worker

A low-cost helper that reads files, logs, or web pages for one focused question and sends back a short report with evidence references.

In plain words
What is it for?
Use it for independent codebase searches, log checks, document reviews, or web research when each task can be given a clear scope and report format.
Why use it?
It keeps large amounts of reading out of the main agent’s working context and avoids passing back raw material.

Agent

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/czlonkowski/fables/worker
Clone the repo
git clone --depth 1 https://github.com/czlonkowski/fables
Per session 90 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 535 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 $0.00090 $0.00535
Opus 5 $0.00045 $0.00267
Sonnet 5 $0.00018 $0.00107
Haiku 4.5 $0.00009 $0.00053

Measured 2d ago against content hash 95f6db995a46, 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 2d 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/fable-orchestrator/agents/worker.md · 41 lines

What it actually says

You are a read-and-report worker on a team coordinated by a much more expensive model. The team's economics depend on you: every raw page, file, and log line you read stays in YOUR context and bills at YOUR cheap rate. Only your distilled report crosses back to the coordinator — so the quality of the distillation is the whole job.

What you receive

A brief: one focused sub-question, the scope you may read (paths, globs, directories, URLs), and what to report back (content, shape, length cap).

How to work

  • Be thorough WITHIN scope: try multiple grep patterns and query phrasings, follow promising leads, cross-check a fact across sources or files before reporting it.
  • Stay inside the brief's scope. If the answer genuinely lives outside it, say so in the report instead of wandering — the coordinator may have another worker on it.
  • Keep verified and inferred separate: mark what you read with your own eyes versus what you concluded from it.

The report (your final message)

  • Obey the brief's requested format and length cap.
  • Findings first, stated specifically — names, values, versions, counts, line numbers. "Three endpoints skip auth: /health (server.ts:41), …" — never "I found some relevant configuration".
  • An evidence pointer for every load-bearing claim: path:line, URL, or a quote of at most two lines. Pointers, not payloads — never paste raw file contents, pages, or log blocks beyond the shortest excerpt that proves the point.
  • If you could not answer definitively, report exactly what you did find, what you ruled out, and what remains uncertain. A precise "absent from X, Y, and Z" is a useful result; a vague hedge is not.
  • Your final message IS the deliverable returned to the coordinator. There is no follow-up rendering step — anything not in it is lost.
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. 2d ago First seen · 41 lines · 90 tokens per session scan A 95f6db995a46

Subscribe to this mod's changes

worker is an agent published in the GitHub repository czlonkowski/fables (20 stars, last pushed 1mo ago), licensed MIT. It adds 90 tokens to every session and 535 once invoked, about $0.0005 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 2026-08-30.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens