# okf-derivation-reader

The okf-derivation-reader Claude Code subagent answers a task set using an OKF bundle. It works from the bundle alone, without task references or extra context.

- subagent · `type=agent` · Claude Code, Codex, Cursor · ★ 105 repo stars
- Author: wmahfoudh
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/wmahfoudh/okf/tree/HEAD/skills-pi/okf-produce/agents/okf-derivation-reader.md
- Updated: 2026-10-31
- Security check: automated, 2026-11-17 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/agents/okf-derivation-reader

## What it does

The subagent answers each question using concepts stored in an OKF bundle. It gives the paths of the concepts behind each answer and says whether the bundle contained the answer directly or supplied knowledge from which it could be derived.

It also reports what the bundle marks as unknown: the `# Not known` section of `overview.md` and concepts whose status is `draft`. Its input is the bundle path and the task-set questions; it receives no extraction context, task references, or expected answers. The available tools are `read`, `grep`, `find`, and `ls`.

## Install

### Claude Code (native platform)

**Manually: put the files in place**
- File: `.claude/agents/okf-derivation-reader.md` — For all projects use ~/.claude/agents/. Claude delegates by the description field or an @-mention

### Codex

**Manually: put the files in place**
- File: `.codex/agents/okf-derivation-reader.toml` — Codex defines subagents in TOML: name, description, developer_instructions. Move the Markdown text into developer_instructions by hand. For all projects use ~/.codex/agents/

### Cursor

**Manually: put the files in place**
- File: `.cursor/agents/okf-derivation-reader.md` — Cursor also reads .claude/agents/

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/wmahfoudh/okf/tree/HEAD/skills-pi/okf-produce/agents/okf-derivation-reader.md

## When to use it
- answer questions from an OKF bundle
- trace each answer to the concepts used
- identify answers supplied directly by the bundle
- collect concepts and notes marked as unknown

## Example prompts
- Answer this task set using the OKF bundle at `path/to/bundle`.
- For each answer, show the concepts you used and their paths.
- Report the unknown items from `overview.md` and concepts marked `draft`.

## Similar
- [formula-derivation](https://affpapa.org/en/nevibecode/skills/formula-derivation.md) — skill · 589 installs
- [okf-knowledge-base](https://affpapa.org/en/nevibecode/skills/okf-knowledge-base.md) — skill · 9400 installs
- [okf](https://affpapa.org/en/nevibecode/skills/okf.md) — skill · 1200 installs
- [memory-okf](https://affpapa.org/en/nevibecode/skills/memory-okf.md) — skill · 305 installs
- [nature-reader](https://affpapa.org/en/nevibecode/skills/nature-reader.md) — skill · 16600 installs
- [okf-open-knowledge-format](https://affpapa.org/en/nevibecode/skills/okf-open-knowledge-format.md) — skill · ★ 141 repo stars

From the same set: [wmahfoudh/okf](https://affpapa.org/en/nevibecode/by/wmahfoudh/okf.md) — 8 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
