wikimind: Instructions file for Claude Code

CLAUDE.md

wikimind CLAUDE.md is an instructions file for Claude Code from thaihoc215/wikimind. It costs 2,532 tokens per session, scanned A, original, MIT.

Project instructions for WikiMind, an LLM-powered tool that maintains a searchable wiki in a `.wiki/vault/` folder. They cover its command-line tool, MCP server, structure, build process, tests, and how to add operations.

In plain words
What is it for?
Use them when adding WikiMind operations, changing its command-line tool or MCP server, updating LLM output validation, or running its Python tests.
Why use it?
They give a coding agent the project context needed to change WikiMind safely and consistently. They also document how to build and test changes without needing live language-model API calls.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions AGENTS.md; mentions OpenCode.

This is thaihoc215/wikimind's own configuration. It tells Claude Code how to work on wikimind itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything wikimind configures →

Reuse

Borrowing it

Nothing to install: this file belongs to thaihoc215/wikimind. 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/thaihoc215/wikimind/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/thaihoc215/wikimind

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.

agentmods badge for wikimind CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/thaihoc215/wikimind/claude-md/github.svg)](https://agentmods.dev/instructions/thaihoc215/wikimind/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/thaihoc215/wikimind/claude-md"><img src="https://agentmods.dev/badge/instructions/thaihoc215/wikimind/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.

agentmods 80×15 button for wikimind CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/thaihoc215/wikimind/claude-md"><img src="https://agentmods.dev/badge/instructions/thaihoc215/wikimind/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,532 This file is loaded in full into every session.
When invoked 2,532 The same file — it is already loaded in full.
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 $0.02532 $0.02532
Opus 5.5 $0.01013 $0.01013
Sonnet 5.5 $0.00506 $0.00506
Haiku 4.5 $0.00253 $0.00253

Measured 14d ago against content hash 53339154b90b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

wikimind CLAUDE.md 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 14d 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.

CLAUDE.md · 206 lines

How it starts

The opening of the file, as written. The whole thing — 206 lines — stays where its author put it; the contents beside it link to each section on GitHub.

WikiMind — Agent Instructions

WikiMind is an LLM-powered wiki tool that maintains itself. It has two modes: a CLI (Mode B, calls an LLM provider directly) and an MCP server (Mode A, the AI assistant IS the LLM). Both write to the same .wiki/vault/ directory.

See ARCHITECTURE.md for a full architecture walkthrough.


Build & test

pip install -e .           # install with editable mode
pip install -e ".[dev]"    # add test deps
pip install -e ".[pdf]"    # add optional PDF support

pytest                     # run all 180 tests (no API keys needed — all LLM calls are mocked)

Requires Python ≥ 3.11. Entry point: wikimind.cli:app (Typer).


Project structure

wikimind/
├── cli.py          # Typer CLI — 10 commands, each loads config → WikiStore + LLMClient + Retriever → operation
├── config.py       # TOML loader → typed dataclasses (ProjectConfig, LLMConfig, WikiConfig, PathsConfig)
├── wiki.py         # WikiStore — ALL filesystem ops (read/write pages, index, log, dedup via SHA256)
├── llm.py          # LLMClient + ProviderAdapter (Anthropic / OpenAI / Ollama) — all return (json, in_tok, out_tok)
├── llm_schema.py   # Typed frozen dataclasses + parse_*() validators for all LLM tool outputs
├── retrieval.py    # Retriever protocol + 3 backends: KeywordIndex / BM25 / Qmd
├── server.py       # FastMCP server — 10 tools, path-sandboxed, background qmd embed thread
├── operations/     # Business logic (ingest, query, lint) — no direct LLM calls in CLI commands
└── prompts/        # System prompts + JSON tool schemas for each operation

Core pattern: adding a new operation

Every operation follows a strict 3-part structure:

  1. prompts/X.py — X_SYSTEM_PROMPT string + X_TOOL JSON schema dict
  2. operations/X.py — def x(store: WikiStore, llm: LLMClient, retriever: Retriever, ...) → XResult
  3. cli.py — Typer command that loads config, instantiates dependencies, calls operations.x()

Read the full file on GitHub · 206 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. 14d ago Changed · +11 lines · +270 tokens per session 53339154b90b
  2. 2mo ago First seen · 195 lines · 2,262 tokens per session scan A 087032732a7c

Subscribe to this mod's changes

wikimind CLAUDE.md is an instructions file published in the GitHub repository thaihoc215/wikimind (2 stars, last pushed 15d ago), licensed MIT. It adds 2,532 tokens to every session, about $0.0101 per session on Opus 5.5. 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.

Related

wikimind CLAUDE.md compared with instructions from other repositories

wikimind CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
wikimind CLAUDE.mdthaihoc215/wikimindInstructions file215d agoMITA2,532Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file144ktodayMITA7,461Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,685GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchainInstructions file150ktodayMITA4,680Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,086GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file282k3d agoMITA4,335Codex, OpenCode