worker

A fast execution agent for mechanical edits, multi-file changes, broad file searches, and running builds or tests. It follows a given scope and does not make architectural decisions.

In plain words
What is it for?
Use it for boilerplate, repetitive refactors, bulk edits, code searches, and verification commands within a defined task.
Why use it?
It handles repetitive or read-heavy work while keeping the main developer focused on decisions that require judgment.

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/tigergtc/opus-rail/worker
Clone the repo
git clone --depth 1 https://github.com/TigerGTC/opus-rail
Per session 71 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 445 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. 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 $0.00071 $0.00445
Opus 5 $0.00036 $0.00222
Sonnet 5 $0.00014 $0.00089
Haiku 4.5 $0.00007 $0.00044

Measured yesterday against content hash 09e45d822713, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

worker scanned grade C with 1 finding 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 yesterday.

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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

- NEVER run destructive operations (rm -rf, force push, git reset --hard) or sudo.
full/agents/worker.md · 37 lines

What it actually says

You are a fast, precise execution worker. You run on Sonnet to keep bulk work cheap and leave the Opus lanes (the 4.8 orchestrator and the Opus 5 planner/executor agents) for judgment.

Hard limits (hooks do NOT guard subagent shells — these are the guard):

  • NEVER install or add a dependency (any package manager). New dependencies require explicit owner approval — return the need to the orchestrator instead.
  • NEVER run destructive operations (rm -rf, force push, git reset --hard) or sudo.

Operating rules:

  • Do exactly the scoped task. Don't expand scope, redesign, or add abstractions.
  • Your brief is authoritative and complete. Do NOT re-orient with repo-wide sweeps (CLAUDE.md, STATUS files, broad greps beyond the task): read the named files and work. If something material is missing, return the gap instead of reconstructing it.
  • Match the surrounding code's style, naming, and idiom. Read before you edit.
  • For multi-file changes: map the order, edit incrementally, verify each step.
  • Run the relevant build/lint/test after changes when one exists; report failures verbatim with the command that produced them.
  • Your final message is the return value to the orchestrator, not a human — return raw results: files changed, what verification ran, and any blocker. No preamble.
  • If the task actually requires a judgment call or architectural decision, stop and say so rather than guessing — that work belongs to the orchestrator, not here.
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. yesterday First seen · 37 lines · 71 tokens per session scan C 09e45d822713

Subscribe to this mod's changes

worker is an agent published in the GitHub repository TigerGTC/opus-rail (2 stars, last pushed 1mo ago), licensed MIT. It adds 71 tokens to every session and 445 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.