insight

insight is a skill for Claude Code, Codex from Hmbown/Wizards-of-the-Ghosts. It costs 79 tokens per session (733 once invoked), scanned A, original, CC0-1.0.

A subtext-analysis skill for identifying meanings, objections, or concerns that are present in a communication but not stated directly. It uses signals in the message or behaviour rather than claiming to read minds.

In plain words
What is it for?
Use it to interpret emails, stakeholder objections, user bug reports, and other requests where the underlying concern is unclear.
Why use it?
It helps explain why a request, bug report, or objection may not mean exactly what it says on the surface. That can reveal the real blocker behind a conversation.

Skill for Claude CodeCodex

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

Good fit Use it to interpret emails, stakeholder objections, user bug reports, and other requests where the underlying concern is unclear.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/hmbown/wizards-of-the-ghosts/insight
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 insight
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 insight

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/hmbown/wizards-of-the-ghosts/insight"><img src="https://agentmods.dev/badge/skills/hmbown/wizards-of-the-ghosts/insight.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 733 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 $0.00733
Opus 5 $0.00039 $0.00367
Sonnet 5 $0.00016 $0.00147
Haiku 4.5 $0.00008 $0.00073

Measured 9d ago against content hash b1e9680dc4c6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

insight 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/insight/SKILL.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.

Insight

Read between the lines to surface what someone means but is not saying.

What This Skill Does

In D&D, Insight detects lies and reads true intentions. The real-world version is subtext analysis: figuring out what an email actually means, what a stakeholder's real objection is, what a user's bug report is actually describing, or what the unsaid concern is behind a seemingly simple question. Insight does not read minds — it reads signals that are present but not foregrounded. In this grimoire, Insight is treated as a metaphorical skill with a shipping-now delivery profile. Canonical reference input: Insight (skill).

When To Use

  • A message, request, or conversation has an obvious surface meaning and a likely different real meaning.
  • You need to understand what someone actually wants rather than what they literally asked for.
  • A stakeholder's stated objection does not match their behavior, and you need to identify the real blocker.

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 surface communication: what is being explicitly said or asked.
  3. Identify the signals that do not fit the surface reading: tone shifts, conspicuous omissions, hedging language, over-specificity.
  4. Generate the most likely subtext: what is the real concern, objection, or request?
  5. Present both readings — surface and subtext — with confidence levels. Never claim the subtext is certain.
  6. Suggest a response that addresses the subtext without calling it out aggressively.
  7. Package the result as the deliverables below, with confidence, assumptions, and unresolved risk called out explicitly.

Deliverables

  • The surface reading: what was literally said.
  • The subtext reading: what is likely meant, with evidence from the signals.
  • A suggested response that addresses the real concern diplomatically.

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. 9d ago First seen · 68 lines · 79 tokens per session scan A b1e9680dc4c6

Subscribe to this mod's changes

insight 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 733 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.