atomicstrata/llm-wiki-compiler is a knowledge compiler that turns raw sources into an interlinked Markdown wiki with citations, review state, and retrieval metadata. It helps agents and people build persistent, auditable knowledge bases from materials such as papers, notes, transcripts, PDFs, images, and web pages. The catalogue instructions support using and working with the compiler.
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/atomicstrata/llm-wiki-compiler/claude-mdgit clone --depth 1 https://github.com/atomicstrata/llm-wiki-compilerWrote 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/atomicstrata/llm-wiki-compiler/claude-md)<a href="https://agentmods.dev/instructions/atomicstrata/llm-wiki-compiler/claude-md"><img src="https://agentmods.dev/badge/instructions/atomicstrata/llm-wiki-compiler/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 | $0.00713 | $0.00713 |
| Opus 5 | $0.00357 | $0.00357 |
| Sonnet 5 | $0.00143 | $0.00143 |
| Haiku 4.5 | $0.00071 | $0.00071 |
Grade A, and why
llm-wiki-compiler 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 5d 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.
This is a copy
100% identical to llm-wiki-compiler AGENTS.md — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
llmwiki
A knowledge compiler CLI. Raw sources in, interlinked wiki out.
Development Guidelines
Code Style & Standards
- Code files (TypeScript, Python, JavaScript, shell, SQL) must be smaller than 400 lines excluding comments. Once 400 is exceeded, initiate a refactor. Markdown and other prose/config files (
.md,.mdx,.yaml,.json,.toml) are exempt — long planning documents, roadmaps, and reference catalogs are allowed to grow as substance requires. - Functions must be smaller than 40 lines excluding comments and the catch/finally blocks of try/catch sections. If a function exceeds that, refactor it.
- test files must be smaller than 400 lines excluding comments. Once 400 is exceeded, split the tests into multiple files.
- tests must be smaller than 40 lines excluding comments and the catch/finally blocks of try/catch sections. If a test exceeds that, refactor it, or separate it into multiple tests.
clean code rules
- Meaningful Names: Name variables and functions to reveal their purpose, not just their value.
- One Function, One Responsibility: Functions should do one thing.
- Avoid Magic Numbers: Replace hard-code values with named constants to give them meaning.
- Use Descriptive Booleans: Boolean names should state a condition, not just its value.
- Keep Code DRY: Duplicate code means duplicate bugs. Try and reuse logic where it makes sense.
- Avoid Deep Nesting: Flatten your code flow to improve clarity and reduce cognitive load.
- Comment Why, Not What: Explain the intention behind your code, not the obvious mechanics.
- Limit Function Arguments: Too many parameters confuse. Group related data into objects.
- Code Should Be Self-Explanatory: Well-written code needs fewer comments because it reads like a story.
Comments and Documentation
- include a substantial JSDoc comment at the top of each file. For python files, use google style docstrings
- Write clear comments for complex logic
- Document public APIs and functions
- Use JSDoc comments for functions
- Keep comments up-to-date with code changes
- Document any non-obvious behavior
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.
- 5d ago First seen · 50 lines · 713 tokens per session scan A caf23948048e
llm-wiki-compiler CLAUDE.md is an instructions file published in the GitHub repository atomicstrata/llm-wiki-compiler (1,990 stars, last pushed 3d ago), licensed MIT. It adds 713 tokens to every session, about $0.0036 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to llm-wiki-compiler AGENTS.md, differing in 0 lines, and is treated as a copy.
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.
hippocampus CLAUDE.md
Instructions for sturlese/hippocampus, covering layout, frontmatter schema, conventions, answering questions from the vault (read order) and contradictions.
hippocampus AGENTS.md
Instructions for sturlese/hippocampus: Read and follow CLAUDE.md in the repository root completely before doing any work. It is the canonical project contract, written for Claude Code as the native host; its vault rules and workflows apply unchanged to Codex.
llm-knowledge-base AGENTS.md
Instructions for arturseo-geo/llm-knowledge-base, covering agents.md — llm knowledge base schema, 1. repository layout, 2. agent identity and scope, 3. file naming conventions and 4. article schema.