task-agent

An autonomous agent that finds available tasks in repositories managed by AllBeads and works through them. It claims a task, moves to the correct repository, makes the changes, runs relevant checks, and reports the result.

In plain words
What is it for?
Use it to find ready tasks, prioritise and claim them, implement changes, run tests or linters, update task status, and record newly found issues.
Why use it?
It reduces the manual effort of searching for unblocked work and keeping task status aligned with implementation. It also records related bugs or follow-up work when they are discovered.

Agent for Claude Code

Part of the allbeads plugin — 1 skill, 19 commands, 4 agents, 1 hook shipped together

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.

agentmods
npx agentmods add agents/thrashr888/allbeads/task-agent
Clone the repo
git clone --depth 1 https://github.com/thrashr888/AllBeads

Made for: Claude Code.

Or install allbeads, the plugin that ships this one along with the rest of its 1 skill, 19 commands, 4 agents, 1 hook.

Per session 11 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 642 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00011 $0.00642
Opus 5 $0.00005 $0.00321
Sonnet 5 $0.00002 $0.00128
Haiku 4.5 $0.00001 $0.00064

Measured 3d ago against content hash e9fb0f68ae7d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

task-agent 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 3d 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.

.claude-plugin/agents/task-agent.md · 96 lines

How it starts

The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Task Agent

Autonomous agent for completing work across AllBeads-managed repositories.

Workflow

  1. Find Ready Work

    ab ready                    # Get unblocked tasks across all contexts
    ab ready -C <context>       # Filter to specific context
    
    • Prefer higher priority tasks (P0 > P1 > P2 > P3 > P4)
    • If no ready tasks, report completion
  2. Claim the Task

    ab show <id>                # Get full task details
    ab update <id> --status=in_progress
    
    • Report what you're working on
    • Note the context (which repo this task is in)
  3. Navigate to Context

    ab context list             # Find the repo path
    cd /path/to/repo            # Work in the correct context
    
  4. Execute the Task

    • Read the task description and any comments
    • Use available tools to complete the work
    • Follow best practices from CLAUDE.md
    • Run tests if applicable
  5. Track Discoveries If you find bugs, TODOs, or related work:

    bd create --title="Found: ..." --type=bug
    bd dep add <new-id> <current-id>   # Link as discovered-from
    
  6. Complete the Task

    cargo test                  # Verify tests pass
    cargo clippy                # Check linter
    git add -A && git commit    # Commit changes
    ab close <id> --reason="Implemented X, added tests"
    git push
    
  7. Continue

    ab ready                    # Check for newly unblocked work
    

    Repeat the cycle.

Important Guidelines

  • Always update issue status when starting and finishing
  • Link discovered work with dependencies
  • Don't close issues unless work is actually complete
  • If blocked, set status to blocked and explain why
  • Push changes before reporting completion
  • Work in the correct repository context

Cross-Context Considerations

AllBeads manages multiple repositories. When working:

  • Check which context the bead belongs to
  • Navigate to that repo before making changes
  • Use ab for cross-context operations
  • Use bd for single-repo operations

Read the full file on GitHub · 96 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. 3d ago First seen · 96 lines · 11 tokens per session scan A e9fb0f68ae7d

Subscribe to this mod's changes

task-agent is an agent published in the GitHub repository thrashr888/AllBeads (8 stars, last pushed 3d ago), licensed MIT. It adds 11 tokens to every session and 642 once invoked, about $0.0001 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 2026-08-31.

Related

Other agents, from other repositories

beads-warden

Guard the beads execution record: enforce the write-flush-verify discipline that defeats the bd rapid-write race, audit epic dependency graphs for cycles and orphans, catch closures whose title overstates what shipped, flag open beads carrying no disposition or a disproven premise, and reconcile bd against its GitHub…

jeremylongshore/tons-of-skills-marketplace · 157 tokens

flow

Context-driven development backed by OKF knowledge bundles. Use when a project has .agents/, when the user asks to set up, plan, draft a PRD, design, research, document, implement, sync, check status, refresh, validate, revise, review, finish, archive, revert, or create a task, or when working in .agents/ files.

cofin/flow · 74 tokens

onboarding

Use when the current repo has existing code but no Piyaz project that matches it, and the user wants to adopt Piyaz on day N. Triggers: "import this repo", "onboard this codebase", "I have an existing app, can you read it and turn it into Piyaz tasks", "reverse-engineer this project". Do not use when no code exists…

FrkAk/piyaz · 120 tokens

preflight

Preflight agent for /next. Runs the mechanical-drift scan and applies obvious fixes, runs the guidance-contradiction check, and reviews any ready worker result. Logs its own decisions to the orchestrator log and returns ONLY a compact report — raw scan output, contradiction reasoning, and diffs stay in this agent's…

dppdppd/rpm · 89 tokens

coverage-guardian

Use to verify and repair the coverage gate — run the repo's unit tests with coverage, find touched files below 95%, and write the specific missing tests to close the gaps. Language- and framework-agnostic.

theam/claude-dev-kit · 48 tokens

codebase-scanner

Scans codebase to assess issue relevance based on current state. Compares issue descriptions against actual implementation to identify stale issues, potentially resolved items, and issues with increased relevance. Use when reprioritizing project backlog.

rjroy/vibe-garden · 44 tokens