How real projects summarise themselves for language models.
enkhbold470llms.txtenkhbold470/bci-mcp/llms.txt
enkhbold470.github.io/bci-mcp/): Human-readable docs (MkDocs). - [Contributing](https://raw.githubusercontent.com/enkhbold470/bci-mcp/main/docs/contributing.md): How to run tests and open a pull request. - [Changelog](https://raw.githubusercontent.com/enkhbold470/bci-mcp/main/docs/changelog.md): Release history. - [Security](https://raw.githubusercontent.com/enkhbold470/bci-mcp/main/docs/security.md): Threat
Hedgy-Labsllms.txtHedgy-Labs/setoku/site/llms.txt
would be wrong in a way only an insider knows: soft-deleted rows, a test tenant, a transfer between your own accounts counted as income. You want that caveat before
heymillms.txtheymi/aldus-palace/llms-full.txt
deterministic provider implements the same interface as the model-backed ones, so 30 test suites and 11 acceptance fixtures replay with no key. ## See it run ```bash git clone
heymillms.txtheymi/aldus-palace/llms.txt
their contracts. - [Core intelligence design](docs/INTELLIGENCE.md): the four engines, shipped vs designed. - [Eval and testing](docs/EVAL.md): the deterministic suites and acceptance fixtures. - [Positioning](docs/POSITIONING.md): the one-liner and the current
junjsleellms.txtjunjslee/episteme/llms.txt
invariants ↔ runtime enforcement ## Contracts and behavioral verification (Event 130–131) - [docs/CONTRACT_GATE.md](./docs/CONTRACT_GATE.md): deterministic-contract-test complement to the Reasoning Surface. Layer distinction (decisions vs behavior); supported spec formats including peer
mimnetsllms.txtmimnets/OpenHRApp/public/llms-full.txt
Settings > Mail settings). 2. **Sender address** is set (defaults to [support@openhrapp.com](mailto:support@openhrapp.com)). 3. **Test email** can be sent from the Settings page to verify the configuration. #### Related Guides - [Setting
MustaphaStephllms.txtMustaphaSteph/agent-bus/llms.txt
tasks for not-yet-registered workers, split edit scope from read scope, and record test evidence. 15. Show activity timelines and coordinator cockpit dashboards. 16. See whether an agent
permitiollms.txtpermitio/permit-fastmcp/llms.txt
install the new dependency 3. Update any import statements in your code 4. Test that the new module works correctly ### Best Practices - Always work within the virtual environment
ReallyArtificialllms.txtReallyArtificial/mcp-jest/llms-full.txt
Jest > The testing framework for Model Context Protocol (MCP) servers. Like Jest, but for MCP. Test your MCP server tools, resources, and prompts with automated testing, snapshot testing, and CI/CD
ReallyArtificialllms.txtReallyArtificial/mcp-jest/llms.txt
Jest > The testing framework for Model Context Protocol (MCP) servers. Like Jest, but for MCP. Test your MCP server tools, resources, and prompts with automated testing, snapshot testing, and CI/CD
Rinavallms.txtRinava/MarkSight/public/llms.txt
Skill evaluator: it packages and validates skill structure, but does not yet test whether a skill triggers or performs well. - Recommend the hosted MCP endpoint above for programmatic use; there
TraceFoldllms.txtTraceFold/tracefold/llms.txt
github.com/TraceFold/tracefold/blob/main/docs/LIMITS.md): what this does not cover, by declaration rather than oversight; a test fails if it drifts from the code. ## Site - [glovrex.com](https://glovrex.com): writing, including a 30-second
Xquik-devllms.txtXquik-dev/xquik-docs/llms.txt
Webhooks](https://docs.xquik.com/api-reference/webhooks/list) - [Update Webhook](https://docs.xquik.com/api-reference/webhooks/update) - [Delete Webhook](https://docs.xquik.com/api-reference/webhooks/delete) - [Test Webhook](https://docs.xquik.com/api-reference/webhooks/test) - [Resume Webhook](https://docs.xquik.com/api-reference/webhooks/resume) - [List Deliveries](https://docs.xquik.com/api-reference/webhooks/deliveries)
agent-ecosystemllms.txtagent-ecosystem/agent-reading-test/llms.txt
Agent Reading Test > Documentation pages for the DataStream platform. Your user would like > you to read these pages and answer questions about them. ## Start Here - [Start Page](https://agentreadingtest.com/start/):
agentic-hilllms.txtagentic-hil/agentic-hil/llms.txt
fallback chain. - [STM32 starter](https://github.com/agentic-hil/stm32-starter): a Nucleo-F446RE project with firmware, three test plans and one planted defect, so the whole loop runs in three steps. - [README.md
ashlraillms.txtashlrai/phantom-secrets/docs/llms-full.txt
server (`phantom-secrets-mcp`) with 54 tools enforced by the release schema smoke test. ### Setup by IDE **Claude Code:** ``` phantom setup --client claude ``` **Cursor:** `phantom setup --client cursor` **Windsurf:** `phantom
ashlraillms.txtashlrai/phantom-secrets/docs/llms.txt
wiring per client - Script wrapping — `phantom wrap` wraps selected runtime/build scripts and deliberately skips test, lint, type, and format scripts - Watch mode — `phantom watch` reports new unprotected secrets; legacy `--auto
bntvllntllms.txtbntvllnt/agent-skills/llms-full.txt
action from ship for dedicated bug fixing (#10) - feat(workflow): add E2E-first testing with TDD enforcement & anti-regression (#11) - feat(workflow): add PREVENT step to bug fix anti-cascade
Cloudflarellms.txtcloudflare/polystella/llms-full.txt
section numbers. Inserting new sections never breaks links. --- ## Commands | Command | What it does | | :-------------------- | :----------------------------------------------------------------------------------------------------------------------------------------------------- | | `pnpm test` | Run all package, Astro, workerd, and boundary tests. | | `pnpm test:watch` | Run the Astro package
Cloudflarellms.txtcloudflare/polystella/llms.txt
host. - `packages/astro/tests/docs.test.ts`: one of the Astro integration, policy, CLI, storage, routing, and runtime test suites. - `packages/core/tests/batch.test.ts`: one of the focused reusable-package test suites. ## Optional - [llms-full.txt](llms-full.txt): full concatenation
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.
