Sponsor Suno AI Music arrow_forward
Subagent

Geepers Corpus

Manages corpus linguistics datasets — acquisition, annotation, data-structure validation, and UTF-8 encoding hygiene across reference, historical, and web corpora. Use when acquiring a new corpus or structuring linguistic data for a research tool. Trigger with "set up the corpus", "validate this linguistic dataset".

Type
Subagent
GitHub stars
2.8k
License
MIT
Repo last updated
Sep 27, 2026
Model
sonnet
Version
1.0.0
Author
Jeremy Longshore <[email protected]>

What Geepers Corpus is

Geepers Corpus is a subagent published in the jeremylongshore/tons-of-skills-marketplace repository on GitHub, which has about 2.8k stars. The repository describes itself as: “Model-agnostic agent-skills platform with a harness-free canonical layer, verified adapters, and the ccpi package manager. Explore at tonsofskills.com.”

A subagent is a specialist assistant that Claude can hand part of a task to. It is a markdown file whose frontmatter sets a name, a description that tells Claude when to delegate, and optionally the tools and model it may use; the body becomes the subagent's own system prompt.

Because a subagent works in its own context, it keeps the main conversation focused: Claude can send a narrow job, such as a review or a specialised analysis, to Geepers Corpus and get back a compact result.

How to install Geepers Corpus

Claude Code

  1. Download geepers_corpus.md from the repository.
  2. Save it to ~/.claude/agents/ to use it in every project, or to .claude/agents/ inside one project to share it through version control.
  3. Claude Code watches these folders, so the subagent is usually available right away. Ask Claude to use it by name, or @-mention it to make sure it runs.

Claude Cowork

  1. Cowork loads subagents through plugins. If the repository is packaged as a plugin marketplace, add it under Customize → Plugins → Add marketplace and install the plugin that contains this subagent.
  2. Otherwise, bundle the file into your own plugin's agents/ folder and upload it from Customize → Plugins.

New to extending Cowork? Our plugins guide and Customize guide explain how skills, plugins, and connectors fit together.

Inside the source file

An excerpt from plugins/community/geepers-agents/agents/geepers_corpus.md, shared under the repository's MIT license. Read the full file on GitHub.

Examples

Example 1

Context: Corpus data management user: "I need to download and organize the BNC corpus" assistant: "Let me use geepers_corpus to help with corpus acquisition and structuring."

Example 2

Context: Linguistic research user: "I want to add historical sound change data to Diachronica" assistant: "I'll use geepers_corpus to validate and structure this linguistic data."

Mission

You are the Corpus Linguistics Expert - specializing in language corpora, computational linguistics, and NLP resources. You understand corpus annotation, linguistic data structures, and research methodologies.

Output Locations

  • Reports: ~/geepers/reports/by-date/YYYY-MM-DD/corpus-{project}.md
  • Recommendations: Append to ~/geepers/recommendations/by-project/{project}.md

Domain Expertise

Corpus Types

  • Reference corpora: BNC, COCA, Brown, LOB
  • Historical corpora: COHA, OED quotations
  • Web corpora: Common Crawl, Wikipedia dumps
  • Specialized: Academic, legal, medical corpora

Linguistic Annotations

  • Part-of-speech (POS) tagging
  • Lemmatization
  • Named entity recognition (NER)
  • Dependency parsing
  • Semantic role labeling

Data Formats

  • CoNLL (tab-separated)
  • XML/TEI markup
  • JSON-lines
  • SQLite databases
  • Vertical text format

Key Projects

COCA (dr.eamer.dev/coca)

  • Corpus of Contemporary American English
  • Port 3035, diachronica.com
  • SQLite + mmap for performance

Diachronica

  • Historical linguistics database
  • Sound changes, reconstructions
  • Etymology timelines

Quality Standards for Linguistic Data

  • Source attribution and licensing
  • Annotation scheme documented
  • Consistent encoding (UTF-8)
  • Metadata complete
  • Citation format specified
  • Version control for updates

Coordination Protocol

Delegates to:

  • geepers_corpus_ux: For UI/visualization work
  • geepers_db: For database optimization
  • geepers_data: For data validation

Called by:

  • Manual invocation for linguistic projects

Shares data with:

  • geepers_status: Corpus project updates

Before you install

  • Read the whole file first. Skills, commands, and subagents are instructions Claude will follow, so make sure they match what you want.
  • Check which tools, scripts, or MCP servers it uses. Local servers and scripts run with your permissions.
  • Try it in a test project or a copy of your files before pointing it at real work.
  • Pin the version you tested, and review changes before updating.
  • Watch for instructions that fetch web content or run shell commands; those are where prompt injection risks start. See our prompt injection guide.

FAQ

What is Geepers Corpus?

Geepers Corpus is a subagent for Claude Code and Claude Cowork from the jeremylongshore/tons-of-skills-marketplace repository on GitHub. Manages corpus linguistics datasets — acquisition, annotation, data-structure validation, and UTF-8 encoding hygiene across reference, historical, and web corpora. Use when acquiring a new corpus or structuring linguistic data for a research tool. Trigger with "set up the corpus", "validate this linguistic dataset".

How do I install Geepers Corpus in Claude Code?

Download geepers_corpus.md from the repository. Save it to ~/.claude/agents/ to use it in every project, or to .claude/agents/ inside one project to share it through version control. Claude Code watches these folders, so the subagent is usually available right away. Ask Claude to use it by name, or @-mention it to make sure it runs.

Can I use Geepers Corpus in Claude Cowork?

Cowork loads subagents through plugins. If the repository is packaged as a plugin marketplace, add it under Customize → Plugins → Add marketplace and install the plugin that contains this subagent. Otherwise, bundle the file into your own plugin's agents/ folder and upload it from Customize → Plugins.

Is Geepers Corpus safe to install?

It is a third-party community resource, not reviewed by Anthropic or this site. Read the source file first, check which tools and connectors it uses, and install only from sources you trust.

Similar resources

Browse all skills, subagents, and plugins →

Listing data comes from the public GitHub repository and was last checked in September 2026. Excerpts are © their authors and shared under MIT. This directory is independent and not affiliated with Anthropic or the resource's authors.