lat.md is a markdown-based knowledge graph for recording a codebase’s design decisions, domain context, constraints, and test specifications in interconnected files. Coding agents use it to find and preserve project knowledge across sessions, while humans can review semantic changes through the graph; the catalogue entries support that workflow.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add vercel-labs/lat.md --skill skillgit clone --depth 1 https://github.com/vercel-labs/lat.mdWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/vercel-labs/lat.md/skill)<a href="https://agentmods.dev/skills/vercel-labs/lat.md/skill"><img src="https://agentmods.dev/badge/skills/vercel-labs/lat.md/skill/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/vercel-labs/lat.md/skill"><img src="https://agentmods.dev/badge/skills/vercel-labs/lat.md/skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00042 | $0.01765 |
| Opus 5.5 | $0.00017 | $0.00706 |
| Sonnet 5.5 | $0.00008 | $0.00353 |
| Haiku 4.5 | $0.00004 | $0.00177 |
Grade A, and why
lat-md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 16d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 211 lines — stays where its author put it; the contents beside it link to each section on GitHub.
lat.md Authoring Guide
This skill covers the syntax, structure rules, and conventions for writing lat.md/ files. Load it whenever you need to create or edit sections in the lat.md/ directory.
Project-specific lat documentation belongs in lat.md/. Do not modify this generated skill or a generated AGENTS.md to record project guidance: both are owned by lat tooling and may be replaced by a later lat init.
What belongs in lat.md
lat.md/ files describe what the project does and why — domain concepts, key design decisions, business logic, and test specifications. They do NOT duplicate source code. Think of each section as an anchor that source code references back to.
Treat lat.md/ as a focused snapshot of the current implemented state. Plans may be drafted in lat.md/ alongside implementation, with the intent that by commit time they describe what was implemented. Otherwise, keep proposals, hypothetical designs, and future work outside lat.md/ unless the user explicitly requests them there. A planning-only task does not require a knowledge-graph update. Do not use it as a journal or changelog, and do not grow it just to record insignificant implementation details.
Good candidates for sections:
- Architecture decisions and their rationale
- Domain concepts and business rules
- API contracts and protocols
- Test specifications (what is tested and why)
- Non-obvious constraints or invariants
Bad candidates:
- Step-by-step code walkthroughs (the code itself is the walkthrough)
- Auto-generated API docs (use tools for that)
- Journal/changelog entries for each change
- Proposals, planned features, hypothetical designs, or promises of future behavior, unless explicitly requested by the user or drafted alongside implementation to describe implemented behavior by commit time
- Temporary notes or TODOs
- Insignificant implementation details that do not change the current-state model
Section structure
Every section must have a leading paragraph — at least one sentence immediately after the heading, before any child headings or other block content.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 16d ago Changed · +10 lines 75e94a4ddb6d
- 1mo ago Changed · +1 lines 996b38dfa19e
- 1mo ago Changed c20cd3fff6aa
- 1mo ago Changed · +2 lines 0b45108a7fc4
- 1mo ago Changed · +12 lines d978d5cd2ef3
- 1mo ago First seen · 186 lines · 42 tokens per session scan A 3c4411c80318
lat-md is a skill published in the GitHub repository vercel-labs/lat.md (2,040 stars, last pushed 8d ago), licensed MIT. It adds 42 tokens to every session and 1,765 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
component-fixtures
Use when creating or updating component fixtures for screenshot testing or their shared infrastructure, or when designing UI components to be fixture-friendly. Covers fixture file structure, theming, service setup, CSS scoping, async rendering, validation, and common pitfalls.