deep-dive

deep-dive is a skill for Claude Code from gtapps/claude-code-hermit. It costs 79 tokens per session (912 once invoked), scanned A, original, MIT.

A follow-up tool for investigating a topic mentioned in a recent news brief. It finds the original item, researches its primary source, and writes a focused analysis.

In plain words
What is it for?
Use it to produce a short general analysis or a security-focused review covering issues such as affected versions and patches.
Why use it?
It saves time when a brief raises a question that needs more context or verification.

Skill for Claude Code

Written for Claude Code: PreToolUse hook event. Also seen: mentions CLAUDE.md.

Part of the feed-hermit plugin — 7 skills, 1 agent shipped together

Good fit Use it to produce a short general analysis or a security-focused review covering issues such as affected versions and patches.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/gtapps/claude-code-hermit/deep-dive
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 gtapps/claude-code-hermit --skill deep-dive
Clone the repo
git clone --depth 1 https://github.com/gtapps/claude-code-hermit

Made for: Claude Code.

Or install feed-hermit, the plugin that ships this one along with the rest of its 7 skills, 1 agent.

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 deep-dive

README.md
[![agentmods](https://agentmods.dev/badge/skills/gtapps/claude-code-hermit/deep-dive.svg)](https://agentmods.dev/skills/gtapps/claude-code-hermit/deep-dive)
Your own site
<a href="https://agentmods.dev/skills/gtapps/claude-code-hermit/deep-dive"><img src="https://agentmods.dev/badge/skills/gtapps/claude-code-hermit/deep-dive.svg" alt="Measured on agentmods" 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 912 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00912
Opus 5 $0.00039 $0.00456
Sonnet 5 $0.00016 $0.00182
Haiku 4.5 $0.00008 $0.00091

Measured 3d ago against content hash af7b4fa088cc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

deep-dive 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 3d 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.

plugins/feed-hermit/skills/deep-dive/SKILL.md · 75 lines

How it starts

The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Deep Dive

Deliver a focused follow-up analysis for a topic slug referenced in a recent brief.

Input

The argument is the slug from the brief CTA (e.g., local-first-sync, apex-one-zero-day).

Steps

  1. Resolve the item. Glob .claude-code-hermit/briefs/ for files from the last 14 days (sort by date, newest first). Scan each for the slug (case-insensitive substring match against the brief body). Extract the surrounding paragraph — the item's headline, description, any URL, and its category/tags.

  2. Web research. Using the URL and headline from the brief (if found), run 1–2 targeted WebFetch calls to reach the primary source. If no URL is available, use the slug as a search hint. Collect what the analysis template needs: what happened, key facts/dates, current status, and (for security items) CVE/CVSS, affected versions, exploitation status, patch status.

  3. Write the analysis. ≤10–15 lines. Pick the template by the briefed item's nature:

    Default (general follow-up) — for any non-security item:

    **Deep dive: <slug>**
    
    **What happened:** One–two sentences on the development and its context.
    **Why it matters:** Concrete stakes — who's affected, what decision it informs.
    **Trajectory:** Where this is heading; what to watch next.
    **Sources:** Primary link(s) and any useful discussion.
    

    Security variant — use ONLY when the briefed item is security-tagged (its category/tags in the brief indicate security, or it's a vulnerability/exploit/breach item):

    **Deep dive: <slug>**
    
    **What it is:** One sentence — vulnerability type, product, CVE if applicable.
    **Severity:** CVSS score (if known) + exploitation status.
    **Who's affected:** Systems/versions/configs at risk.
    **What attackers can do:** Concrete impact (RCE, cred theft, privilege escalation, etc.).
    **Exploitation status:** PoC public / in-the-wild / CISA KEV / theoretical.
    **Patch/mitigation:** Version to upgrade to, workaround if patch unavailable.
    **Timeline:** Disclosed → PoC → exploitation → patch (key dates only).
    **Bottom line:** One sentence — patch now / monitor / low priority.
    

Read the full file on GitHub · 75 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. 3d ago First seen · 75 lines · 79 tokens per session scan A af7b4fa088cc

Subscribe to this mod's changes

deep-dive is a skill published in the GitHub repository gtapps/claude-code-hermit (74 stars, last pushed today), licensed MIT. It adds 79 tokens to every session and 912 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.