think-tool

think-tool is a skill for Claude Code, Codex from ChrisLamDev/hermes-core-skills. It costs 54 tokens per session (1,557 once invoked), scanned C, original, MIT.

A structured pause for thinking through difficult choices, unclear requirements, complex operations, or changes that cannot easily be undone.

In plain words
What is it for?
Use it before large refactors, destructive commands, irreversible changes, multi-step work, or recovering from an error.
Why use it?
It reduces rushed decisions and repeated mistakes when several approaches are possible or an action may be destructive.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions Claude Code; mentions Codex.

Good fit Use it before large refactors, destructive commands, irreversible changes, multi-step work, or recovering from an error.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/chrislamdev/hermes-core-skills/think-tool
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.

Any agent
npx skills add ChrisLamDev/hermes-core-skills --skill think-tool
Clone the repo
git clone --depth 1 https://github.com/ChrisLamDev/hermes-core-skills

Made for: Claude Code, Codex.

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 think-tool

README.md
[![agentmods](https://agentmods.dev/badge/skills/chrislamdev/hermes-core-skills/think-tool.svg)](https://agentmods.dev/skills/chrislamdev/hermes-core-skills/think-tool)
Your own site
<a href="https://agentmods.dev/skills/chrislamdev/hermes-core-skills/think-tool"><img src="https://agentmods.dev/badge/skills/chrislamdev/hermes-core-skills/think-tool.svg" alt="Measured on agentmods" height="20"></a>
Per session 54 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,557 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. 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 $0.00054 $0.01557
Opus 5 $0.00027 $0.00779
Sonnet 5 $0.00011 $0.00311
Haiku 4.5 $0.00005 $0.00156

Measured 7d ago against content hash b0fbba1de62a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade C, and why

think-tool scanned grade C with 1 finding 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

- **Before using potentially destructive tools** — `rm -rf`, `git reset --hard`, `DROP TABLE`
skills/think-tool/SKILL.md · 198 lines

How it starts

The opening of the file, as written. The whole thing — 198 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Think Tool

Overview

Before making complex or irreversible decisions, stop and think. The Think Tool is a structured reasoning step that happens before you act — not after. It's the difference between guessing and understanding.

Core principle: If you're not sure, think first. If you're sure, think again.

When to Use

Use Think Tool whenever:

  • Multiple approaches exist — "I could do X or Y" → Stop, think, decide
  • Irreversible changes — Deleting files, modifying database, pushing to main branch
  • Complex multi-step operations — More than 3 tool calls in sequence
  • Error recovery — Something failed and you're about to try a fix
  • Before using potentially destructive toolsrm -rf, git reset --hard, DROP TABLE
  • You catch yourself rushing — "Just try this and see" is a red flag
  • Ambiguous requirements — Not sure what the user actually wants

Do NOT use for: Simple, obvious operations (single file edit, reading a file, running tests)

How to Think

When you call Think Tool, work through these steps in order:

Step 1: State the Situation

In one sentence, what's happening?

"I need to refactor the ChantingHall feature from 4 files to 2 files."

Step 2: List the Options

What are the possible approaches?

Option A: Merge Manager + UI into one file, keep Types separate Option B: Merge everything into one file Option C: Keep current 4-file structure, just add new features

Step 3: Evaluate Each Option

For each option, answer:

  • Pros — What's good about this?
  • Cons — What's the risk?
  • Effort — How much work?
  • Alignment — Does it match the project's existing patterns?

Step 4: Make a Decision

State clearly what you're going to do and why. Then proceed.

"I'll go with Option A because it reduces complexity while keeping type definitions clean and reusable."

Output Format

When using Think Tool, output your reasoning in this format:

🧠 Think Tool
─────────────
Situation: [one sentence]

Options:
1. [Option A] — [brief description]
   → Pros: [...]
   → Cons: [...]
   → Effort: [small/medium/large]

2. [Option B] — [brief description]
   → Pros: [...]
   → Cons: [...]
   → Effort: [small/medium/large]

Decision: [Option X]
Reason: [why this one wins]

Read the full file on GitHub · 198 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 · 198 lines · 54 tokens per session scan C b0fbba1de62a

Subscribe to this mod's changes

think-tool is a skill published in the GitHub repository ChrisLamDev/hermes-core-skills (9 stars, last pushed 2mo ago), licensed MIT. It adds 54 tokens to every session and 1,557 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

unicli-repair

Evidence-driven repair workflow for a broken Uni-CLI adapter. Trigger on a failed unicli envelope, a quarantined adapter, or an explicit adapter-repair request. Classifies non-source failures, edits only the reported adapter path, and uses the original command as a bounded oracle.

olo-dot-io/Uni-CLI · 68 tokens

autonomous-run

Prepare, start, inspect, resume, or stop a finite local overnight coding run after a human has accepted a Wayfinder terminal spec; coordinates a declared Claude/Codex maker and independent checker without pushing, merging, or writing to external systems.

PromptPartner/agentsmith · 53 tokens

authentication-patterns

OAuth 2.0, JWT, SSO, MFA, NextAuth/Clerk/Supabase Auth implementation patterns.

travisjneuman/.claude · 28 tokens

case-interview-practice

Interactive consulting case interview practice with structured frameworks, feedback mechanisms, and progressive difficulty. Use when preparing for management consulting interviews, case competitions, or business problem-solving exercises.

travisjneuman/.claude · 39 tokens

i18n-localization

Internationalization and localization for global applications. Use when adding multi-language support, handling regional formats, or preparing apps for global markets.

travisjneuman/.claude · 32 tokens

electron-desktop

Desktop application development with Electron for Windows, macOS, and Linux. Use when building cross-platform desktop apps, implementing native OS features, or packaging web apps for desktop.

travisjneuman/.claude · 38 tokens