prospector

prospector is an agent for Claude Code from pjt222/agent-almanac. It costs 25 tokens per session (1,870 once invoked), scanned A, original, MIT.

A field guide for finding and identifying rocks, minerals, and precious metals. It covers geological site reading, alluvial gold recovery, and responsible extraction practices.

In plain words
What is it for?
Use it to identify minerals by properties such as hardness and streak, read landscapes and streams, pan or sluice for alluvial gold, recognize ore indicators, and plan responsible site work.
Why use it?
It helps turn field observations into informed identification and prospecting decisions while accounting for practical and legal concerns.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the agent-almanac plugin — 122 skills, 76 agents shipped together

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.

agentmods
npx agentmods add agents/pjt222/agent-almanac/prospector
Clone the repo
git clone --depth 1 https://github.com/pjt222/agent-almanac

Made for: Claude Code.

Or install agent-almanac, the plugin that ships this one along with the rest of its 122 skills, 76 agents.

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 prospector

README.md
[![agentmods](https://agentmods.dev/badge/agents/pjt222/agent-almanac/prospector.svg)](https://agentmods.dev/agents/pjt222/agent-almanac/prospector)
Your own site
<a href="https://agentmods.dev/agents/pjt222/agent-almanac/prospector"><img src="https://agentmods.dev/badge/agents/pjt222/agent-almanac/prospector.svg" alt="Measured on agentmods" height="20"></a>
Per session 25 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,870 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00025 $0.01870
Opus 5 $0.00013 $0.00935
Sonnet 5 $0.00005 $0.00374
Haiku 4.5 $0.00003 $0.00187

Measured 6d ago against content hash 1a56f481c603, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

prospector 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 6d 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.

agents/prospector.md · 166 lines

How it starts

The opening of the file, as written. The whole thing — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Prospector Agent

A mineral and precious metal specialist that guides field identification of rocks and minerals, alluvial gold recovery techniques, geological site reading, and responsible extraction practices. Combines practical fieldcraft with geological literacy.

Purpose

This agent provides expert-level prospecting instruction, combining geological knowledge with hands-on fieldcraft. It guides users through mineral identification using physical properties, teaches gold panning and sluicing techniques, and helps read geological landscapes for indicators of valuable deposits. Every recommendation includes responsible extraction practices and awareness of legal requirements.

Capabilities

  • Mineral Identification: Systematic field identification using hardness (Mohs scale), streak, luster, cleavage, crystal habit, and chemical tests
  • Gold Recovery: Alluvial gold panning technique, sluice box operation, site reading for pay streaks, and fine gold recovery methods
  • Geological Site Reading: Interpret landscape features, rock types, and stream dynamics to locate promising prospecting sites
  • Ore Indicators: Recognize geological signs that indicate the presence of gold, silver, copper, and other valuable minerals
  • Equipment Guidance: Select and use prospecting equipment from basic (pan, classifier) to intermediate (sluice box, highbanker)
  • Regulatory Awareness: Remind users of permit requirements, claim systems, and environmental regulations for their jurisdiction

Available Skills

This agent can execute the following structured procedures from the skills library:

Prospecting

  • mineral-identification — Field identification using hardness, streak, luster, cleavage, and chemical tests
  • gold-washing — Alluvial gold recovery using panning, sluicing, and classification

Usage Scenarios

Scenario 1: First-Time Gold Panning

Guide a complete beginner through their first gold panning experience.

User: I want to try gold panning this weekend. How do I start?
Agent: [Runs gold-washing procedure]
       1. Equipment: 14-inch gold pan with riffles, classifier, snuffer bottle
       2. Location: research known gold-bearing streams in your area
       3. Site reading: inside bends, behind boulders, bedrock cracks
       4. Technique: classify → submerge → shake side-to-side → wash off lighter material
       5. What to look for: black sand concentrates, bright yellow flakes
       6. Regulatory: check local permit requirements before going

Read the full file on GitHub · 166 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. 6d ago First seen · 166 lines · 25 tokens per session scan A 1a56f481c603

Subscribe to this mod's changes

prospector is an agent published in the GitHub repository pjt222/agent-almanac (32 stars, last pushed yesterday), licensed MIT. It adds 25 tokens to every session and 1,870 once invoked, about $0.0001 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 2026-08-30.

Related

Other agents, from other repositories

learn-this

Loaded when the user invokes /learn-this, says "learn this" / "remember this", or accepts your auto-detect offer to capture a correction.

kakha13/think-like-me · 0 tokens

new-rule

Loaded when the user invokes /new-rule or says "new rule" to add a rule from scratch (not tied to a correction).

kakha13/think-like-me · 0 tokens

scientific-paper-research

Research agent that searches scientific papers and retrieves structured experimental data from full-text studies using the BGPT MCP server.

asleekgeek/claude-multiagent-catalogue · 28 tokens

java-security-expert

Expert security auditor specializing in DevSecOps, comprehensive cybersecurity, and compliance frameworks. Masters vulnerability assessment, threat modeling, secure authentication (OAuth2/OIDC), OWASP standards, cloud security, and security automation. Handles DevSecOps integration, compliance (GDPR/HIPAA/SOC2), and…

giuseppe-trisciuoglio/developer-kit · 85 tokens

architect

Fixture for the Signal IR extractor-collision-detection conformance case. Body intentionally contains a markdown link whose visible text starts with @./api.md, so the at-directive extractor matches the same byte range INSIDE the markdown-link extractor's match. Cross-extractor range overlap; the resolver picks ONE…

crystian/skill-map · 85 tokens

arxiv-2308-14329

Agent "arxiv-2308-14329" from SAIRAMANALADI/vybe-intelligence-vault, covering summary, why it matters, paper metadata and key topics & tags.

SAIRAMANALADI/vybe-intelligence-vault · 0 tokens