What is corpus-research-cycle?

A command that runs a complete qualitative research workflow, from loading source material through coding and reporting. It pauses at decisions that require a person, such as approving new codes, and can continue after those decisions are made.

Use it to process interview or other text data, run research stages in guided or unattended modes, watch a folder for new files, and emit machine-readable progress events.

It prevents important research judgements from being made automatically while still coordinating the repeatable parts of the process.

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

Your own site

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

Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 425 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	$0.00015	$0.00425
Opus 5.5	$0.00006	$0.00170
Sonnet 5.5	$0.00003	$0.00085
Haiku 4.5	$0.00002	$0.00042

Measured 20d ago against content hash 8c5a20b142d3, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

corpus-research-cycle 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-research-cycle.md · 49 lines

What it actually says

corpus-research-cycle — the full pipeline with human-critical gates

Chain ingest -> inductive -> deductive -> keywords -> report without writing a step script. The cycle HALTS at human-critical gates - codebook_promotion is hard-floored (promotion is never automated) - prints AWAITING HUMAN: <gate> plus the exact next command, and resumes when you re-run it after acting on the gate.

Postures:

Fully in the loop - exactly ONE stage per call:
```
corpus-kb research cycle --mode in
```
On the loop - one stage, then it asks before continuing:
```
corpus-kb research cycle --mode on [--guide]
```

Out of the loop - unattended except at the halt gates:

corpus-kb research cycle --mode out --dir <drop-dir> --question "<q>" [--guide]

Watch a drop directory in the foreground (re-arms on new files):
```
corpus-kb research cycle --mode out --watch <dir>
```
--guide turns every halt into a taught decision (proposed codes, example units, promote-vs-skip consequences); --json emits one stage/gate event per line for agents.
Unattended runs: --approve confirms every gate without asking; --deny refuses every gate. Closed stdin cannot hang the cycle.
Long-running and synchronous on every surface: http/mcp/socket POSTs run the same cycle and return the receipt when it ends. Exit codes: 0 complete; 2 embeddings unavailable; 10-17 one gate halted; 20 approval denied; 21 awaiting approval.
All flags: corpus-kb research cycle --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 8c5a20b142d3
22d ago Changed · +4 lines a5ffb85ff9ff
29d ago First seen · 43 lines · 15 tokens per session scan A f323a09ef897

Subscribe to this mod's changes

corpus-research-cycle is a command published in the GitHub repository moliver28/corpus-kb (1 stars, last pushed today), licensed MIT. It adds 15 tokens to every session and 425 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 2026-10-08.

Research

corpus-research-cycle next to 6 commands from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
corpus-research-cyclemoliver28/corpus-kb	Command	1	today	MIT	A	15	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