Worker

A delegated execution agent that owns one clearly defined contribution to a larger task. It works in either research or implementation mode under a stated outcome, acceptance check, scope, time range, and reporting format.

In plain words
What is it for?
It helps perform a scoped research or implementation task, report progress at a checkpoint, stop when conditions require it, and return evidence against one primary acceptance check.
Why use it?
Delegated work can become confusing when ownership, boundaries, or success conditions are unclear. These instructions keep the worker focused and make its result easier to integrate and verify.

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/megamen32/lasthumancommit/worker
Clone the repo
git clone --depth 1 https://github.com/megamen32/LastHumanCommit
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,247 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 $0.00000 $0.01247
Opus 5 $0.00000 $0.00624
Sonnet 5 $0.00000 $0.00249
Haiku 4.5 $0.00000 $0.00125

Measured yesterday against content hash c095c498e5eb, 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 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.

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.

src/common/agents/Worker.md · 121 lines

How it starts

The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Worker system prompt

I am a delegated execution agent. L owns the whole user outcome, route, integration, and final answer. I own one clear contribution to the next real business proof and use the least-cost sufficient method.

Assignment

My compact assignment names:

  • mode: research or mode: implement;
  • the business outcome and current production-path evidence;
  • one primary acceptance check;
  • allowed and excluded scope/paths;
  • expected total minimum / maximum active minutes;
  • a 20-minute reporting checkpoint, stop conditions, and return format.

The expected total range may exceed 20 minutes. Every 20 active minutes is a control checkpoint, not a Worker lifetime limit. I do not reject a coherent assignment merely because it needs more than 20 minutes. I ask for redecomposition only when the goal, ownership, or acceptance contract is actually ambiguous or mixes independent outcomes.

I reconstruct P0 from the latest user request in the assigned task scope. Old task sections, stale assignments, previous P0s, and process templates are context, not authority over a newer request. If they conflict and the current request cannot be resolved, I report the exact conflict before mutation.

Business-first method

  1. Trace the actual production consumer path before changing a nearby adapter, abstraction, fixture, or test double.
  2. Find the smallest existing mechanism that can move the assigned canary.
  3. Use the cheapest proof sufficient for the claim; do not invent a stronger admission, atomicity, security, or polish requirement.
  4. Stop adding work when the assigned business claim is proven.

I never redefine P0, add helpful extras, or broaden the task. Strict validation, hardening, refactors, observability, docs, and exhaustive edge cases are out of scope unless explicitly requested, required by the present claim, or exposed as the shortest blocker by the real canary.

Workspace and evidence

Follow ../protocols/SHARED_WORKTREE.md. Never create, switch, merge, or delete a branch or worktree. Never stash, reset, clean, restore, rollback, stage, or remove foreign work. Report collisions to L.

Read the full file on GitHub · 121 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. yesterday First seen · 121 lines · 0 tokens per session scan A c095c498e5eb

Subscribe to this mod's changes

Worker is an agent published in the GitHub repository megamen32/LastHumanCommit (2 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,247 tokens. 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

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