amp-expert

amp-expert is an agent for coding agents from jkitchin/discopt. It costs 79 tokens per session (2,042 once invoked), scanned A, original, EPL-2.0.

An expert agent for Adaptive Multivariate Partitioning, an optimization method for problems with both continuous and yes-or-no decisions. It alternates between simplified linear problems and nonlinear estimates while refining the search.

In plain words
What is it for?
Use it for questions about turning on AMP, tuning partitions, or diagnosing AMP behavior. It is aimed at mixed-integer nonlinear programming, where some decisions are whole-number or binary and others vary continuously.
Why use it?
It helps answer whether this solver should be enabled, how its partitions should be tuned, and why it may be behaving unexpectedly. These problems can require choosing values and discrete options at the same time.

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/jkitchin/discopt/amp-expert
Clone the repo
git clone --depth 1 https://github.com/jkitchin/discopt

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for amp-expert

README.md
[![agentmods](https://agentmods.dev/badge/agents/jkitchin/discopt/amp-expert.svg)](https://agentmods.dev/agents/jkitchin/discopt/amp-expert)
Your own site
<a href="https://agentmods.dev/agents/jkitchin/discopt/amp-expert"><img src="https://agentmods.dev/badge/agents/jkitchin/discopt/amp-expert.svg" alt="Measured on agentmods" height="20"></a>
Per session 79 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,042 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin unknown 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 $0.00079 $0.02042
Opus 5 $0.00039 $0.01021
Sonnet 5 $0.00016 $0.00408
Haiku 4.5 $0.00008 $0.00204

Measured 4d ago against content hash 1917f99d6e6a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

amp-expert 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 4d 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.

python/discopt/skills/agents/amp-expert.md · 103 lines

The source is not reproduced here

Licensed EPL-2.0

The repository is licensed EPL-2.0, which this catalogue does not treat as permission to reproduce the file. Read it at the source.

Read it on GitHub

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. 4d ago First seen · 103 lines · 79 tokens per session scan A 1917f99d6e6a

Subscribe to this mod's changes

amp-expert is an agent published in the GitHub repository jkitchin/discopt (24 stars, last pushed 4d ago), licensed EPL-2.0. It adds 79 tokens to every session and 2,042 once invoked, about $0.0004 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

algorithm-expert

RL algorithm expert. Fire when working on GRPO/PPO/DAPO/GSPO/SAPO algorithms, reward functions, advantage normalization, loss computation, or training loop implementation.

redai-infra/Relax · 37 tokens

by-campaign

Plan design campaigns. Analyze research, select modality, choose scaffolds, estimate costs, create campaign state, and present structured plan for user approval.

001TMF/blatant-why · 33 tokens

mathodology-problem-analyst

Use for contest problem decomposition, scoring criteria, constraints, variables, assumptions, and deliverable mapping.

sweetcornna/mathodology · 29 tokens

validator

Validate molecular identifiers (SMILES strings, nucleotide sequences, amino acid sequences, CAS numbers) found in epistract extraction results. Uses RDKit for chemistry and Biopython for sequences. Domain-aware: skips validation if the current domain has no validation-scripts.

usathyan/epistract · 53 tokens

gpd-plan-checker

Verifies plans will achieve phase goal before execution. Goal-backward analysis of plan quality for physics research. Spawned by the plan-phase and verify-work workflows.

psi-oss/get-physics-done · 38 tokens

data-cruncher

Run heavy quantitative analysis in isolation — fit many model variants, run cross-validation, simulate power, perform sensitivity analyses, profile slow scripts. Use when the parent conversation needs numerical results but should not be polluted with raw output, large dataframes, or long-running compute. Returns a…

Marazii/research-co-pilot · 82 tokens