How real projects summarise themselves for language models.
abhinavg6llms.txtabhinavg6/yutha/docs/llms.txt
escalation, supervisor-required for refunds above a threshold. - [Code review crew with security boundaries](https://yutha.ai/examples/code-review/): reviewer + auto-fix agents with capability gates around security-tagged paths. - [AP & invoice
AetherCore-Devllms.txtAetherCore-Dev/ag402/llms.txt
request with x402 auto-payment (6-step visualization) | | `ag402 status` | Dashboard: balance, budget bars, security layers, recent txns | | `ag402 balance` | Quick balance + budget usage with progress bars | | `ag402 history` | Transaction
Arun-kcllms.txtArun-kc/schemabrain/docs/llms.txt
hints. - [Landscape](https://github.com/Arun-kc/schemabrain/blob/main/docs/landscape.md): Where SchemaBrain sits in the AI-database tooling ecosystem. ## Security & operations - [Security](https://github.com/Arun-kc/schemabrain/blob/main/docs/security.md): Procurement-friendly summary — security architecture, threat model, disclosure process. - [Threat
bradleybond512llms.txtbradleybond512/crystal-ball/public/llms-full.txt
Syria, Yemen, Myanmar, Venezuela, Brazil, UAE. Computed from baseline risk (40%), unrest events (20%), security activity (20%), and information velocity (20%) - **Trending Keyword Spike Detection**: 2-hour rolling window
CarakaDevllms.txtCarakaDev/caraka/llms.txt
threads, lifecycle, routing, housekeeping - [Telegram integration](https://github.com/CarakaDev/caraka/blob/main/docs/telegram-integration.md): Bot API 10.2 mapping - [Security](https://github.com/CarakaDev/caraka/blob/main/docs/security.md): threat model, mandatory controls, policy modes, and the pre-release checklist with
dgeniollms.txtdgenio/contextweaver/llms-full.txt
ordering, logical-ID uniqueness, and the canonical capability digest. It is **not**: - deployment approval; - security certification; - authentication or authorization; - a guarantee that a tool implementation is correct; - routing-quality evaluation
dgeniollms.txtdgenio/contextweaver/llms.txt
routing - [Daily Driver](docs/daily_driver.md): Operator workflow, client instructions, fit guidance, and debugging - [MCP Security Model](docs/security_model.md): Gateway data flow, trust boundaries, artifact exposure, and hardening - [MCP Gateway Security Guide](docs/security_mcp_gateway.md
hermes-labs-aillms.txthermes-labs-ai/hermeneutic/llms.txt
sensitive text; review before sharing. ## Project - Repository: https://github.com/hermes-labs-ai/hermeneutic - Documentation: README.md - Citation: CITATION.cff - Security: SECURITY.md - License: Apache-2.0 - Public display author: Rolando Bosch, Hermes Labs
JAYcodrllms.txtJAYcodr/claude-code-ultimate-guide-zh/llms-full.txt
most comprehensive community resource for Claude Code. It covers everything from installation to production security, with 186 ready-to-use templates for agents, hooks, commands, and skills. ## Who This Guide
JAYcodrllms.txtJAYcodr/claude-code-ultimate-guide-zh/llms.txt
Skills - User-invocable + model-invocable templates (/pr, /commit, /diagnose remain available) 7. Hooks - Security automation and formatting (production hooks for bash + PowerShell) 8. MCP Servers - External tool integration (databases, browsers
Karthick-Ramachandranllms.txtKarthick-Ramachandran/persist-os/llms.txt
Persist OS writes structured, reviewable memory (product intent, architecture decisions, module ownership, testing and security expectations, AI agent rules) into plain files that live next to the code and survive
kensaurusllms.txtkensaurus/cursor-kenji/llms.txt
modelSettings`, frontmatter `effort:`), the pack's routing table, what changed for Opus 5.5 ## MCP & security - [mcp/README.md](https://github.com/kensaurus/cursor-kenji/blob/main/mcp/README.md): MCP server setup, pinned package versions - [SECURITY.md](https://github.com/kensaurus/cursor-kenji/blob/main/SECURITY.md): Secrets
mcpwarellms.txtmcpware/IntentProbe/llms-full.txt
research preview: a local, single-pass, registration-time review signal, not a hard security boundary. ## What problem it solves MCP servers, AI agent tools, and skills describe themselves in normal
mcpwarellms.txtmcpware/IntentProbe/llms.txt
Claude Code PreToolUse. - Research preview, a local registration-time review signal, NOT a hard security boundary. ## Install ``` pip install intentprobe intentprobe scan-config auto --format summary ``` ## Links - Repository: https://github.com
melbinjpllms.txtmelbinjp/jules-prompts/llms.txt
state, software or physical, to production quality. It does its one job dependably and securely on every platform its people use, loses and leaks nothing, feels finished, carries nothing
mrdulasolutionsllms.txtmrdulasolutions/NakatomiCRM/llms.txt
Repository: https://github.com/mrdulasolutions/NakatomiCRM - Roadmap: /ROADMAP.md - Ethos: /ETHOS.md - MCP usage: /docs/MCP.md - Skill install: /docs/SKILLS.md - Security policy: /SECURITY.md
occasiolabsllms.txtoccasiolabs/occasio/web/llms.txt
policy proxy: deny-list patterns, path enforcement, secret redaction, transform rules. - Claude Code security: native in-process interception of Read, Glob, Grep, TodoWrite, TodoRead. - MCP security: lf namespace, mcp-primary
saifeldeen911llms.txtsaifeldeen911/actionfence/llms-full.txt
schemas` is passed. Treat the output as a review starting point, not a completed security review. When `--pin-schemas` is used, generated actions also include a `schema_snapshot` so later
saifeldeen911llms.txtsaifeldeen911/actionfence/llms.txt
return `ACTIONFENCE_RECEIPT_PERSISTENCE_FAILED` and prevent handler execution when storage is unavailable - Security: HMAC signing secrets must be ≥16 bytes; `payloadRedactor` strips sensitive fields before receipt storage; `maxPayloadBytes` (default
thevibeworksllms.txtthevibeworks/cctrace/llms.txt
auto-generated MITM CA ## Docs - [README](https://raw.githubusercontent.com/thevibeworks/cctrace/main/README.md): overview, quick start, comparison, security model - [Install & options](https://raw.githubusercontent.com/thevibeworks/cctrace/main/docs/install.md): install methods, runtime, prerequisites, full options table, `--` pass-through - [Capture
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.
