How real projects summarise themselves for language models.
Kanevryllms.txtKanevry/session-orchestrator/site/llms.txt
counted 2026-09-19 at 8f6ac022 · skills 50 · commands 26 · agents 14 · hooks 28 · test files 692 · sessions 433 · learnings 253 · npm downloads (30d) 1728 · GitHub stars 52 Generated
MrPunyapalllms.txtMrPunyapal/laravel-auditor/docs/llms-full.txt
facts: PHP and Laravel versions, database engine, route surface, models, migrations, dependencies, authorization setup, tests, and ecosystem packages. These facts come from Laravel Auditor's context tools, not from guessing
ariffazilllms.txtariffazil/arifOS/static/llms-full.txt
assume A2A federation is live. --- ## Constitutional Floors (13 Floors) Every AI action is tested against all 13 floors in real-time. A single floor failure triggers a HOLD verdict
assafkipllms.txtassafkip/huntkit/llms.txt
Install ``` /plugin install assafkip/huntkit ``` Or clone from https://github.com/assafkip/huntkit. ## Intended use Authorized security testing, due diligence, journalistic / academic research on public figures, defensive threat intelligence and incident response
sandraschillms.txtsandraschi/blender-mcp/llms-full.txt
Guidelines for AI-assisted development** - Best practices for working with AI - Code quality standards - Testing requirements - Documentation expectations --- ### **2. AI Development Tools Comparison** 📄 [AI_DEVELOPMENT_TOOLS_COMPARISON.md](AI_DEVELOPMENT_TOOLS_COMPARISON.md) **Comparison of AI coding assistants
xiaobei930llms.txtxiaobei930/cc-best/docs/llms.txt
commands (role, mode, build, git, context, quality, ops, setup) - 19 skills (backend, frontend, testing, security, architecture, devops, git, learning) - 8 agents (architect, planner, code-reviewer, code-simplifier, security-reviewer
datallmhubllms.txtdatallmhub/agentflow4j/docs/llms.txt
walkthrough of `BudgetPolicy`, `ToolPolicy`, `StatePolicy` and `ApprovalGate` on a refund-issuing support agent ## Testing & samples - [Testing](https://datallmhub.github.io/agentflow4j/testing/): `MockAgent` and `TestGraph` for LLM-free unit testing of graph workflows
remete618llms.txtremete618/widemem-ai/llms.txt
README.md#claude-code-skill): persistent-memory skill powered by widemem - [Development](README.md#development): running tests and contributing
undergroundrapllms.txtundergroundrap/UEFN-TOOLBELT/llms.txt
tb.register()` once before `mcp_start`. ## Key files for AI agents - `AGENTS.md` — repository authority, testing, launch, and publishing gates - `CLAUDE.md` — full codebase context, every tool table, mandatory rules - `docs/PIPELINE.md` — 6-phase
vstorm-collms.txtvstorm-co/agenticos/llms.txt
what it cost and who approved it — written even when the run failed. This test is written to be applied to other products in the category, and to this
dcc-mcpllms.txtdcc-mcp/dcc-mcp-core/llms-full.txt
# dcc-mcp-core — Full API Reference > This document provides comprehensive API documentation for AI
dcc-mcpllms.txtdcc-mcp/dcc-mcp-core/llms.txt
composes with `HostUiDispatcherBase` or any `drain_queue(budget_ms)` pump. Use `ManualHostTimerAdapter` for conformance tests, `ThreadedHostTimerAdapter` for standalone/headless tests, and `QtHostTimerAdapter` for Qt-bearing DCCs. Stats expose queue size, active
memi-designllms.txtmemi-design/memi/llms.txt
until external checks execute. Codex owns connector calls, editing and the project's actual tests. Figma/Paper selected context enters a bounded host-supplied envelope. Checked-in mappings are a fallback
swarm-ai-researchllms.txtswarm-ai-research/swarm/docs/llms-full.txt
Toxicity Circuit Breaker**: Freezes agents exceeding cumulative toxicity threshold. NO DETECTABLE EFFECT in any tested scenario (Cohen's d = -0.02, p = 0.88). Fires after damage is done — lagging indicator
zuke-buildllms.txtzuke-build/zuke/llms-full.txt
import { Build, target, run } from "@zuke/core"; import { $ } from "@zuke/core/shell"; class MyBuild extends Build { test = target() .description("Run the test suite") .executes(async () => { await $`deno test -A`; }); } await run(MyBuild
zuke-buildllms.txtzuke-build/zuke/llms.txt
from "@zuke/core"; import { DenoTasks } from "@zuke/deno"; class CI extends Build { lint = target().executes(() => DenoTasks.lint()); test = target().dependsOn(this.lint) .executes(() => DenoTasks.test((s) => s.allowAll())); } await run(CI); ``` ## CLI Run a build with
emlaillms.txtemlai/defi-native-skill/llms.txt
live-data discipline. MIT licensed. ## Core - [SKILL.md](SKILL.md): prime directives, working loop, orientation, competence test - [README.md](README.md): what this is and how it is organized - [api-routes.json](api-routes.json): question
openqa-cnllms.txtopenqa-cn/codexqa/llms.txt
code quality, trace change blast radius, detect logic defects, audit PRD requirements, generate manual test cases, construct test data, replay browser UI workflows, and diagnose root causes before merging
ssdeanxllms.txtssdeanx/AgentStack/llms.txt
tools, workflows, networks, MCP/A2A servers), frontend UI (Next.js app + shadcn/ui components), documentation, examples, and tests. Use the sections below to quickly find core docs, specs, examples, and configuration. ## Documentation - [Main
DeliciousBudingllms.txtDeliciousBuding/xiaohongshu-skill/site/llms-full.txt
verification. - Use headed mode for login and manual verification. - Keep pacing enabled. - Use test accounts for live tests. - Do not expose cookies, QR codes, profile links, screenshots, account names
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.
