agentmods.dev

corpus-analyze

corpus-analyze is a skill for Claude Code from moliver28/corpus-kb. It costs 51 tokens per session (307 once invoked), scanned A, original, MIT.

A research-analysis helper that chooses a suitable statistical or text-analysis method for a question and explains the choice in plain language.

In plain words
What is it for?
Use it to compare possible methods, understand what their results mean, and check whether your corpus contains the needed data.
Why use it?
It helps when you know what you want to learn but do not know which analysis to use or what data that analysis requires.

Skill for Claude Code

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

Part of the corpus-rag plugin — 3 skills, 2 commands, 2 hooks shipped together

not rated 1repo yesterday A scan 51 tokens original MIT

Good fit Use it to compare possible methods, understand what their results mean, and check whether your corpus contains the needed data.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/moliver28/corpus-kb/corpus-analyze
View source ↗ moliver28/corpus-kb
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.

Any agent
npx skills add moliver28/corpus-kb --skill corpus-analyze
Clone the repo
git clone --depth 1 https://github.com/moliver28/corpus-kb

Made for: Claude Code.

Or install corpus-rag, the plugin that ships this one along with the rest of its 3 skills, 2 commands, 2 hooks.

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 corpus-analyze

README.md
[![agentmods](https://agentmods.dev/badge/skills/moliver28/corpus-kb/corpus-analyze/github.svg)](https://agentmods.dev/skills/moliver28/corpus-kb/corpus-analyze)
Your own site
<a href="https://agentmods.dev/skills/moliver28/corpus-kb/corpus-analyze"><img src="https://agentmods.dev/badge/skills/moliver28/corpus-kb/corpus-analyze/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 corpus-analyze

Your own site · 80×15
<a href="https://agentmods.dev/skills/moliver28/corpus-kb/corpus-analyze"><img src="https://agentmods.dev/badge/skills/moliver28/corpus-kb/corpus-analyze.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 51 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 307 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 $0.00051 $0.00307
Opus 5.5 $0.00020 $0.00123
Sonnet 5.5 $0.00010 $0.00061
Haiku 4.5 $0.00005 $0.00031

Measured yesterday against content hash 1196db2bcacc, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

corpus-analyze 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 yesterday.

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.

plugins/corpus-rag/skills/corpus-analyze/SKILL.md · 34 lines

What it actually says

Corpus Analyze

Help a novice pick the right analysis and understand the result. The engine has a method selector; this skill wraps it in plain language.

Steps

  1. Collect the question in one sentence. Ask the user if it is unclear.

  2. Ask the engine to name the method:

    corpus-kb analysis-select-method

    Follow the engine's prompt for the question text. The output names a method and says why it fits.

  3. Explain the choice in plain English. One short paragraph: what the method does, what data it needs, what the result will mean.

  4. Suggest the next question the user can ask. Offer to run the method.

  5. If the engine names more than one method, present them as a short list. Say what each one answers and let the user pick.

Notes

  • The user may say "I don't know what analysis to run". That is the main use of this skill. Start from their goal, not from method names.
  • Keep claims about the data honest. If the corpus lacks the data a method needs, say so and propose ingesting more files (see corpus-ingest).
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. yesterday First seen · 34 lines · 51 tokens per session scan A 1196db2bcacc

Subscribe to this mod's changes

corpus-analyze is a skill published in the GitHub repository moliver28/corpus-kb (1 stars, last pushed yesterday), licensed MIT. It adds 51 tokens to every session and 307 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-11-07.

Analytics and metricsResearch
Related

corpus-analyze compared with skills from other repositories

corpus-analyze next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
corpus-analyzemoliver28/corpus-kbSkill1yesterdayMITA51Claude Code
imagegenopenai/codexSkill134ktodayApache-2.0A113Codex
local-ai-agentsmicrosoft/ai-agents-for-beginnersSkill79kyesterdayMITA200Claude Code, Codex
playwright-climicrosoft/playwrightSkill100kyesterdayApache-2.0A19Claude Code
browser-automationopenclaw/openclawSkill394ktodayMITA36Claude Code
systematic-debuggingobra/superpowersSkill314k5d agoMITA21Claude Code
next-cache-components-adoptionvercel/next.jsSkill143ktodayMITA95Claude Code