What is corpus-classification?

A few-shot classification tool for a document collection. It learns from a small set of examples with labels, then writes predictions for other text chunks.

Use it to build predictions from a seed-label file and list the stored predictions, using either the standard or optional SetFit tier.

It can classify more chunks from a seed set instead of requiring a person to label every item manually. The feature is disabled by default until enabled.

How moliver28/corpus-kb configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to moliver28/corpus-kb. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/moliver28/corpus-kb/master/.claude/commands/corpus-classification.md

Clone the repo

git clone --depth 1 https://github.com/moliver28/corpus-kb

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/moliver28/corpus-kb/corpus-classification/github.svg)](https://agentmods.dev/commands/moliver28/corpus-kb/corpus-classification)

Your own site

<a href="https://agentmods.dev/commands/moliver28/corpus-kb/corpus-classification"><img src="https://agentmods.dev/badge/commands/moliver28/corpus-kb/corpus-classification/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.

Your own site · 80×15

<a href="https://agentmods.dev/commands/moliver28/corpus-kb/corpus-classification"><img src="https://agentmods.dev/badge/commands/moliver28/corpus-kb/corpus-classification.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 13 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 178 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.

Model	Per session	Once invoked
Fable 5.1	$0.00013	$0.00178
Opus 5.5	$0.00005	$0.00071
Sonnet 5.5	$0.00003	$0.00036
Haiku 4.5	$0.00001	$0.00018

Measured 16d ago against content hash 8890e4b2ee0a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

corpus-classification 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 16d 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/commands/corpus-classification.md · 26 lines

What it actually says

corpus-classification — few-shot classification over the corpus

Fit a classifier against a seed label set and write calibrated chunk predictions. Dormant by default: analysis.classification.enabled: false in config.yaml.

Build the predictions (tier head on stored embeddings, or the opt-in setfit tier):
```
corpus-kb classification-build [--seed-file <path>]
```
List the built predictions (bounded window):
```
corpus-kb classification-list [--limit N]
```
A disabled feature is an honest no-op result, not an error.
All flags: corpus-kb classification-build --help

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.

16d ago First seen · 26 lines · 13 tokens per session scan A 8890e4b2ee0a

Subscribe to this mod's changes

corpus-classification is a command published in the GitHub repository moliver28/corpus-kb (1 stars, last pushed today), licensed MIT. It adds 13 tokens to every session and 178 once invoked, about $0.0001 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 2026-10-21.

Data and AI

corpus-classification next to 6 commands from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
corpus-classificationmoliver28/corpus-kb	Command	1	today	MIT	A	13	Claude Code
bootmicrosoft/PromptKit	Command	113	9d ago	MIT	A	14	GitHub Copilot
music-suno-promptfrankxai/Starlight-Intelligence-System	Command	10	yesterday	MIT	A	23	Claude Code
audit-promptOwl-Listener/ai-design-skills	Command	199	5mo ago	MIT	A	13	Claude Code
laravel-ai-sdkjpcaparas/superpowers-laravel	Command	157	4mo ago	MIT	A	27	Claude Code
vlm-ocr-evaluationscdenney/open-science-skills	Command	69	yesterday	none	A	0	Claude Code
dare-llm-integrationdewtech-technologies/dare-method	Command	5	3mo ago	MIT	A	0	Claude Code

corpus-kb: Command for Claude Code