A qualitative-research tool for labeling interview or other text transcripts, building a codebook, and developing themes. Qualitative research studies meanings and experiences in text or other non-numeric data.

Use it to prepare and anonymize transcripts, choose a coding approach, create codes, identify themes, assess agreement between coders, and explore large text collections.

It gives a consistent way to move from raw transcripts to defensible findings. It also includes checks such as comparing coders and validating automated suggestions against manual coding.

code-themes — Command for coding agents by Marazii: A qualitative-research tool for labeling interview or other text…

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.

agentmods

npx agentmods add commands/marazii/research-co-pilot/code-themes

Clone the repo

git clone --depth 1 https://github.com/Marazii/research-co-pilot

Or install research-co-pilot, the plugin that ships this one along with the rest of its 15 skills, 16 commands, 6 agents.

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/marazii/research-co-pilot/code-themes.svg)](https://agentmods.dev/commands/marazii/research-co-pilot/code-themes)

Your own site

<a href="https://agentmods.dev/commands/marazii/research-co-pilot/code-themes"><img src="https://agentmods.dev/badge/commands/marazii/research-co-pilot/code-themes.svg" alt="Measured on agentmods" height="20"></a>

Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 235 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

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	$0.00016	$0.00235
Opus 5	$0.00008	$0.00118
Sonnet 5	$0.00003	$0.00047
Haiku 4.5	$0.00002	$0.00023

Measured 4d ago against content hash 5661be412117, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

code-themes 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 4d 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.

commands/code-themes.md · 21 lines

What it actually says

Invoke the qualitative-coding skill from the research-co-pilot plugin and execute its full workflow.

The skill file is at skills/qualitative-coding/SKILL.md relative to this plugin. Read it and follow it precisely — including:

Phase 1-2: Diagnose the project, prepare the corpus (anonymize, standardize).
Phase 3-5: Choose tradition (thematic, grounded theory, IPA, framework, content), build codebook, code.
Phase 6: Inter-rater reliability where applicable.
Phase 7: Theme development and final report.
Phase 8: NLP-assisted exploration for large corpora — always validate against hand-coding.

For corpora with many files, delegate to the transcript-coder subagent for cleaning and batch coding.

User input: $ARGUMENTS

If no transcripts/question were given, ask what data they have and what tradition / question is driving the analysis.

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.

4d ago First seen · 21 lines · 16 tokens per session scan A 5661be412117

Subscribe to this mod's changes

code-themes is a command published in the GitHub repository Marazii/research-co-pilot (13 stars, last pushed 3mo ago), licensed MIT. It adds 16 tokens to every session and 235 once invoked, about $0.0001 per session on Opus 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 2026-08-30.

Research academic ai-research claude claude-code claude-skills data-analysis

code-themes

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

What this file has done since we first saw it

Other commands, from other repositories

ars-lit-review

ars-plan

ars-revision-coach

factcheck

ars-3w

ars-citation-check