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.
zereightllms.txtzereight/gitlab-mcp/docs/llms.txt
without MCP](getting-started/cli-without-mcp.md): Skill + CLI - [Claude Code](clients/claude-code.md) - [Cursor](clients/cursor.md) - [VS Code](clients/vscode.md) - [Codex](clients/codex.md) - [JSON clients](clients/json-clients.md) - [OAuth2](auth/oauth-setup.md) - [Environment variables](configuration/environment-variables.md) - [Tools](tools/index.md): generated reference - [Skill
zereightReads credentialsllms.txtzereight/gitlab-mcp/llms-full.txt
files per call 3. `create_merge_request_thread` or draft notes for review comments `project_id` accepts a numeric ID or a URL-encoded path. Example: merge request
zereightllms.txtzereight/gitlab-mcp/llms.txt
zereight.github.io/gitlab-mcp/getting-started/cli-without-mcp/): Skill + CLI - [Claude Code](https://zereight.github.io/gitlab-mcp/clients/claude-code/) - [Cursor](https://zereight.github.io/gitlab-mcp/clients/cursor/) - [VS Code](https://zereight.github.io/gitlab-mcp/clients/vscode/) - [Codex](https://zereight.github.io/gitlab-mcp/clients/codex/) - [JSON clients](https://zereight.github.io/gitlab-mcp/clients/json-clients/) - [OAuth2](https://zereight.github.io
pyrevitlabsllms.txtpyrevitlabs/pyRevit/docs/llms-full.txt
# https://docs.pyrevitlabs.io/ llms-full.txt ## pyRevit Development Tools [Skip to content](https://docs.pyrevitlabs.io/#pyrevit-can-help-you) pyRevitRapid Application
No other project uses it yet
ranutsllms.txtranuts/document/public/llms.txt
Rewrite, summarize and translate currently operate on Word selections. Generated text is shown for review and only replaces the selection after confirmation. Changed targets invalidate proposals. Stop or turn
No other project uses it yet
MicrosoftPipes a download into a shellllms.txtmicrosoft/WhatTheHack/068-AzureOpenAIApps/Student/Resources/data/mcp-info/llms-full.txt
# Example Clients Source: https://modelcontextprotocol.io/clients A list of applications that support MCP integrations
1 project uses a version of this
bklitllms.txtbklit/bklit-ui/wiki/llms-full.txt
with an AI agent Paste this prompt into Claude Code, Cursor, Codex, or another coding agent, from the root of your project. It finds your installed charts, re-adds them
OpenAdaptAIllms.txtOpenAdaptAI/OpenAdapt/llms-full.txt
weeks") # the agent does it; a DRAFT is saved # a person reviews, runs the canary, and admits the draft jit.run(note="Recheck knee in ten days") # the program runs
OpenAdaptAIllms.txtOpenAdaptAI/OpenAdapt/llms.txt
named agents answer. Released. 8. **Repairs itself, with a person approving.** Governed repair (propose, review, campaign, canary, rollback), agent-demonstrated fixes for a halted run, and fleet drift patches shared
kenn-iollms.txtkenn-io/roborev/docs/llms.txt
roborev > roborev is local, continuous code review for the agentic loop: an > open-source review daemon for teams that ship with coding agents. A git > hook reviews every commit
fynnflueggePipes a download into a shellllms.txtfynnfluegge/agtx/llms-full.txt
coding agents in parallel. agtx manages coding agent sessions through a spec-driven workflow with phases: backlog, planning, implementation (running), review, and done. Each task gets its own git worktree
No other project uses it yet
fynnflueggePipes a download into a shellllms.txtfynnfluegge/agtx/llms.txt
orchestrates multiple AI coding agents in parallel. agtx manages coding agent sessions through a spec-driven workflow: backlog, planning, implementation, review, done. Each task gets its own git worktree
No other project uses it yet
siddsacharPipes a download into a shellllms.txtsiddsachar/Thoth/docs/llms-full.txt
take, such as reading files, searching documents, using a browser, running commands in a code folder, or sending through a channel. - **Approvals** ask you to approve or deny sensitive actions
siddsacharllms.txtsiddsachar/Thoth/docs/llms.txt
conversation's Design panel. - [Code Folders](/docs/developer/) Route: /docs/developer/. Work on a folder or repository from a conversation: bind or clone it, review changes, run checks
patrickchughllms.txtpatrickchugh/terravision/docs/llms-full.txt
staging and prod from one codebase with `--varfile`; why it matters (security review of another team's code against its design or an approved pattern, onboarding without account access, seeing
Steady3 mentions in 2 weeks
No other project uses it yet
patrickchughllms.txtpatrickchugh/terravision/docs/llms.txt
staging and prod from one codebase with `--varfile`; why it matters (security review of another team's code against its design or an approved pattern, onboarding without account access, seeing
Steady3 mentions in 2 weeks
No other project uses it yet
TraceMachinaDeletes or force-pushesllms.txtTraceMachina/nativelink/llms-full.txt
your own hardware, and cannot leave; and when agents write and commit code faster than people can review it, the build is the last checkpoint that has to stay honest
TraceMachinallms.txtTraceMachina/nativelink/llms.txt
second check for whether your build is one that benefits. - [AI coding agents](https://docs.nativelink.com/use-cases/ai-coding-agents): An agent's edit-build-test loop runs far more often than a human
Jarvis322Deletes or force-pushesllms.txtJarvis322/macos-sysdata/docs/llms-full.txt
downloads; the AI coding tools (Claude Code, Codex, Grok, Copilot, Kilo, Gemini); Claude's local VM bundles and Chrome's on-device model | Review / Manual | | Logs & diagnostics | unified log store
razzantllms.txtrazzant/ouroboros/docs/llms.txt
Claudexor](https://claudexor.ai/): The local execution layer Ouroboros uses for delegated coding and hosted-agent review. - [Claudexor source](https://github.com/razzant/claudexor): Routing, execution, and durable evidence for connected coding
Steady3 mentions in 2 weeks
No other project uses it yet
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.
