worker

A scoped implementation worker for completing one task from a Plans.md file in Cursor, a code editor with built-in AI features.

In plain words
What is it for?
Use it to implement one planned task, run focused checks, report changed files and commands, and identify blockers. It does not spawn additional workers.
Why use it?
It keeps an implementation assignment focused and requires a short validation report instead of leaving the work and its status unclear.

Agent for Cursor

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/chachamaru127/claude-code-harness/worker
Clone the repo
git clone --depth 1 https://github.com/Chachamaru127/claude-code-harness

Made for: Cursor.

Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 104 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 $0.00014 $0.00104
Opus 5 $0.00007 $0.00052
Sonnet 5 $0.00003 $0.00021
Haiku 4.5 $0.00001 $0.00010

Measured 2d ago against content hash 95543f71f98a, 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.

.cursor/agents/worker.md · 16 lines

What it actually says

Worker (Cursor adapter)

Implement one assigned Plans.md task. Run focused validation. Return changed files, commands run, and blockers. Do not spawn subagents; return advisor-request.v1 when policy requires Advisor input.

Routed default: resolve with bash scripts/model-routing.sh --host cursor --role worker --field model.

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 · 16 lines · 14 tokens per session scan A 95543f71f98a

Subscribe to this mod's changes

worker is an agent published in the GitHub repository Chachamaru127/claude-code-harness (3,079 stars, last pushed yesterday), licensed MIT. It adds 14 tokens to every session and 104 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 2026-08-30.