detect-thoughts

detect-thoughts is a skill for Claude Code, Codex from Hmbown/Wizards-of-the-Ghosts. It costs 79 tokens per session (715 once invoked), scanned A, original, CC0-1.0.

An intent-analysis skill for working out what someone is trying to achieve from their wording, priorities, concerns, and omissions. It turns a message or request into a clearer picture of the underlying goal.

In plain words
What is it for?
Use it to interpret requirements, feature requests, stakeholder messages, negotiation positions, or other communications.
Why use it?
It helps when a literal request does not fully describe the real need. This can prevent teams from solving the wrong problem or missing an important concern.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to interpret requirements, feature requests, stakeholder messages, negotiation positions, or other communications.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/hmbown/wizards-of-the-ghosts/detect-thoughts
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 Hmbown/Wizards-of-the-Ghosts --skill detect-thoughts
Clone the repo
git clone --depth 1 https://github.com/Hmbown/Wizards-of-the-Ghosts

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 detect-thoughts

README.md
[![agentmods](https://agentmods.dev/badge/skills/hmbown/wizards-of-the-ghosts/detect-thoughts/github.svg)](https://agentmods.dev/skills/hmbown/wizards-of-the-ghosts/detect-thoughts)
Your own site
<a href="https://agentmods.dev/skills/hmbown/wizards-of-the-ghosts/detect-thoughts"><img src="https://agentmods.dev/badge/skills/hmbown/wizards-of-the-ghosts/detect-thoughts/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.

agentmods 80×15 button for detect-thoughts

Your own site · 80×15
<a href="https://agentmods.dev/skills/hmbown/wizards-of-the-ghosts/detect-thoughts"><img src="https://agentmods.dev/badge/skills/hmbown/wizards-of-the-ghosts/detect-thoughts.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 79 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 715 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 $0.00079 $0.00715
Opus 5 $0.00039 $0.00358
Sonnet 5 $0.00016 $0.00143
Haiku 4.5 $0.00008 $0.00072

Measured 9d ago against content hash 1f20d1b89452, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

detect-thoughts 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 9d 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.

generated/hermes/investigation-and-preparation/detect-thoughts/SKILL.md · 67 lines

How it starts

The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Detect Thoughts

Surface the likely intent, priorities, and concerns behind a communication.

What This Skill Does

In D&D, Detect Thoughts lets you read surface thoughts and probe deeper. The real-world version is intent analysis: figuring out what someone is trying to accomplish based on what they said, how they said it, and what they chose not to say. This is the analytical complement to Insight (which reads subtext intuitively) — Detect Thoughts is more structured and systematic. In this grimoire, Detect Thoughts is treated as a metaphorical spell with a shipping-now delivery profile. Canonical reference input: Detect Thoughts (spell).

When To Use

  • You have a message, brief, or request and need to systematically extract the sender's priorities, concerns, and unstated goals.
  • A requirements document or feature request needs to be decoded: what do they actually need vs. what they asked for?
  • You want to prepare for a negotiation or conversation by mapping the other party's likely positions and concerns.

Prerequisites

  • No extra runtime dependencies beyond Hermes Agent and the normal toolset for this session.

Procedure

  1. Restate the target, the success condition, and any no-touch boundaries before taking action.
  2. Read the communication and identify explicit statements of intent, priority, and concern.
  3. Analyze word choice, emphasis, and structure for implicit signals about what matters most.
  4. Map the gap between stated and likely intent: where do they diverge?
  5. Deliver the intent analysis with confidence levels and a recommendation for how to respond to the real priorities.
  6. Package the result as the deliverables below, with confidence, assumptions, and unresolved risk called out explicitly.

Deliverables

  • An intent analysis: stated goals, implicit priorities, and likely concerns ranked by importance.
  • A gap analysis: where stated intent and likely real intent diverge, with evidence.
  • A response recommendation that addresses real priorities, not just stated ones.

Read the full file on GitHub · 67 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. 9d ago First seen · 67 lines · 79 tokens per session scan A 1f20d1b89452

Subscribe to this mod's changes

detect-thoughts is a skill published in the GitHub repository Hmbown/Wizards-of-the-Ghosts (107 stars, last pushed 5mo ago), licensed CC0-1.0. It adds 79 tokens to every session and 715 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 2026-09-03.