agentglass / landing
SirAllap/agentglass/landing/llms.txt
machine holds the terminals (real tmux panes), the agents — Claude Code, Codex, Gemini CLI, OpenCode — their pull requests and reviews, the diffs they write, git and Docker, a browser they
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.
SirAllap/agentglass/landing/llms.txt
machine holds the terminals (real tmux panes), the agents — Claude Code, Codex, Gemini CLI, OpenCode — their pull requests and reviews, the diffs they write, git and Docker, a browser they
zenodo/zenodo-rdm/static/llms.txt
change, so take the current values from the response headers rather than hard-coding them. - Clients identified as crawlers get a much stricter limit, which is shared by every client
raysonmeng/agent-bridge/site/llms.txt
largely built by Claude Code and Codex collaborating through it — the very tool they were building together. Every PR written by one agent was reviewed by the other, with
zapier/gtm-cheat-codes/llms.txt
agent skills Zapier GTM teams use to turn scattered context into reviewable work products. This repository helps coding agents understand and use GTM workflows with Zapier MCP and Zapier
rixinhahaha/snip/site/llms.txt
user's screenshot library - `snip transcribe ` — extract text from an image via OCR All review commands block until the user finishes and return JSON: `{ status, edited, path, text }`. ## Resources - [README
vishalsachdev/canvas-mcp/docs/llms.txt
code execution API ## Source Code - [GitHub Repository](https://github.com/vishalsachdev/canvas-mcp): Full source code, issues, and contributions - [PyPI Package](https://pypi.org/project/canvas-mcp/): Python package installation via pip - [MCP Registry](https://registry.modelcontextprotocol.io
fjrevoredo/mini-diarium/website/llms-full.txt
subject includes only the app version. Nothing is sent from the app itself; you review and send the message yourself. As an alternative to your password, you can register
vstorm-co/agenticos/llms.txt
Configuration can only ever reach what code registered, which is what makes a no-code Builder safe to hand to somebody who is not an engineer. Companies end up with
rrrrrredy/industry-research-framework/docs/llms.txt
pasted instructions. Native Skill installation is optional for reading methods. In Codex, Claude Code and OpenCode, the agent reuses existing local usage configuration and configures it with the bundled Python
dzianisv/opencode-mobile/docs-site/llms-full.txt
Android phone to your own opencode server and run AI coding sessions from anywhere: stream replies token by token, review file diffs, and approve tool calls before the agent executes
dzianisv/opencode-mobile/docs-site/llms.txt
Android phone to your own opencode server and run AI coding sessions from anywhere: stream replies token by token, review file diffs, and approve tool calls before the agent executes
jayanthmb14/forthepeople/public/llms.txt
Hindi (beta, `/hi`) and Kannada (beta, `/kn`). Hindi and Kannada are machine drafts under review. - **Cost:** free for everyone, no ads, no user accounts. Supported by voluntary contributions from citizens
Pangu-Immortal/KeepLiveService/llms-full.txt
propagation are represented in the strategy table with version checks and explicit skip codes. - **Safety boundary**: high-risk BAL, shell/root, and system UI abuse paths are not shipped as exploit
jfarcand/mirroir-mcp/llms.txt
accept # re-record every baseline; refuses to run in CI ``` Three verdicts, three exit codes: **0 = PASS**, **1 = FAIL**, **65 = DRIFT** — every structural assertion held and a drift metric moved
Keesan12/martin-loop/llms-full.txt
does not claim to replace Git, GitHub, CI/CD, dedicated security scanners, observability platforms, human code review, or all testing infrastructure. It can connect work that uses those systems into
Keesan12/martin-loop/llms.txt
needs to work across multiple coding agents or hosts - non-engineers need a clearer path from product intent to software work that can be reviewed and trusted Technical controls such
Undertone0809/rudder/docs/llms.txt
external connections are limited, and what differs by platform. - [Code Signing Policy](https://docs.rudderhq.dev/reference/code-signing-policy): How Rudder builds, reviews, approves, and signs Windows Desktop release artifacts. - [Privacy Policy](https://docs.rudderhq.dev
ohad6k/emulo/site/llms.txt
privacy. - [Carry preferences between agents](https://emulo.vercel.app/agent-profile#switch-agents): reuse a reviewed profile from Claude Code in a Codex project's AGENTS.md; conversation history and hidden state are not transferred. - [Verify
Priyanshu-byte-coder/devtrack/public/llms.txt
GitHub achievements. Only shown for users who made their profile public. - [Year in Code](https://devtrack.live/wrapped): a yearly recap of a developer's GitHub activity ## How rankings work
KimYx0207/Meta_Kim/llms.txt
recommendation - route work to bounded agents, skills, scripts, MCP providers, or runtime tools - review and verify results with artifacts - distinguish structural checks, routing, native invocation and actual task outcomes - write
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.