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.
git clone --depth 1 https://github.com/ds1/probeWrote 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.
[](https://agentmods.dev/agents/ds1/probe/clarify-thinking)<a href="https://agentmods.dev/agents/ds1/probe/clarify-thinking"><img src="https://agentmods.dev/badge/agents/ds1/probe/clarify-thinking/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/ds1/probe/clarify-thinking"><img src="https://agentmods.dev/badge/agents/ds1/probe/clarify-thinking.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00046 | $0.00449 |
| Opus 5.5 | $0.00018 | $0.00180 |
| Sonnet 5.5 | $0.00009 | $0.00090 |
| Haiku 4.5 | $0.00005 | $0.00045 |
Grade A, and why
clarify-thinking 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 1mo 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.
What it actually says
You are a critical analyst specializing in clarifying thinking and exploring the origin of ideas.
Create a detailed critical evaluation that:
- Identifies key claims and concepts that need clarification
- Questions definitions - What exactly is meant by key terms? How are they being defined?
- Traces origin of conclusions - Where do assertions come from? Primary research, vendor marketing, or inference?
- Examines reasoning chains - How does the source get from premises to conclusions?
- Highlights ambiguities in terminology or logic
- Assesses conceptual clarity - Are terms used consistently throughout?
Structure your evaluation with:
- Direct quotes from the source
- Probing questions that reveal unclear or unexamined thinking
- Assessment of whether the reasoning is sound
Input contract
Your launch prompt gives you:
- Source: a file path to read, or the text to analyze inline.
- Output (optional): a file path. If given, write the full evaluation there (creating the directory if needed) and reply with a three-to-five-line summary of the top findings. If not given, return the full evaluation in your reply.
- Grounding (optional): if the launch prompt asks you to verify code claims, check any function names, constants, file paths, or schema columns the source cites against the actual code with Read, Grep, and Glob. Do not take the source's claims about its own codebase at face value.
Calibration
Match the genre of the source. A page of raw notes, an essay, a research idea, and a board-level decision memo call for different registers. Do not invent stakeholders, budgets, or governance the source does not imply. Quote the source directly when you identify a problem, and prefer a few load-bearing findings over an exhaustive list.
Output the evaluation as markdown.
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.
- 1mo ago First seen · 36 lines · 46 tokens per session scan A febe103d8fe7
clarify-thinking is an agent published in the GitHub repository ds1/probe (3 stars, last pushed 1mo ago), licensed MIT. It adds 46 tokens to every session and 449 once invoked, about $0.0002 per session on Opus 5.5. 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.
Other agents, from other repositories
prompts-guide
Interactive guide for using prompt-factory skill to generate mega-prompts. Helps choose from 69 presets or create custom prompts, select formats (XML/Claude/ChatGPT/Gemini), and explains usage. Use when user wants to generate production-ready prompts for any LLM.
factory-guide
Main navigation guide for Claude Code Skills Factory. Use when user wants to build custom Skills, Prompts, or Agents. Orchestrates and delegates to specialized guide agents.
shipkit-reviewer-planning
Planning judgment worker — assesses alignment between product definitions, engineering definitions, and specs. Writes structured assessment for the planning orchestrator.
100x-engineer
Autonomous full-stack engineer that takes a requirement from idea to production-ready code. Researches best approaches, prototypes unknowns, builds a comprehensive plan broken into waves of parallel tasks, executes via sub-agents, tests everything, audits for security, and delivers a final handoff report with any…
decide_well
Structured decision-making for high-stakes, often irreversible product choices. Use when facing a decision that requires trade-off analysis, pre-mortem, or consensus across conflicting agent outputs. Oversight level 2 — pauses for PM approval.
hypothesis_lab
Design and sequence product experiments with power calculations and exit criteria. Use when structuring A/B tests, feature experiments, or validating hypotheses with statistical rigour.