rk-create

rk-create is a skill for Claude Code from Sixz-AI/repo-knowledge. It costs 67 tokens per session (814 once invoked), scanned A, original, MIT.

A codebase knowledge-base builder that clones a Git repository, documents its functions and classes, and creates a searchable index. A Git repository is a project stored with version history.

In plain words
What is it for?
Creating or indexing a knowledge base from a Git URL, generating documentation for code components, and caching the results for later search.
Why use it?
It turns an unfamiliar repository into searchable documentation, so developers do not have to read every file to find how the code is organised.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the repo-knowledge plugin — 9 skills, 2 agents, 1 hook shipped together

Good fit Creating or indexing a knowledge base from a Git URL, generating documentation for code components, and caching the results for later search.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/sixz-ai/repo-knowledge/rk-create
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.

Any agent
npx skills add Sixz-AI/repo-knowledge --skill rk-create
Clone the repo
git clone --depth 1 https://github.com/Sixz-AI/repo-knowledge

Made for: Claude Code.

Or install repo-knowledge, the plugin that ships this one along with the rest of its 9 skills, 2 agents, 1 hook.

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.

agentmods badge for rk-create

README.md
[![agentmods](https://agentmods.dev/badge/skills/sixz-ai/repo-knowledge/rk-create/github.svg)](https://agentmods.dev/skills/sixz-ai/repo-knowledge/rk-create)
Your own site
<a href="https://agentmods.dev/skills/sixz-ai/repo-knowledge/rk-create"><img src="https://agentmods.dev/badge/skills/sixz-ai/repo-knowledge/rk-create/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.

agentmods 80×15 button for rk-create

Your own site · 80×15
<a href="https://agentmods.dev/skills/sixz-ai/repo-knowledge/rk-create"><img src="https://agentmods.dev/badge/skills/sixz-ai/repo-knowledge/rk-create.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 67 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 814 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00067 $0.00814
Opus 5 $0.00034 $0.00407
Sonnet 5 $0.00013 $0.00163
Haiku 4.5 $0.00007 $0.00081

Measured 9d ago against content hash 4ff11b87adde, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

rk-create 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 9d 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.

skills/rk-create/SKILL.md · 124 lines

How it starts

The opening of the file, as written. The whole thing — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.

RK Create — Initialize Codebase Knowledge Base

Create a new knowledge base from a git repository.

Input

  • Git repository URL (HTTPS or SSH)

Process

Step 1: Clone the Repository

cd ~/.repo-knowledge/_repos/
git clone <git-url> <project-name>

Derive {project-name} from the repo URL (e.g., [email protected]:org/my-project.git -> my-project).

Step 2: Create Project Cache Structure

mkdir -p ~/.repo-knowledge/<project-name>/docs/

Step 3: Scan and Index

Launch an indexer Agent to scan the codebase:

Use the Agent tool with this prompt:

You are a Codebase Indexer Agent.

Codebase path: "~/.repo-knowledge/_repos/{project-name}/"
Cache path: "~/.repo-knowledge/{project-name}/"

## Your Task
Scan the entire codebase and generate documentation for every function and class.

## Rules for Document Granularity
- One document per function
- One document per class (if class < 200 lines)
- If class > 200 lines, split by method — one document per method
- If function > 100 lines, split by logical sections

## For Each Component, Generate:

```markdown
---
cached: {YYYY-MM-DD}
source: {relative/path/to/file.ext}
---

## [Function/Class Name]
**File:** [relative/path/to/file.ext]

### What It Does
[1-2 sentence explanation in English and Chinese]

### Code
```[language]
[actual code]

Parameters

  • param_name (type): Description

Returns

  • (type): Description

Usage Example

[practical working example]

Notes

  • Caveats, edge cases, related functions

## Save Each Document
1. Organize by directory structure matching source:
   `~/.repo-knowledge/{project-name}/docs/{source-dir}/{kebab-case-name}.md`
2. After ALL docs are generated, create `_index.md`:
   ```markdown
   # {project-name} Knowledge Index

   - [component-name](docs/path/component-name.md) — English description(中文描述)

Scan Strategy

  1. Use Glob to find all code files (*.ts, *.js, *.py, *.go, *.java, *.rs, etc.)
  2. Skip: node_modules, .git, dist, build, vendor, pycache
  3. Read each file
  4. Extract functions and classes
  5. Generate doc for each
  6. Save to cache
  7. Build _index.md

Read the full file on GitHub · 124 lines

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.

  1. 9d ago First seen · 124 lines · 67 tokens per session scan A 4ff11b87adde

Subscribe to this mod's changes

rk-create is a skill published in the GitHub repository Sixz-AI/repo-knowledge (2 stars, last pushed 4mo ago), licensed MIT. It adds 67 tokens to every session and 814 once invoked, about $0.0003 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 2026-08-31.