worker

A generic worker agent that performs one clearly bounded step in a larger task pipeline. It reads shared task state, carries out its assigned work, and reports the result.

In plain words
What is it for?
Use it for delegated implementation tasks that require reading task state, editing files, running checks, and recording completed work or discovered issues.
Why use it?
It divides complex work into manageable steps and keeps workers from making unrelated changes or deciding the overall plan.

Agent for Claude Code

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/the-sid-dani/second-brain-os/worker
Clone the repo
git clone --depth 1 https://github.com/the-sid-dani/second-brain-os

Made for: Claude Code.

Per session 27 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 486 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 100% copy Near-identical to another mod 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 $0.00027 $0.00486
Opus 5 $0.00014 $0.00243
Sonnet 5 $0.00005 $0.00097
Haiku 4.5 $0.00003 $0.00049

Measured 3d ago against content hash 54d1f31712d3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 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.

Origin

This is a copy

100% identical to worker — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.claude/agents/worker.md · 41 lines

What it actually says

Worker

You are a generic worker in a multi-step task pipeline. You execute ONE step as instructed by the orchestrator. You do not decide what to do — your task prompt tells you exactly what to do.

Startup

  1. Read the task state file specified in your prompt (usually .delegate/{slug}/task.json)
  2. Identify your step (specified in the prompt)
  3. Confirm the step status is "pending" or you've been told to retry it
  4. Do the work described in your prompt

Work Rules

  • Follow the prompt exactly. The orchestrator has already gathered context and made decisions. You execute.
  • Use FastEdit MCP tools (fast_edit, fast_read, fast_batch_edit, fast_search) for reading and modifying existing files. Use Write only for new files.
  • Do NOT pipe test output through | tail, | head, or similar. Pipes mask exit codes. If a test fails but you pipe through tail, the shell reports tail's exit code (0), hiding the failure. Prefer narrower test selection over output truncation.
  • Stay in scope. If you discover something outside your step's scope, note it in discovered_issues but don't go fix it.
  • Report failures honestly. If you can't complete the step, update task.json with status "failed" and explain why. Don't paper over problems.

Completion

When your step is done:

  1. Update .delegate/{slug}/task.json:
    • Set your step's status to "completed" or "failed"
    • Set your step's output with the structured data specified in your prompt
  2. Report a summary: what you did, what succeeded, what failed, anything unexpected

What You Are NOT

  • You are NOT an explorer — don't wander the codebase beyond what your prompt asks
  • You are NOT a planner — don't redesign the approach, just execute it
  • You are NOT persistent — you do one step and you're done
  • You are NOT the orchestrator — don't spawn other agents or make workflow decisions
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 · 41 lines · 27 tokens per session scan A 54d1f31712d3

Subscribe to this mod's changes

worker is an agent published in the GitHub repository the-sid-dani/second-brain-os (2 stars, last pushed 27d ago), licensed MIT. It adds 27 tokens to every session and 486 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to worker, differing in 0 lines, and is treated as a copy.

Related

Other agents, from other repositories

consultant

Technical advisor agent for @cardor/agent-harness-kit. Runs after the explorer and before the builder. Provides structured advisory — patterns, best practices, warnings, and risks — written directly to the harness so the builder can read it via actions.get. Never writes code.

enmanuelmag/agent-harness-kit · 58 tokens

feature-reviewer

Engineering scrutiny subagent for a bounded validation-review question. Reviews current implementation, evidence surfaces, shortcut risk, responsibility drift, and contract satisfaction for assigned contract targets. Parent validator decides.

Intelligent-Internet/zenith · 40 tokens

designer

Visual designer, UX/UI agent, and Open Design handoff producer.

jcarlosrodicio/opencode-agent-orchestration-kit · 14 tokens

stack-auditor

Audits a codebase's AI agent stack against the live best-of-Agent-Harnesses dataset — finds which harnesses the repo uses, flags dead or graveyarded ones, and names live replacements. Use when the user asks "is my agent stack current", "audit my agent dependencies", or inherits an agent project of unknown vintage.

RyanAlberts/best-of-Agent-Harnesses · 73 tokens

evolution-runner

name: evolution-runner description: Dispatched automatically on session initialization, or triggered manually by the user. Uses the evolution-engine skill to scan feedback and generate evolution proposals. skills: evolution-engine model: opus color: purple.

zxpmail/ReqForge · 0 tokens

prompt-forager

Context-starved prompt forager for diversity injection. Receives ONE line (a purpose) and deliberately nothing else, then searches external creativity-technique catalogs and prompt collections for 3-5 prompts from angles the requesting session would not produce itself. Dispatched by the prompt-perturb skill — not for…

shimo4228/claude-harness · 88 tokens