probe-start

probe-start is a command for coding agents from ds1/boilerplate.md. It costs 0 tokens per session (892 once invoked), scanned A, original, MIT.

A document-review command that starts six parallel question-based analyses and combines their findings. It examines a document from a path you provide and saves the results as Markdown files.

In plain words
What is it for?
Use it to review research papers, proposals, specifications, or other documents. Give it the document path and an output directory for the six evaluations and their combined findings.
Why use it?
It reduces the time and effort needed to inspect an argument from several angles. Separate analyses can reveal unclear terms, unsupported assumptions, missing evidence, and weak reasoning.

Command

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/ds1/boilerplate.md/probe-start
Clone the repo
git clone --depth 1 https://github.com/ds1/boilerplate.md

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 probe-start

README.md
[![agentmods](https://agentmods.dev/badge/commands/ds1/boilerplate.md/probe-start.svg)](https://agentmods.dev/commands/ds1/boilerplate.md/probe-start)
Your own site
<a href="https://agentmods.dev/commands/ds1/boilerplate.md/probe-start"><img src="https://agentmods.dev/badge/commands/ds1/boilerplate.md/probe-start.svg" alt="Measured on agentmods" height="20"></a>
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 892 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 $0.00892
Opus 5 $0.00000 $0.00446
Sonnet 5 $0.00000 $0.00178
Haiku 4.5 $0.00000 $0.00089

Measured 4d ago against content hash 9e071a89eaeb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

probe-start 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.

commands/probe-start.md · 100 lines

How it starts

The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Probe: Full Socratic Analysis

Launch 6 parallel Socratic evaluation agents to analyze a document, then synthesize findings.

Usage

/probe-start <path-to-document> <output-directory>

Arguments

  • $ARGUMENTS - Path to document to analyze and output directory (space-separated)

Prompt

You are orchestrating a comprehensive Socratic analysis. Parse the arguments to get:

  1. The document path (first argument)
  2. The output directory (second argument)

Step 1: Launch 6 Parallel Analysis Agents

Use the Task tool to launch 6 subagents in parallel. Each agent should:

  • Read the source document
  • Apply their specialized Socratic questioning technique
  • Write their evaluation as a markdown file to the output directory

Agent 1: Clarify Thinking -> socratic-1-clarify-thinking.md Examine arguments by asking: "What do you mean by...?", "What is the source of this idea?", "How did you come to this conclusion?"

  • Identify key claims needing clarification
  • Question definitions and terminology
  • Trace origin of conclusions (primary research vs. inference)
  • Examine reasoning chains
  • Highlight ambiguities

Agent 2: Challenge Assumptions -> socratic-2-challenge-assumptions.md Ask: "What are you assuming here?", "How do you know this is true?", "What if you were wrong?"

  • Identify hidden assumptions
  • Question foundational premises
  • Challenge comparison methodology
  • Test robustness of conclusions

Agent 3: Evidence Basis -> socratic-3-evidence-basis.md Ask: "What evidence supports this?", "Is this evidence sufficient?", "What would disprove this?"

  • Audit sources for bias and reliability
  • Identify unsupported assertions
  • Evaluate evidence quality for key claims
  • Assess completeness of evidence

Agent 4: Alternative Viewpoints -> socratic-4-alternative-viewpoints.md Ask: "What is the counter-argument?", "Who would disagree?", "What are other ways to look at this?"

  • Present strongest counter-arguments
  • Identify unrepresented stakeholder perspectives
  • Explore internal contradictions
  • Steel-man rejected options

Read the full file on GitHub · 100 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. 4d ago First seen · 100 lines · 0 tokens per session scan A 9e071a89eaeb

Subscribe to this mod's changes

probe-start is a command published in the GitHub repository ds1/boilerplate.md (5 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 892 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.