commit. Automatically invoked by the scheduler. Result files are created in the corresponding WORK directory.

davepoon/buildwithclaude · 36 tokens

Jira Workflow Steward

Expert delivery operations specialist who enforces Jira-linked Git workflows, traceable commits, structured pull requests, and release-safe branch strategy across software teams.

SHAdd0WTAka/Zen-Ai-Pentest · 34 tokens

Issue Tracker

Your GitHub issue command center -- find, triage, review, and respond to issues with full markdown + HTML reports saved to your workspace. Includes reactions, release context, and discussion awareness.

Community-Access/accessibility-agents · 42 tokens

FAI Git Workflow Expert

Git workflow specialist — trunk-based development, conventional commits, PR best practices, branch protection, merge strategies, CODEOWNERS, and Git hooks for AI project collaboration.

frootai/frootai · 39 tokens

task-executor

Use this agent to execute a single tracked task with TDD, commit, and PR creation in an isolated git worktree. Dispatched by /coco:loop for parallel execution. Context: Multiple tasks are ready with non-overlapping file ownership. /coco:loop dispatches parallel agents. assistant: "I'll dispatch task-executor agents…

skullninja/coco-workflow · 97 tokens

Shipper

Post-review shipping agent — commits, updates the roadmap, captures postmortem, and optionally creates a PR after a PASS verdict.

srnichols/plan-forge · 29 tokens