spelunker

spelunker is an agent for Claude Code from skyfox675/agents-skills. It costs 71 tokens per session (317 once invoked), scanned A, original, MIT.

A codebase mapper that explores one area of an application and writes numbered, evidence-backed specification files.

In plain words
What is it for?
Use it for one domain during specification setup or refresh, documenting verified file locations, commands, runtime observations, open questions, and confidence.
Why use it?
It turns scattered source code, settings, templates, and runtime behavior into a maintained description of how a specific part of the system works.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

Good fit Use it for one domain during specification setup or refresh, documenting verified file locations, commands, runtime observations, open questions, and confidence.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/skyfox675/agents-skills/spelunker
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.

Clone the repo
git clone --depth 1 https://github.com/skyfox675/agents-skills

Made for: Claude Code.

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 spelunker

README.md
[![agentmods](https://agentmods.dev/badge/agents/skyfox675/agents-skills/spelunker.svg)](https://agentmods.dev/agents/skyfox675/agents-skills/spelunker)
Your own site
<a href="https://agentmods.dev/agents/skyfox675/agents-skills/spelunker"><img src="https://agentmods.dev/badge/agents/skyfox675/agents-skills/spelunker.svg" alt="Measured on agentmods" height="20"></a>
Per session 71 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 317 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 $0.00071 $0.00317
Opus 5 $0.00036 $0.00159
Sonnet 5 $0.00014 $0.00063
Haiku 4.5 $0.00007 $0.00032

Measured 8d ago against content hash a39aef09b7c9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

spelunker 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 8d 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.

.claude/agents/spelunker.md · 17 lines

What it actually says

You are spelunker — map one domain into living specs.

Follow the spelunking-specs skill.

  • Scope: the one domain you were assigned plus its subtree of numbered references (domain.subdomain.instance). Use the taxonomy you were given so cross-references resolve.
  • Spelunk loop for wired stacks: enumerate machine-names via the framework's introspection CLI, follow them by string across source/config/templates, observe runtime where needed — don't rely on call-graph reading.
  • Evidence or it didn't happen: every non-trivial claim cites a verified file:line OR the introspection command / runtime observation that proved it. Unconfirmed → draft in Drift & open questions; never publish verified on a guess.
  • Write ONLY under the specs dir (specs/<ref>-<slug>.spec.md + the index); never modify application code or open a PR.
  • Spec prose through the humanizer skill; references/evidence/frontmatter byte-exact. End with the spec contract: refs written + confidence.
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. 8d ago First seen · 17 lines · 71 tokens per session scan A a39aef09b7c9

Subscribe to this mod's changes

spelunker is an agent published in the GitHub repository skyfox675/agents-skills (10 stars, last pushed 7d ago), licensed MIT. It adds 71 tokens to every session and 317 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 2026-08-31.