skill-finder-investigator

skill-finder-investigator is an agent for Claude Code from pkarpovich/environment. It costs 73 tokens per session (2,164 once invoked), scanned A, original, no licence file.

A review agent for one candidate coding skill, given its URL and author. It assesses whether the skill fits the topic and whether its author appears reliable.

In plain words
What is it for?
Use it as part of a skill-finder workflow that reviews several candidates in parallel; it is not intended for direct use.
Why use it?
It helps filter possible skills before they are accepted into a larger skill-finding process.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the skills plugin — 31 skills, 4 commands, 5 agents shipped together

Good fit Use it as part of a skill-finder workflow that reviews several candidates in parallel; it is not intended for direct use.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/pkarpovich/environment/skill-finder-investigator
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/pkarpovich/environment

Made for: Claude Code.

Or install skills, the plugin that ships this one along with the rest of its 31 skills, 4 commands, 5 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 skill-finder-investigator

README.md
[![agentmods](https://agentmods.dev/badge/agents/pkarpovich/environment/skill-finder-investigator/github.svg)](https://agentmods.dev/agents/pkarpovich/environment/skill-finder-investigator)
Your own site
<a href="https://agentmods.dev/agents/pkarpovich/environment/skill-finder-investigator"><img src="https://agentmods.dev/badge/agents/pkarpovich/environment/skill-finder-investigator/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.

agentmods 80×15 button for skill-finder-investigator

Your own site · 80×15
<a href="https://agentmods.dev/agents/pkarpovich/environment/skill-finder-investigator"><img src="https://agentmods.dev/badge/agents/pkarpovich/environment/skill-finder-investigator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 73 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,164 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 unknown 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 $0.00073 $0.02164
Opus 5 $0.00036 $0.01082
Sonnet 5 $0.00015 $0.00433
Haiku 4.5 $0.00007 $0.00216

Measured 12d ago against content hash d66d880b7fcf, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

skill-finder-investigator 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 12d 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.

dotfiles/claude/agents/skill-finder-investigator.md · 114 lines

The source is not reproduced here

No licence file

A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.

Read it on GitHub

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. 12d ago First seen · 114 lines · 73 tokens per session scan A d66d880b7fcf

Subscribe to this mod's changes

skill-finder-investigator is an agent published in the GitHub repository pkarpovich/environment (2 stars, last pushed 5d ago), with no licence file. It adds 73 tokens to every session and 2,164 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.

Related

Other agents, from other repositories

code-refiner

Code refinement specialist for improving elegance, readability, and maintainability. Use PROACTIVELY when major developments are completed and you're at a stopping point.

stephendolan/dotfiles · 34 tokens

documentation-refiner

Documentation maintenance expert for Markdown files, package configs, and developer docs. Use when major changes have been made. Focus on uppercase-named files like README, CONTRIBUTING, CLAUDE, AGENTS, and CHANGELOG.

stephendolan/dotfiles · 49 tokens

architecture-reviewer

Evaluates codebases for brittleness, complexity, and coupling. Use when assessing technical debt, reviewing architecture, or planning refactors. Covers dependency analysis and structural issues.

stephendolan/dotfiles · 38 tokens

code-reviewer

Reviews code for bugs, logic errors, security vulnerabilities, and convention adherence. Use when reviewing diffs, checking PRs, or validating changes. Covers confidence-based filtering and severity assessment.

stephendolan/dotfiles · 41 tokens

comment-sicko

Comment Sicko reviews scoped code comments and suppressions, deleting only comments that fail a strict keep test and reporting structural fixes for the code beneath them.

stephendolan/dotfiles · 35 tokens

pr-comment-reviewer

Critically evaluates an individual PR review comment to determine whether any suggested changes should be implemented. Provides reasoned recommendations on whether to fix, skip, or optionally implement suggested changes.

stephendolan/dotfiles · 40 tokens