WALKERKILLERWALKERKILLER/Look-Tongji-Notes/llmwiki/AGENTS.md

Look-Tongji-Notes / llmwiki

AGENTS.md53 starsChanged 5 months agoMITView on GitHub

In this repository13 other files it gives its agents.
- AGENTS.mdAGENTS.md
- vision-support/AGENTS.mdAGENTS.md
- look-tongji-notesSkill
- addSkill
- cheatsheetSkill
- listSkill
- noteSkill
- pageSkill
- ralphtransSkill
- setupSkill
- transSkill
- wikiSkill
- vision-supportSkill

The file

We found no rules to list in this file: it reads as prose or reference rather than instructions.

Create a free account to mount

Files

AGENTS.md

llmwiki

Purpose

Core Python package for the llmwiki project. Version 1.3.82.

Key Files

File	Description
`__init__.py`	Package root with lazy re-exports and version metadata
`__main__.py`	Module entry point
`_frontmatter.py`	Frontmatter parser (stdlib-only)
`_system_pages.py`	System page slugs and filenames
`adapter_config.py`	Adapter config validation
`backlinks.py`	Backlink injection
`build.py`	Static HTML site builder
`cache.py`	Prompt caching scaffolding
`candidates.py`	Candidate approval workflow
`categories.py`	Category page generator
`changelog_timeline.py`	Changelog and timeline renderer
`cli.py`	CLI entry point
`compare.py`	Entity comparison pages
`completion.py`	Shell completion generators
`confidence.py`	Confidence scoring for wiki pages
`config_schedule.py`	Schedule configuration
`context_md.py`	Folder-level context helpers
`convert.py`	Session transcript converter
`docs_pages.py`	Docs-site compiler
`exporters.py`	AI-consumable export formats
`freshness.py`	Content freshness badges
`graph.py`	Knowledge graph builder
`graphify_bridge.py`	Graphify integration bridge
`ingest_queue.py`	Ingest queue
`lifecycle.py`	Page lifecycle state machine
`link_checker.py`	Link checker
`log_reader.py`	Log parser
`manifest.py`	Build manifest
`models_page.py`	Models page rendering
`obsidian_output.py`	Obsidian vault export
`pipeline.py`	Pipeline orchestrator
`project_topics.py`	Project topic tags
`py.typed`	PEP 561 marker
`quarantine.py`	Convert error quarantine
`queue.py`	Back-compat shim
`references.py`	Reverse-reference index
`schema.py`	Entity schema
`search_facets.py`	Search facets
`search_tree.py`	Tree-aware search
`serve.py`	HTTP server
`skill_installer.py`	Skill installer
`tag_utils.py`	Tag parsing utilities
`tags.py`	Tag operations
`vault.py`	Vault-overlay mode
`viz_heatmap.py`	Activity heatmap
`viz_tokens.py`	Token visualizations
`viz_tools.py`	Tool bar chart
`watch.py`	File watcher

Subdirectories

Directory	Purpose
`adapters/`	Session store adapters
`lint/`	Lint rules and runner
`mcp/`	MCP server
`render/`	CSS and JS assets
`sync/`	Sync status
`synth/`	LLM synthesis

For AI Agents

Working In This Directory

Core llmwiki Python package.
Modules are loosely coupled by domain.

Testing Requirements

Tests in tests/ directory.
Independently testable modules.

Common Patterns

Lazy imports.
Stdlib-only.
Frontmatter parsing.

Dependencies

Internal

llmwiki.adapters
llmwiki.lint
llmwiki.synth
llmwiki.render
llmwiki.sync

External

markdown
graphify
ollama

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

It worked
Partly
It didn't

What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free