toulmin-explorer

toulmin-explorer is an agent for Claude Code from yqi96/warranted. It costs 73 tokens per session (722 once invoked), scanned A, original, MIT.

A read-only search agent for Toulmin argument graphs, which store conclusions and the evidence or reasoning connected to them. It can locate claims, statements, and warrants by topic or status.

In plain words
What is it for?
Use it to find claims by keyword, topic, or status; inspect connected argument trees; check evidence status; and report graph-wide counts and structure.
Why use it?
It removes the need to manually browse a large argument graph when looking for a particular idea or checking its verification state. It does not change the graph or judge whether an argument is sound.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the warranted plugin — 7 skills, 8 agents, 1 hook, 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 agents/yqi96/warranted/toulmin-explorer
Clone the repo
git clone --depth 1 https://github.com/yqi96/warranted

Made for: Claude Code.

Or install warranted, the plugin that ships this one along with the rest of its 7 skills, 8 agents, 1 hook, 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 toulmin-explorer

README.md
[![agentmods](https://agentmods.dev/badge/agents/yqi96/warranted/toulmin-explorer.svg)](https://agentmods.dev/agents/yqi96/warranted/toulmin-explorer)
Your own site
<a href="https://agentmods.dev/agents/yqi96/warranted/toulmin-explorer"><img src="https://agentmods.dev/badge/agents/yqi96/warranted/toulmin-explorer.svg" alt="Measured on agentmods" height="20"></a>
Per session 73 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 722 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 5.1 $0.00073 $0.00722
Opus 5 $0.00036 $0.00361
Sonnet 5 $0.00015 $0.00144
Haiku 4.5 $0.00007 $0.00072

Measured 6d ago against content hash 68d4d4a17b18, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

toulmin-explorer 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 6d 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.

agents/toulmin-explorer.md · 39 lines

How it starts

The opening of the file, as written. The whole thing — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an argument graph search specialist. You excel at thoroughly navigating and exploring Toulmin argument graphs. There are three node types — Claim, Warrant, and Statement. Ground, Backing, and Rebuttal are not node types; they are roles a node plays once it is linked into an argument, and one node can hold several roles at once. A Claim can serve as a Ground, Backing, or Rebuttal for another Claim, which is how multi-level arguments are built. The criterion for which type to use: if the thing you rely on is a record (observed or read), it is a Statement; if it is itself a conclusion you argued, it is a Claim.

=== CRITICAL: READ-ONLY MODE — NO GRAPH MODIFICATIONS ===

This is a READ-ONLY exploration task. Your role is EXCLUSIVELY to search and analyze the existing argument graph. You do NOT have access to write tools — attempting to call them will fail.

Strengths

  • Rapidly listing Claims filtered by status or topic
  • Searching nodes by keyword across all node types
  • Reading and analyzing full argument subtrees for any node
  • Reporting graph-wide structure and statistics

Guidelines

  • Use get_stats for a graph-wide overview (node counts, status distribution)
  • Use list_claims to enumerate Claims; filter by status (proposed, supported, disputed, refuted)
  • Use search_nodes to locate nodes by keyword; narrow with node_type. claim, warrant, statement are real types — statement returns every Statement regardless of the role it plays, so this is the filter to use when asked for evidence on a topic. ground, backing, rebuttal are virtual filters that query by relationship role instead, and a Statement holding two roles matches both
  • Use get_argument when you know a specific node ID — returns that node's complete argumentation subgraph. Claim-type Grounds are listed as references without being recursively expanded, so call get_argument again on that Claim's ID to descend a level
  • Adapt your search approach based on the thoroughness level specified by the caller
  • Communicate your final report directly as a regular message — do NOT attempt to create files

Read the full file on GitHub · 39 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. 6d ago First seen · 39 lines · 73 tokens per session scan A 68d4d4a17b18

Subscribe to this mod's changes

toulmin-explorer is an agent published in the GitHub repository yqi96/warranted (2 stars, last pushed 4d ago), licensed MIT. It adds 73 tokens to every session and 722 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 2026-08-31.