ampl-explain

ampl-explain is a command for coding agents from worc4021/ampl-mcp. It costs 14 tokens per session (167 once invoked), scanned A, original, MIT.

A command for explaining an AMPL optimization result, including which limits affected the solution and how valuable additional resources would be.

In plain words
What is it for?
Use it after solving an AMPL model to examine binding constraints, shadow prices, slack, variables at bounds, and solver failures.
Why use it?
Optimization output can show numbers without explaining what caused them. This turns constraint and variable details into plain-language findings, or diagnoses an unsuccessful solve.

Command

Part of the ampl plugin — 1 skill, 3 commands, 1 MCP server shipped together

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 commands/worc4021/ampl-mcp/ampl-explain
Clone the repo
git clone --depth 1 https://github.com/worc4021/ampl-mcp

Or install ampl, the plugin that ships this one along with the rest of its 1 skill, 3 commands, 1 MCP server.

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 ampl-explain

README.md
[![agentmods](https://agentmods.dev/badge/commands/worc4021/ampl-mcp/ampl-explain.svg)](https://agentmods.dev/commands/worc4021/ampl-mcp/ampl-explain)
Your own site
<a href="https://agentmods.dev/commands/worc4021/ampl-mcp/ampl-explain"><img src="https://agentmods.dev/badge/commands/worc4021/ampl-mcp/ampl-explain.svg" alt="Measured on agentmods" height="20"></a>
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 167 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 $0.00167
Opus 5 $0.00007 $0.00084
Sonnet 5 $0.00003 $0.00033
Haiku 4.5 $0.00001 $0.00017

Measured 3d ago against content hash 478adcfaffe0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ampl-explain 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 3d 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.

commands/ampl-explain.md · 15 lines

What it actually says

Explain the current solution.

  1. Call ampl_solve if no solve has happened yet in this session.
  2. For each constraint, read ampl_get_data(name, suffix="dual") and ampl_get_data(name, suffix="slack") (one suffix per call).
  3. Identify the binding constraints (slack near zero) and report their shadow prices in plain language: what one more unit of that resource would be worth.
  4. Read suffix="rc" on the variables and explain any that sit at a bound.
  5. If the model did not solve (ok is not true), call ampl_diagnose and explain instead.
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. 3d ago First seen · 15 lines · 14 tokens per session scan A 478adcfaffe0

Subscribe to this mod's changes

ampl-explain is a command published in the GitHub repository worc4021/ampl-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 14 tokens to every session and 167 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 2026-08-31.