A command that runs a complete example of a qualitative research workflow on two included interview transcripts. It loads the files, creates starter codes, codes the text, waits for review, and produces reports and a cited notebook answer.

Use it to demonstrate or verify the setup for transcript ingestion, coding, human review, governance reporting, and cited research answers.

It gives new users a repeatable way to see how the research pipeline works without preparing their own data first.

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-demo.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-demo/github.svg)](https://agentmods.dev/commands/moliver28/corpus-kb/corpus-demo)

Your own site

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

Per session 9 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 255 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	$0.00009	$0.00255
Opus 5.5	$0.00004	$0.00102
Sonnet 5.5	$0.00002	$0.00051
Haiku 4.5	$0.00001	$0.00026

Measured 20d ago against content hash 04d73d655dec, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

corpus-demo 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 20d 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-demo.md · 25 lines

What it actually says

corpus-demo — narrated demo pipeline

Run the full qualitative-coding pipeline on the bundled two-interview demo corpus (docs/demo-corpus/): ingest, codebook seed, coding run, review gate, governance report, and a cited notebook answer.

corpus-kb research demo

Requires corpus-kb setup (Postgres + migrations + models) plus a research-grade embedder: pull qwen3-embedding:8b-q8_0 and set embedding.model/dimensions accordingly (>=1024 dims - the default nomic-embed-text makes the demo abstain by design; see docs/getting-started.md "Before you start").
Every stage narrates what it is doing and links the relevant docs.
Re-runs are safe: file and text hashes make ingested files no-ops.
Long-running and synchronous on every surface: http/mcp/socket POSTs return a receipt envelope (status, exit code, captured narration).
All flags: corpus-kb research demo --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.

20d ago Changed · +2 lines 04d73d655dec
22d ago Changed 65b072b1d2ac
27d ago Changed · +4 lines 5ccd7e13d91a
29d ago First seen · 19 lines · 9 tokens per session scan A 1b93535aaf10

Subscribe to this mod's changes

corpus-demo is a command published in the GitHub repository moliver28/corpus-kb (1 stars, last pushed today), licensed MIT. It adds 9 tokens to every session and 255 once invoked, about $0.0000 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 2026-10-08.

Research

corpus-demo next to 6 commands from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
corpus-demomoliver28/corpus-kb	Command	1	today	MIT	A	9	Claude Code
checklistgithub/spec-kit	Command	148k	yesterday	MIT	A	13	Claude Code
clarifygithub/spec-kit	Command	148k	yesterday	MIT	A	27	Claude Code
specifygithub/spec-kit	Command	148k	yesterday	MIT	A	13	Claude Code
analyzegithub/spec-kit	Command	148k	yesterday	MIT	A	26	Claude Code
convergegithub/spec-kit	Command	148k	yesterday	MIT	A	35	Claude Code
implementgithub/spec-kit	Command	148k	yesterday	MIT	A	14	Claude Code

corpus-kb: Command for Claude Code