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 ChrisMckerracher/claude-dream-team --skill spelunkinggit clone --depth 1 https://github.com/ChrisMckerracher/claude-dream-teamWrote 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/chrismckerracher/claude-dream-team/spelunking)<a href="https://agentmods.dev/skills/chrismckerracher/claude-dream-team/spelunking"><img src="https://agentmods.dev/badge/skills/chrismckerracher/claude-dream-team/spelunking/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.
<a href="https://agentmods.dev/skills/chrismckerracher/claude-dream-team/spelunking"><img src="https://agentmods.dev/badge/skills/chrismckerracher/claude-dream-team/spelunking.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00052 | $0.01344 |
| Opus 5 | $0.00026 | $0.00672 |
| Sonnet 5 | $0.00010 | $0.00269 |
| Haiku 4.5 | $0.00005 | $0.00134 |
Grade A, and why
Spelunking - Codebase Exploration 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 11d 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 — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Spelunking - Persistent Codebase Exploration
Spelunking is a system for deep, targeted codebase exploration that produces persistent, reusable documentation. Instead of each agent re-reading the same files, spelunk docs are generated once and reused until the underlying code changes.
Core Concept
Agent needs to understand code area
→ Check if spelunk doc exists for that area
→ If YES and FRESH: read the doc, skip exploration
→ If YES and STALE: re-explore, update the doc
→ If NO: explore, create the doc
Document Storage
docs/spelunk/
├── contracts/ # Type definitions, API signatures (for Architect, QA)
├── flows/ # User flows, entry points (for Product)
├── boundaries/ # Module edges, dependencies (for Architect)
├── trust-zones/ # Auth boundaries, data flow (for Security)
├── _index.md # Human-readable navigation index
└── _staleness.json # Machine-readable staleness tracking
Hash-Based Staleness Tracking
Each spelunk document tracks the source files it was generated from:
// docs/spelunk/_staleness.json
{
"docs/spelunk/flows/user-authentication.md": {
"generated": "2025-01-10T14:30:00Z",
"source_files": {
"src/auth/login.ts": "a1b2c3d4",
"src/auth/middleware.ts": "e5f6g7h8",
"src/routes/auth.ts": "i9j0k1l2"
}
}
}
Staleness Check Algorithm
1. Read _staleness.json entry for the target doc
2. For each source file:
a. Compute current hash: first 8 chars of SHA-256
b. Compare with stored hash
3. If ANY hash differs → STALE
4. If all hashes match → FRESH
5. If no entry exists → MISSING (needs full exploration)
Computing File Hash
# First 8 characters of SHA-256
sha256sum src/auth/login.ts | cut -c1-8
Spelunk Command Syntax
spelunk --for=<agent-type> --focus="<area description>"
Options:
--for Target agent lens: architect, product, qa, security
--focus Natural language description of exploration area
--check Only check staleness, don't re-explore
--force Re-explore even if FRESH
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.
- 11d ago First seen · 170 lines · 52 tokens per session scan A eaeb4e128999
Spelunking - Codebase Exploration is a skill published in the GitHub repository ChrisMckerracher/claude-dream-team (5 stars, last pushed 6mo ago), licensed MIT. It adds 52 tokens to every session and 1,344 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…