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.
npx skills add gtapps/claude-code-hermit --skill deep-divegit clone --depth 1 https://github.com/gtapps/claude-code-hermitWrote 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/skills/gtapps/claude-code-hermit/deep-dive)<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>- NVIDIA SkillSpector pass
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 | $0.00079 | $0.00912 |
| Opus 5 | $0.00039 | $0.00456 |
| Sonnet 5 | $0.00016 | $0.00182 |
| Haiku 4.5 | $0.00008 | $0.00091 |
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.
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
-
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. -
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.
-
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.
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.
- 3d ago First seen · 75 lines · 79 tokens per session scan A af7b4fa088cc
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.
Other skills, from other repositories
cco-tools
Show what tools actually cost in tokens — learned per-tool averages from observed results, replacing the hardcoded MCP/Agent guesses.
github-pr-creation
Creates GitHub Pull Requests with automated validation and task tracking. Use when user wants to create PR, open pull request, submit for review, or check if ready for PR. Analyzes commits, validates task completion, generates Conventional Commits title and description, suggests labels. NOTE - for merging existing…
design-system-reference
Style guides and implementation rules for frontend design. Works with design-discovery agent which handles context gathering and VS-based style recommendations. Contains detailed style guides, anti-patterns, and implementation checklists.
magic-compact
Compact this Claude Code session.
boss-briefing
Vault health check — workflow pattern analysis, profile sync, session gap recovery, persona rule proposals.
subagent-output-templating
Template for structured sub-agent output including YAML log format, task completion reports (WHY/WHAT/TRADE-OFFS/RISKS), and summary constraints. Use when defining how sub-agents should report results.