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.
npx agentmods add instructions/doum1004/llmwiki-cli/claude-mdgit clone --depth 1 https://github.com/doum1004/llmwiki-cliWrote 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.
[](https://agentmods.dev/instructions/doum1004/llmwiki-cli/claude-md)<a href="https://agentmods.dev/instructions/doum1004/llmwiki-cli/claude-md"><img src="https://agentmods.dev/badge/instructions/doum1004/llmwiki-cli/claude-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.01695 | $0.01695 |
| Opus 5 | $0.00847 | $0.00847 |
| Sonnet 5 | $0.00339 | $0.00339 |
| Haiku 4.5 | $0.00169 | $0.00169 |
Grade A, and why
llmwiki-cli 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 3d 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.
How it starts
The opening of the file, as written. The whole thing — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LLM Wiki CLI — AI / agent context
Audience: This file is for AI assistants and coding agents (instructions, rules, architecture, conventions). Humans should use README.md for project overview, installation, badges, and user-oriented examples.
What this is
A CLI tool that helps LLM agents (Claude Code, Codex, etc.) build and maintain personal knowledge bases. The CLI is the hands — it reads, writes, searches, and manages wiki files. The LLM is the brain — it decides what to create, update, and connect.
Key principle: The CLI never calls any LLM API. It is a pure filesystem tool: markdown under the wiki root via StorageProvider / WikiManager.
Write path: wiki write <path> reads JSON from stdin, validates fields, writes YAML frontmatter + markdown body, and upserts wiki/index.md for paths under wiki/ (except wiki/index.md). There is no separate index command. To edit a page: wiki read → merge in the agent → wiki write with full JSON.
Tech stack
- Runtime: Bun (development), Node.js (published bundle)
- Language: TypeScript
- Dependencies: commander (CLI), js-yaml (YAML parsing)
- Build:
bun buildbundles todist/index.jstargeting Node.js - Tests: Bun test runner (
bun test)
LLM agent skill guide
Run wiki skill to print the full guide. Source of truth for that text is the SKILL_GUIDE string in src/commands/skill.ts — keep it aligned with commands registered in src/index.ts and with scaffolded wiki docs in src/lib/templates.ts (e.g. SCHEMA.md). End users are also pointed here from README.
Project structure
dist/index.js # Built bundle (npm-published artifact)
src/
index.ts # CLI entry point (source)
types.ts # Shared TypeScript interfaces
lib/
storage.ts # StorageProvider factory (createProvider → WikiManager)
wiki.ts # WikiManager: filesystem StorageProvider
config.ts # .llmwiki.yaml read/write
registry.ts # Global registry (~/.config/llmwiki/registry.yaml)
resolver.ts # Wiki resolution chain (--wiki → cwd → walk up → default)
templates.ts # Default file content (SCHEMA.md, index.md; optional viz workflow/scripts for drop-in)
search.ts # Full-text search with term-frequency ranking
index-manager.ts # IndexManager: uses StorageProvider for index.md (upsert/remove)
frontmatter.ts # YAML frontmatter parse/detect/add
link-parser.ts # Wikilink extraction and link graph building
commands/
init.ts # wiki init (--name, --domain)
registry.ts # wiki registry
use.ts # wiki use
read.ts # wiki read
write.ts # wiki write (JSON stdin)
delete.ts # wiki delete
list.ts # wiki list
search.ts # wiki search
lint.ts # wiki lint
links.ts # wiki links
backlinks.ts # wiki backlinks
orphans.ts # wiki orphans
status.ts # wiki status
skill.ts # wiki skill (print LLM agent guide)
test/
init.test.ts # Config, registry, resolver, templates, init integration
read-write.test.ts # WikiManager page operations
storage.test.ts # StorageProvider factory
filesystem-provider.test.ts # Filesystem provider contract tests
commands.test.ts # End-to-end CLI command integration tests
scripts/
generate-viz-scripts.ts # Extracts viz build scripts from templates.ts (used by demo workflow)
test-wiki-page/
wiki/ # Example wiki pages for live demo on GitHub Pages
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.
- 3d ago First seen · 151 lines · 1,695 tokens per session scan A 10f9bf4b46b3
llmwiki-cli CLAUDE.md is an instructions file published in the GitHub repository doum1004/llmwiki-cli (101 stars, last pushed 4mo ago), licensed MIT. It adds 1,695 tokens to every session, about $0.0085 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 2026-08-30.
Other instructions, from other repositories
llm-wiki-agent AGENTS.md
AGENTS.md instructions for SamurAIGPT/llm-wiki-agent, covering llm wiki agent — schema & workflow instructions, how to use, directory layout, page format and ingest workflow.
llm-wiki-agent CLAUDE.md
Claude Code instructions for SamurAIGPT/llm-wiki-agent, covering llm wiki agent — schema & workflow instructions, slash commands (claude code), directory layout, page format and ingest workflow.
llm-wiki-agent GEMINI.md
Gemini CLI instructions for SamurAIGPT/llm-wiki-agent, covering llm wiki agent — schema & workflow instructions, how to use, directory layout, page format and ingest workflow.
llm-wiki-compiler AGENTS.md
AGENTS.md instructions for atomicstrata/llm-wiki-compiler, covering llmwiki, development guidelines, code style & standards, clean code rules and comments and documentation.
obsidian-mcp-server AGENTS.md
Instructions for cyanheads/obsidian-mcp-server, covering agent protocol, what's next?, core rules, patterns and tool — obsidianlisttags.
student-llm-wiki AGENTS.md
Instructions for IssacW228/student-llm-wiki, covering student llm wiki — agent instructions, 操作规则 operation rules, token预算规则(最高优先级), 架构 architecture and 命令 commands.