---
title: "Math-proof worker: review, role & definition · Undominated.ai"
canonical: https://undominated.ai/agents/anthropic-math-proof-worker/
description: "Answers one self-contained mathematics question into a file, separates proved claims from sketches and open questions, and appends the task's end marker only when finished."
---

# Math-proof worker: review, role & definition · Undominated.ai

> Answers one self-contained mathematics question into a file, separates proved claims from sketches and open questions, and appends the task's end marker only when finished.

[← Explore all agents](/agents/)

MATHEMATICS / Anthropic

# Math-proof worker

Answers one self-contained mathematics question into a file, separates proved claims from sketches and open questions, and appends the task's end marker only when finished.

 [Use this definition ↓](#setup)[Original source ↗](https://github.com/anthropics/claude-plugins-official/blob/b78ac49cdc6b3d7b61c4439470e311f4291265b1/plugins/math-proof/agents/math-proof-worker.md)

SOURCE REVIEW

 Reviewed 2026-10-14
 Evidence 4 linked sources
 Publisher Anthropic
 Licence [Apache-2.0 ↗](https://github.com/anthropics/claude-plugins-official/blob/b78ac49cdc6b3d7b61c4439470e311f4291265b1/plugins/math-proof/LICENSE)
 Revision b78ac49cdc6b
 [Read what was—and wasn’t—checked ↓](#review)

“A math-proof worker: it answers one self-contained question from a file, writing its answer to a file as it reasons. It has no memory between questions and is launched only by the math-proof plugin's siege skill.”

 [Anthropic · upstream description ↗](https://github.com/anthropics/claude-plugins-official/blob/b78ac49cdc6b3d7b61c4439470e311f4291265b1/plugins/math-proof/agents/math-proof-worker.md) Our analysis follows below.

01 / THE REASONING

## Why this made the selection.

 - The answer file has to separate what is proved, what is only sketched or conjectured, and what remains open, and a literature result must be labeled as cited from memory.
- The last line is the task's exact end marker, written only when the answer is finished and moved back to the end if the file is extended. The reply abstract is at most 300 words.

### A good fit for

 - Give it one query file, the full problem statement, an answer path and the exact completion marker; obtain a durable answer with proved, conjectured and open claims separated.
- Recover a cut-off task by passing its named partial answer to a fresh worker, which must recheck every reused claim.
- Supply one query path, full authoritative problem and an optional named interrupted answer.
- Recover a partial attempt without treating the predecessor’s statements as established facts.

### Weigh up before choosing

 - Read, Write and Edit are the only declared tools; no code execution or web access is available to verify calculations or literature.
- The end marker means the worker finished its answer, including an answer that leaves the question open. It does not certify a proof.
- The siege skill and ledger.py decide whether answers are finished, partial or missing. Installing this file alone omits that recovery logic.
- The higher-effort worker variant is not counted as a separate resource because its body is shared. The plugin licence appendix retains its template copyright line.
- The profile has no code or web tools and cannot independently retrieve cited literature or test numerical counterexamples.

02 / THE REVIEW RECORD

## What we actually inspected.

Source review has boundaries. A clear record is more useful than a “safe” badge.

### Material inspected

 - plugins/math-proof/agents/math-proof-worker.md
- plugins/math-proof/LICENSE
- plugins/math-proof/README.md (installation, prerequisites, use, resume and warnings)
- plugins/math-proof/skills/siege/SKILL.md (frontmatter, setup and orchestration rules; not a full protocol audit)
- Round 2: pinned definition, output contract and permission/dependency boundaries reread on 2026-10-14

### Our findings

 - The licence file is the Apache License, Version 2.0. The appendix line is Copyright [yyyy] [name of copyright owner].
- Tools are Read, Write, and Edit. model is inherit, effort is low, and maxTurns is 80. The worker reads the query, the problem statement, the problem file if the pasted copy looks garbled, and a named unfinished answer file. Nothing else in the directory is in scope.
- The worker writes intermediate statements before long reasoning so an interrupted attempt leaves recoverable evidence.
- The inspected siege rules launch a fresh worker for a partial answer, retain a partial file, and use ledger.py answers to classify completion before deciding on a rerun.
- The last-line marker is supplied per query; the source requires it even when the worker cannot settle the task.
- A resumed worker must check reusable material itself; an unfinished answer is evidence to inspect, not inherited truth.
- The final answer separates proved statements, sketches and open questions, and literature recalled from memory must be identified as such.

### Not established by this review

 - The agent was not executed; model behaviour, host compatibility and task outcomes were not runtime-tested.
- No plugin installation, proof run or bookkeeping-script execution was performed.
- The remaining siege protocol and ledger.py implementation were not fully audited.

The review applies to the material and revision named here. A newer upstream release can change its behavior.

03 / PUT IT TO WORK

## Use the role in your project.

[Upstream setup instructions ↗](https://github.com/anthropics/claude-plugins-official/blob/b78ac49cdc6b3d7b61c4439470e311f4291265b1/plugins/math-proof/agents/math-proof-worker.md)
 - Copy the worker file at the reviewed commit into the location your host uses for agent prompts.
- No install command is published. Installing the whole math-proof plugin was not reviewed.

### Before you start

 - One query file and the problem statement
- A path for the answer file

### Compatibility

Hosts that can load a Markdown agent file with a tool list

### Implementation

Markdown

### Reads the named question and writes one answer file

 - Read the query, the problem statement, and a named unfinished answer file
- Write and edit the answer file

### Cost model

Apache-2.0 instructions. Each judge and worker call uses the host’s model allowance or API budget; no cost or proof-success benchmark was measured.

04 / FOLLOW THE EVIDENCE

## The source trail.

Our notes are separate from the original resource. Check upstream before adopting a new version.

 - [Math-proof worker ↗](https://github.com/anthropics/claude-plugins-official/blob/b78ac49cdc6b3d7b61c4439470e311f4291265b1/plugins/math-proof/agents/math-proof-worker.md) Checked 2026-10-14 https://github.com/anthropics/claude-plugins-official/blob/b78ac49cdc6b3d7b61c4439470e311f4291265b1/plugins/math-proof/agents/math-proof-worker.md Supports: summary, whySelected, output format
- [Apache-2.0 licence ↗](https://github.com/anthropics/claude-plugins-official/blob/b78ac49cdc6b3d7b61c4439470e311f4291265b1/plugins/math-proof/LICENSE) Checked 2026-10-14 https://github.com/anthropics/claude-plugins-official/blob/b78ac49cdc6b3d7b61c4439470e311f4291265b1/plugins/math-proof/LICENSE Supports: Redistribution terms, Unfilled copyright appendix
- [Math-proof plugin setup and operating limits ↗](https://github.com/anthropics/claude-plugins-official/blob/b78ac49cdc6b3d7b61c4439470e311f4291265b1/plugins/math-proof/README.md) Checked 2026-10-14 https://github.com/anthropics/claude-plugins-official/blob/b78ac49cdc6b3d7b61c4439470e311f4291265b1/plugins/math-proof/README.md Supports: Whole-plugin installation, Runtime prerequisites, Model usage and resume procedure
- [Siege orchestration: setup and rules ↗](https://github.com/anthropics/claude-plugins-official/blob/b78ac49cdc6b3d7b61c4439470e311f4291265b1/plugins/math-proof/skills/siege/SKILL.md) Checked 2026-10-14 https://github.com/anthropics/claude-plugins-official/blob/b78ac49cdc6b3d7b61c4439470e311f4291265b1/plugins/math-proof/skills/siege/SKILL.md Supports: Agent dependencies, Completion-marker handling, Fresh worker launches and interruption recovery

KEEP COMPARING

## Other approaches to consider.

Related by category or shared topics. These are alternatives to inspect, not a measured quality order.

 [### Math-proof judge ↗ Runs one named step of a math-proof siege: writes only the files that step names, keeps notes under 4000 words, and requires proof.md to stand alone.](/agents/anthropic-math-proof-judge/)[### Math proof worker, deep ↗ Pins the higher-effort math-proof worker that answers one question per launch and writes the answer to a file the orchestrator reads.](/agents/anthropic-math-proof-worker-deep/)[### Undominated · Inference Scaling Strategist ↗ Analyzes test-time compute scaling laws, verifier passes, and search budgets to optimize accuracy per dollar spend.](/agents/undominated-inference-scaling-strategist/)

 [AI Tools ↗](/tools/)[Skills ↗](/skills/)[Agents ↗](/agents/)[MCP Servers ↗](/mcp-servers/)[Workflows ↗](/workflows/)

## Continue your investigation

 - [Find reusable instructions](/skills/)
- [Inspect connections](/mcp-servers/)
- [Build a toolkit](/tools/)
- [Choose the model](/compare/)
