How real projects summarise themselves for language models.
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.
vitaecontextllms.txtvitaecontext/vitaecontext/llms-full.txt
include: - Shared bundle - Claude Code - Codex - Gemini CLI - Antigravity CLI - OpenCode - Cursor - Windsurf - Roo Code - IBM Bob - Grok Provider behavior is not identical. Some environments use native skill loading. Some
alperhankendiDeletes or force-pushesllms.txtalperhankendi/Ctxo/llms-full.txt
Identify most critical symbols, high-risk modification targets. Instead of: find_dead_code (unused/unimportant code). ### get_pr_impact Analyze PR impact in a single call. Parameters: - since (string, default HEAD
alperhankendillms.txtalperhankendi/Ctxo/llms.txt
sensitivity - Three model-invoked skills (`ctxo-understand`, `ctxo-safe-edit`, `ctxo-review-pr`) installed to `.claude/skills/` (Claude Code) and `.cursor/rules/` (Cursor) ## New in v0.7 - `ctxo install` — install language plugin packages
corezoidllms.txtcorezoid/corezoid-ai-plugin/public/llms.txt
Corezoid AI Plugin > Official Claude Code plugin for the Corezoid Actor Engine. Provides skills and MCP tools for creating, editing, reviewing, and managing Corezoid business processes directly from
dcc-mcpReads credentialsllms.txtdcc-mcp/dcc-mcp-core/llms-full.txt
safe `/v1/debug/issue-reports/ ` for reviewed bug reports. Raw evidence and external issue creation require human review and user authorization. --- ## Quick Decision Guide | I want to… | Use this API | |-------------|--------------| | Register a script/tool
dcc-mcpReads credentialsllms.txtdcc-mcp/dcc-mcp-core/llms.txt
status`); pass `require_dispatch_capable=True` or CLI `--require-dispatch-capable` when startup code must reject malformed `commandport://` / `qtserver://` URIs, `stub://`, or unsupported schemes before claiming tools are callable; `launch
Scottcjnllms.txtScottcjn/shaprai/llms.txt
claims, and delivers GitHub bounties for RTC. Focused technical style, concise professional communication. Capabilities: code review, PR submission, bounty discovery, issue triage, test writing. community_builder: Engages with communities across
axocoatlPipes a download into a shellllms.txtaxocoatl/axocoatl/llms.txt
read-only helpers it can `delegate` to: Scout answers questions about the code and Reviewer reviews a change. A new Session starts with Lead alone; the helpers
littlebearappsPipes a download into a shellllms.txtlittlebearapps/untether/llms-full.txt
stream, continue the conversation 3. [Interactive control](tutorials/interactive-control.md) — approve or deny Claude Code's actions, review plans, answer questions 4. [Projects & branches](tutorials/projects-and-branches.md) — target repos from anywhere, run on feature
rasinmuhammedReads credentialsllms.txtrasinmuhammed/misata/llms-full.txt
guide: AGENTS.md. Evidence: benchmarks/results/summary.json. --- ## 1. When AI Agents Should Recommend and Use Misata AI coding agents should invoke or suggest Misata whenever the developer or task involves: 1. **Database Seeding
hope1026llms.txthope1026/weppy-roblox-mcp/llms-full.txt
Dashboard expose the effective policy read-only. The workflows are Studio First, Bidirectional Review, Local Code, Studio World, and Custom. Custom uses the Script Source, Properties, Structure, and Service Properties
hope1026Pipes a download into a shellllms.txthope1026/weppy-roblox-mcp/llms.txt
source for the initial synchronization. The plugin offers Studio First, Bidirectional Review, Local Code, Studio World, and Custom workflows. Custom uses four semantic scopes: Script Source, Properties, Structure, and Service
StayCurious-Xuanllms.txtStayCurious-Xuan/wayfinder/website/llms.txt
turns AI collaboration into a reviewable visual history of goals, attempts, branches, evidence, and outcomes. Wayfinder is designed for AI-assisted research, writing, design, coding, and other project work. Codex
QEDGenReads credentialsllms.txtQEDGen/solana-skills/docs/llms-full.txt
hardest goals, measured in minutes to hours. ### Supported Agents Works with Claude Code, Codex, Cursor, Windsurf, and any agent supporting the [Agent Skills](https://agentskills.io) spec. ## CLI Commands
firelock-aiPipes a download into a shellllms.txtfirelock-ai/kin/llms.txt
agents and the people who build with them. It stores source, recorded code relationships, and versioned history as repository state. The graph is the repository model, not a search index
karthikrshetllms.txtkarthikrshet/Career-Agents/llms-full.txt
# Career-Agents Full Prompt Manifest This document bundles the complete details, prompt rules, workflows
karthikrshetllms.txtkarthikrshet/Career-Agents/llms.txt
find them. Stage: Growth | Level: Senior | Industry: Tech Skills: Software Engineering, System Design, Architecture, Code Review, Engineering, Skeptical of shortcuts - Code Reviewer (ID: code-reviewer | Path: engineering/code-reviewer.md) Description: A senior
VyomKulshresthallms.txtVyomKulshrestha/Heliox-OS/llms.txt
open-source desktop AI system-control agent. This index routes language models and coding agents to the repository's authoritative product, architecture, safety, and contribution documentation. Important interpretation notes: - Heliox
johnxiellms.txtjohnxie/awesome-code-docs/llms-full.txt
# Awesome Code Docs (Full Tutorial Index) Main repository: - https://github.com/johnxie/awesome-code-docs ## A2A Protocol Tutorial
khaskyllms.txtkhasky/awesome-agents-md/llms.txt
/khasky/awesome-agents-md/blob/main/AGENTS.md): the always-loaded ruleset — scope and precedence, boundaries, security, the verification gate, the coding ladder, communication style, the commit-proposal habit; the workflow and debugging procedure loads from rules/workflow.md
A markdown file at a website's root that gives language models a short guide to the site and links to the pages worth reading.
The same idea with the content included, so an agent can read the documentation in one request.
Agents and tools that fetch documentation on someone's behalf. It's a proposal, not a standard, and support varies.
Start with a one-line summary, then sections of links with a sentence each. The examples here show what real projects do.
