rk-delete

rk-delete is a skill for Claude Code from Sixz-AI/repo-knowledge. It costs 52 tokens per session (283 once invoked), scanned C, original, MIT.

A cleanup procedure that permanently removes a project's codebase knowledge base, cached documentation, cloned repository, and registry entry. A knowledge base is the stored project information used for later code queries.

In plain words
What is it for?
Use it when someone asks to delete a knowledge base, remove a repository, or run rk-delete. It first requires confirmation, then removes the relevant cache and registry records.
Why use it?
It removes stored project data when it is no longer needed, including the local copy of a repository when one exists.

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 Use it when someone asks to delete a knowledge base, remove a repository, or run rk-delete. It first requires confirmation, then removes the relevant cache and registry records.

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

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/sixz-ai/repo-knowledge/rk-delete"><img src="https://agentmods.dev/badge/skills/sixz-ai/repo-knowledge/rk-delete.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 52 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 283 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. 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 $0.00052 $0.00283
Opus 5 $0.00026 $0.00142
Sonnet 5 $0.00010 $0.00057
Haiku 4.5 $0.00005 $0.00028

Measured 10d ago against content hash d8f2b7f6a2fc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade C, and why

rk-delete scanned grade C with 1 finding 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 10d 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

rm -rf ~/.repo-knowledge/<project-name>/
skills/rk-delete/SKILL.md · 39 lines

What it actually says

RK Delete — Remove Knowledge Base

Delete a project's knowledge base completely.

Input

  • Project name

Process

Step 1: Confirm with User

Ask: "Are you sure you want to delete the knowledge base for {project-name}? This will remove all cached documentation."

Step 2: Delete Cache

rm -rf ~/.repo-knowledge/<project-name>/

Step 3: Delete Cloned Repo (skip for personal knowledge bases)

Check ~/.repo-knowledge/<project-name>/_meta.md before deleting (read it first from Step 2's backup or skip if already deleted).

If type: personal or git_url: none: skip this step — there is no cloned repo.

Otherwise:

rm -rf ~/.repo-knowledge/_repos/<project-name>/

Step 4: Update Registry

Remove the project's row from ~/.repo-knowledge/_registry.md.

Step 5: Confirm

Tell the user: "Knowledge base for {project-name} has been deleted."

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. 10d ago First seen · 39 lines · 52 tokens per session scan C d8f2b7f6a2fc

Subscribe to this mod's changes

rk-delete is a skill published in the GitHub repository Sixz-AI/repo-knowledge (2 stars, last pushed 4mo ago), licensed MIT. It adds 52 tokens to every session and 283 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.