How real projects summarise themselves for language models.
griddynamicsllms.txtgriddynamics/rosetta/llms-full.txt
cause (why agents fail): autoregressive token gen over current context. Miss a concern once (security, a convention, an assumption 3 steps ago) → never returns to it; shallow "side-quest" reasoning
raysonmengllms.txtraysonmeng/agent-bridge/site/llms.txt
tenant system. - Not a generic orchestration framework for arbitrary agent backends. - Not a hardened security boundary between tools you do not trust. ## Three core benefits - Cross-review, not just cross
gameworkerkimllms.txtgameworkerkim/vibe-investing/llms.txt
North-Korea Kimsuky AI-click + Lazarus AnySign4PC](https://github.com/gameworkerkim/vibe-investing/blob/main/02.Investment%20Idea%20Column/NorthKorea/Lazarus_AnySign4PC.md): State-mandated security app became the attack path (zero-day, 72+ institutions); Kimsuky reused opencode lures. / 국가 강제 설치 보안SW
gameworkerkimllms.txtgameworkerkim/vibe-investing/TechDoc/llms.txt
20tier%20guide.md) | Comprehensive guide to Cloudflare's free tier: Workers, Pages, D1, R2, KV, security services. - [Cloudflare Free Tier Usage — VibeQuant Case (KR)](CloudFlare/Cloudflare_무료티어_사용법.md) | What Cloudflare
claude-did-thisllms.txtclaude-did-this/MCPControl/docs/llms-full.txt
Tool integration for executing commands and scripts * Local server connections for enhanced privacy and security > ? Note: The Claude.ai web application does not currently support MCP. MCP features are only available
SirAllapllms.txtSirAllap/agentglass/landing/llms.txt
raw.githubusercontent.com/SirAllap/agentglass/main/docs/CONFIG.md): every environment variable the code reads, the whole HTTP API, the architecture - [Security](https://raw.githubusercontent.com/SirAllap/agentglass/main/SECURITY.md): the trust model, what each surface can reach, retention, how to report
88linllms.txt88lin/computer-repair-skill/docs/llms.txt
confirmation. - L3 high-impact change — delete, kill, elevate, install, uninstall, batch move, startup or security settings; needs exact commands plus separate confirmation. - L4 system red line — boot volume, partition table
kydlikebtcllms.txtkydlikebtc/awesome-grokbot/llms.txt
Grok Bot account share one cloud computer, so a second bot is not a security boundary. ## Licence Catalog rows are CC0-1.0 or CC-BY-4.0 per row (the `license
oriveollms.txtoriveo/oriveo/llms.txt
what this edition is for, and the kinds of change it will not accept - [Security policy](https://github.com/oriveo/oriveo/blob/main/SECURITY.md): how to report a vulnerability privately, and what counts
ohad6kllms.txtohad6k/emulo/site/llms.txt
source and destination status. - [Published package](https://pypi.org/project/emulo/): CLI releases and Python requirement. - [Security policy](https://github.com/ohad6k/emulo/blob/main/SECURITY.md): redaction and local versus hosted processing. - [License](https://github.com/ohad6k/emulo/blob/main/LICENSE):
Scottcjnllms.txtScottcjn/rustchain-bounties/llms.txt
directories (30 RTC)](https://github.com/Scottcjn/rustchain-bounties/issues/3075): cross-ecosystem discovery. - [#2867 Red Team security audit (50-200 RTC per finding)](https://github.com/Scottcjn/rustchain-bounties/issues/2867): real reproducible CVSS findings only. - [#2864 RTC Reward
KimYx0207llms.txtKimYx0207/Meta_Kim/llms.txt
changes. Upgrade to `npm run meta:verify:all` for install, runtime, hook, dependency, package, security, or release-grade changes. ## Public Claims Boundary Safe claims: - Meta_Kim has default formal projections
loulanyuellms.txtloulanyue/awesome-claude-notes/llms.txt
target Provenance and support: - Upstream source: https://github.com/affaan-m/ECC - Distribution repository: https://github.com/loulanyue/awesome-claude-notes - Security reports: use the repository Security tab, not a public Issue
gosudallms.txtgosuda/portal-tunnel/llms.txt
operate a relay. - [API reference](https://raw.githubusercontent.com/gosuda/portal-tunnel/main/docs/src/routes/api-reference/+page.md): Relay HTTP endpoints and shared types. - [Security model](https://raw.githubusercontent.com/gosuda/portal-tunnel/main/docs/src/routes/security-model/+page.md): Encryption and trust boundaries. - [Public relay state](%s/api/state): Current public leases
aws-samplesllms.txtaws-samples/sample-well-architected-skills-and-steering/llms.txt
agents Well-Architected aware. When loaded, you should apply the six pillars (Operational Excellence, Security, Reliability, Performance Efficiency, Cost Optimization, Sustainability) to architecture discussions, code reviews, and design decisions. ## Installation
billy-enrizkyllms.txtbilly-enrizky/openbrowser-ai/stress-tests/llms-full.txt
openbrowser import BrowserProfile profile = BrowserProfile( headless=True, viewport_width=1280, viewport_height=720, disable_security=False, extra_chromium_args=["--disable-gpu"], record_video_dir="./recordings", proxy={ "server": "http://proxy.example.com:8080", "username
vinkius-labsllms.txtvinkius-labs/mcpfusion/docs/llms.txt
# MCP Fusion > fusion is the TypeScript framework for production MCP servers. MVA architecture, structured
Sentryllms.txtgetsentry/dotagents/docs/public/llms.txt
filename as the subagent name. ```md --- name: code-reviewer description: Review code for correctness, security, and missing tests. --- Review the current diff and return findings with file references. ``` | Field | Type
ffrolivallms.txtffroliva/gflow-cli/llms.txt
layout, review-before-sharing, HAR escalation), selector-drift diagnosis, structured log keys, WAF cadence. - [Security](https://github.com/ffroliva/gflow-cli/blob/main/docs/SECURITY.md): Threat model, where secrets live, automatic-vs-sensitive incident-artifact tiers
Scottcjnllms.txtScottcjn/beacon-skill/llms.txt
docs/SECURITY.md) — Nonce strategy, timestamp validation, replay protection - [CONTRIBUTING.md](CONTRIBUTING.md) — How to contribute - [SECURITY.md](SECURITY.md) — Security disclosure policy
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.
