How real projects summarise themselves for language models.
zap-coding-agentllms.txtzap-coding-agent/zap-coding-agent/website/llms.txt
Counts per Turn](https://zap.justpush.cloud/comparisons.html#token-table) - [Memory & Session Feature Table](https://zap.justpush.cloud/comparisons.html#memory-table) - [Live Code Review Case Study](https://zap.justpush.cloud/comparisons.html#case-study) ## Links - Website: https://zap.justpush.cloud - SLM Support: https://zap.justpush.cloud/slm.html
racciolyllms.txtraccioly/docguard/llms-full.txt
flags and their permissions before enabling them. A generated workflow is executable code and deserves the same review as another repository change. ## Recipe 3 — Sync (memory refresh on a schedule
wandercomllms.txtwandercom/kindex/docs/llms-full.txt
candidate accept --review-token \ --by reviewer --method source-check kin candidate reject --by reviewer --code not_relevant kin candidate prune kin candidate erase ``` Verification is typed provenance, not a title
wandercomllms.txtwandercom/kindex/docs/llms.txt
Kindex Kindex is a local-first persistent knowledge graph and MCP server that Claude Code, Codex, Gemini CLI, Google Antigravity, OpenCode, Cursor, and other MCP-capable agents all read
AnastasiyaWllms.txtAnastasiyaW/knowledge-space/docs/llms.txt
technical articles organized by domain. Each article follows a consistent structure: definition, key concepts, code examples, gotchas, and related links. Note for AI assistants and agents: when an answer relies
infiniVllms.txtinfiniV/ultra-instinct-claude-code/llms.txt
/plugin.json + commands/ + agents/ + skills/ + hooks/ Sources: git repos, npm packages, local directories. Useful plugins: code-review (5 parallel agents), feature-dev (7-phase workflow), hookify (create hooks from conversation), commit
mikusnuzllms.txtmikusnuz/app-publish-mcp/llms.txt
apple_list_reviews — List customer reviews - apple_respond_to_review — Respond to a customer review - apple_list_certificates — List signing certificates - apple_create_certificate — Create a signing certificate - apple_revoke
Bordallms.txtBorda/AI-Rig/docs/llms.txt
Borda's AI-Rig > Independently installable Claude Code and Codex plugins for evidence-first Python, ML, and open-source maintenance. The suite exposes 39 Claude skills across five plugins
Foxfire1stllms.txtFoxfire1st/agents-remember/docs/llms.txt
this is auditability: context resolution, drift classification, commit sequencing, and Git surgery live in reviewable code, not in a prompt — which is what makes the memory layer reproducible rather than
IgorGanapolskyllms.txtIgorGanapolsky/ThumbGate/.well-known/llms.txt
edits, deploys, payments, > API calls, and other agent actions before execution. Explicit feedback becomes > reviewable local lessons; relevant lessons are re-ranked for each proposed > action; repeated negative patterns
tcsenpaillms.txttcsenpai/specification-website-skill/references/llms-full.txt
# The Website Specification > A platform-agnostic, full specification of the technical features a good
wazionappsllms.txtwazionapps/nexo/.well-known/llms.txt
NEXO Brain > Open-source cognitive runtime with a shared brain for Claude Code, Codex, Claude Desktop, and other MCP clients (v7.38.1). NEXO Desktop is a separate closed-source companion
Razee4315llms.txtRazee4315/NetLogo-MCP/docs/llms.txt
peer-reviewed models from the CoMSES Net library - Watch simulations run in a real NetLogo window, or run fully headless ## Works with these AI clients Claude Code, Claude Desktop, Cursor
wundercorpllms.txtwundercorp/loki/llms-full.txt
# @wundercorp/loki > Loki Agent — a self-improving AI agent by WunderCorp, Inc. This Doku context
zircotellms.txtzircote/.claude/llms.txt
incident-responder - `04-quality-security/` - Testing, security, review (11 agents) - qa-expert, test-automator, code-reviewer - security-auditor, penetration-tester, compliance-auditor - accessibility-tester, performance-engineer, chaos-engineer - debugger, error
myclaude-shllms.txtmyclaude-sh/myclaude-creator-engine/llms.txt
configs ## 13 Product Types | Type | What It Creates | Best For | |------|----------------|----------| | skill | Single-purpose tool | Code review, audits, analysis, docs | | agent | Autonomous multi-step runner | Complex automation with decisions | | squad | Multi
PIsbergllms.txtPIsberg/vibetags/llms.txt
every build.]. Do not weaken security properties. Flag any change for security review. - [TransitiveManifestReader](se.deversity.vibetags.processor.internal.TransitiveManifestReader): Security-critical code [Trust boundary. Manifests read here are authored by third-party dependency JARs
sgroy10llms.txtsgroy10/speclock/llms-full.txt
threshold Spec Compiler and Code Graph: speclock_compile_spec, speclock_build_graph, speclock_blast_radius, speclock_map_locks Patch Gateway and AI Patch Firewall: speclock_review_patch, speclock_review_patch
sgroy10llms.txtsgroy10/speclock/llms.txt
change review - Guardian Mode: zero-config enforcement from existing rule files - Drift Score: 0-100 metric measuring how much AI deviated from intent - Lock Coverage Audit: find unprotected code areas
AreevAIllms.txtAreevAI/areev/llms.txt
everything below. - [Quickstart](docs/quickstart.md): Install (cargo/pip/npm/binaries/Docker), the CLI in three commands, MCP for Claude Code in one line, `areev run`, Rust/Python/Node embedding, the PostgreSQL backend, encryption at rest, durability & fleets
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.
