What is kbask CLAUDE.md?

Project-specific instructions for kbask, a Python MCP server that combines two code-analysis tools. One maps where code is connected, while the other explains why parts of the code exist; MCP is a standard way for AI clients to use tools.

Asking questions about a codebase, tracing calls and imports, finding ownership, and creating onboarding explanations through an MCP-compatible client.

They help an AI assistant understand both a codebase’s structure and its purpose, reducing the guesswork involved in tracing unfamiliar code and onboarding to a project.

How sughosh-pocketfm/kbask configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to sughosh-pocketfm/kbask. 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/sughosh-pocketfm/kbask/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/sughosh-pocketfm/kbask

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/instructions/sughosh-pocketfm/kbask/claude-md/github.svg)](https://agentmods.dev/instructions/sughosh-pocketfm/kbask/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/sughosh-pocketfm/kbask/claude-md"><img src="https://agentmods.dev/badge/instructions/sughosh-pocketfm/kbask/claude-md/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/instructions/sughosh-pocketfm/kbask/claude-md"><img src="https://agentmods.dev/badge/instructions/sughosh-pocketfm/kbask/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 3,623 This file is loaded in full into every session.

When invoked 3,623 The same file — it is already loaded in full.

Security scan B 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.

Model	Per session	Once invoked
Fable 5.1	$0.03623	$0.03623
Opus 5.5	$0.01449	$0.01449
Sonnet 5.5	$0.00725	$0.00725
Haiku 4.5	$0.00362	$0.00362

Measured 2mo ago against content hash 9dfd87b6b7c1, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

kbask CLAUDE.md scanned grade B 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 2mo 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

│ │ ├── codex.py # writes ~/.codex/config.toml

CLAUDE.md · 330 lines

How it starts

The opening of the file, as written. The whole thing — 330 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — kbask

Guidance for Claude Code (and other AI agents) working in this repo.

What this project is

kbask is a single Python MCP (Model Context Protocol) server that joins two upstream code-analysis tools into one MCP endpoint:

Graphify — deterministic tree-sitter AST graph (calls, imports, ownership). Tells you where things are.
Understand-Anything — LLM-derived semantic knowledge graph (purpose, domain, onboarding narrative). Tells you why things exist.

The product value is the hybrid layer (ask / trace / onboard), which queries the structural graph and decorates the result with the semantic graph's narrative. The host LLM (Claude / Codex / Gemini) does the synthesis — kbask itself never calls a model.

Host-agnostic: works in any MCP-compatible client (Claude Code, Codex CLI, Gemini CLI, AGY future).

Public repo: https://github.com/sughosh-pocketfm/kbask. PyPI name target: kbask (fallback kbask).

Critical mental model

Graphify is a self-running CLI; Understand-Anything is not.

graphify update . runs deterministically — tree-sitter parses, writes graphify-out/graph.json. Cheap, fast, idempotent.
Understand-Anything has no analyzer binary. Its knowledge graph is built by an LLM following prompts shipped in the Claude Code plugin (auto-update-prompt.md). The output lives at <repo>/.understand-anything/knowledge-graph.json.

So kbask update does not rebuild the semantic graph from scratch. It:

Runs graphify update for the structural side.
Mirrors the upstream .understand-anything/knowledge-graph.json into kbask-out/knowledge-graph.json if present.
Tracks per-file content hashes in kbask-out/meta.json for incremental change detection.

If .understand-anything/ is absent, structural tools still work; the semantic tools return a clean not built error pointing the user at the right command in their host (/understand-update in Claude Code).

Read the full file on GitHub · 330 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.

2mo ago First seen · 330 lines · 3,623 tokens per session scan B 9dfd87b6b7c1

Subscribe to this mod's changes

kbask CLAUDE.md is an instructions file published in the GitHub repository sughosh-pocketfm/kbask (0 stars, last pushed 2mo ago), licensed MIT. It adds 3,623 tokens to every session, about $0.0145 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

kbask CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
kbask CLAUDE.mdsughosh-pocketfm/kbask	Instructions file	0	2mo ago	MIT	B	3,623	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

kbask: Instructions file for Claude Code