probe-synthesis

probe-synthesis is a command for Claude Code from ds1/boilerplate.md. It costs 0 tokens per session (538 once invoked), scanned A, original, MIT.

A command that combines six Socratic evaluations—reviews based on careful questioning—into one summary document.

In plain words
What is it for?
Use it to consolidate document evaluations into an executive summary and structured findings report.
Why use it?
It gathers scattered reviews into a single assessment of findings, evidence quality, assumptions, and risks.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution.

Good fit Use it to consolidate document evaluations into an executive summary and structured…

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/ds1/boilerplate.md/probe-synthesis
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.

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

Made for: Claude Code.

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-synthesis

README.md
[![agentmods](https://agentmods.dev/badge/commands/ds1/boilerplate.md/probe-synthesis.svg)](https://agentmods.dev/commands/ds1/boilerplate.md/probe-synthesis)
Your own site
<a href="https://agentmods.dev/commands/ds1/boilerplate.md/probe-synthesis"><img src="https://agentmods.dev/badge/commands/ds1/boilerplate.md/probe-synthesis.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 538 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00000 $0.00538
Opus 5 $0.00000 $0.00269
Sonnet 5 $0.00000 $0.00108
Haiku 4.5 $0.00000 $0.00054

Measured 7d ago against content hash fe9b9a5bf4a6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

probe-synthesis 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 7d 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-synthesis.md · 68 lines

How it starts

The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Probe: Synthesis

Synthesize findings from existing Socratic evaluation files into a consolidated summary.

Usage

/probe-synthesis <directory-containing-evaluations>

Prompt

You are synthesizing findings from 6 Socratic evaluations into a comprehensive summary document.

Look in the directory: $ARGUMENTS

Find and read these evaluation files:

  • socratic-1-clarify-thinking.md
  • socratic-2-challenge-assumptions.md
  • socratic-3-evidence-basis.md
  • socratic-4-alternative-viewpoints.md
  • socratic-5-implications-consequences.md
  • socratic-6-question-the-question.md

Create socratic-synthesis.md in the same directory that consolidates:

  1. Executive Summary - Bottom-line assessment in 2-3 sentences. What's the verdict?

  2. Critical Findings Table

    # Evaluation Key Finding
    1 Clarify Thinking ...
    2 Challenge Assumptions ...
    3 Evidence Basis ...
    4 Alternative Viewpoints ...
    5 Implications ...
    6 Question the Question ...
  3. Evidence Quality Assessment - Summary of source reliability, bias, and gaps

  4. Assumption Risk Matrix - Key assumptions ranked by impact if wrong

    Assumption Confidence Impact if Wrong
  5. Unexplored Alternatives - Options the original document didn't consider

  6. Hidden Costs & Consequences - Implications not addressed in the original

  7. The Meta-Question - Is the original document asking the right question? What should it ask instead?

  8. Decision Framework - Checklist of what must be validated before proceeding

    • Item 1
    • Item 2
    • ...
  9. Stakeholder Questions

    • For the CEO: ...
    • For the CTO: ...
    • For the CFO: ...
    • For Product: ...
  10. Final Verdict - Is the recommendation ready for action, or does it need more work?

The synthesis should be actionable, providing a clear path forward for decision-makers.

Read the full file on GitHub · 68 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. 7d ago First seen · 68 lines · 0 tokens per session scan A fe9b9a5bf4a6

Subscribe to this mod's changes

probe-synthesis 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 538 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.