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 agentmods add instructions/software-a-g/meet-ai/agents-mdgit clone --depth 1 https://github.com/SoftWare-A-G/meet-aiWrote 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/instructions/software-a-g/meet-ai/agents-md)<a href="https://agentmods.dev/instructions/software-a-g/meet-ai/agents-md"><img src="https://agentmods.dev/badge/instructions/software-a-g/meet-ai/agents-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.01404 | $0.01404 |
| Opus 5 | $0.00702 | $0.00702 |
| Sonnet 5 | $0.00281 | $0.00281 |
| Haiku 4.5 | $0.00140 | $0.00140 |
Grade A, and why
meet-ai AGENTS.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 4d 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Instruction for agents to work with meet-ai monorepo
Commands
bun run test # Run tests across all packages
bun run lint # Run oxlint across all files
bun run lint-changed # Run oxlint for changed files
bun run lint-changed:fix # Fix changed files by oxlint if possible
bun run lint-staged # Run oxlint for stages files
bun run lint-staged:fix # Fix staged files by oxlint if possible
bun run typecheck # Run TypeScript checks across all packages
Skill mappings - when working in these areas, load the linked skill file into context.
skills:
TanStack Start — framework & server
- task: "TanStack Start project setup, Vite plugin config, entry points, or root route document shell" load: "node_modules/.bun/@[email protected]/node_modules/@tanstack/start-client-core/skills/start-core/SKILL.md"
- task: "React bindings for TanStack Start, createStart, StartClient, StartServer, or useServerFn hook" load: "packages/worker/node_modules/@tanstack/react-start/skills/react-start/SKILL.md"
- task: "Server functions, createServerFn, or server-side data fetching" load: "node_modules/.bun/@[email protected]/node_modules/@tanstack/start-client-core/skills/start-core/server-functions/SKILL.md"
- task: "Server-side API routes using createFileRoute server property or createHandlers" load: "node_modules/.bun/@[email protected]/node_modules/@tanstack/start-client-core/skills/start-core/server-routes/SKILL.md"
- task: "Middleware for server functions or requests, createMiddleware, context passing" load: "node_modules/.bun/@[email protected]/node_modules/@tanstack/start-client-core/skills/start-core/middleware/SKILL.md"
- task: "Environment boundaries, createServerOnlyFn, createClientOnlyFn, ClientOnly, useHydrated, or isomorphic patterns" load: "node_modules/.bun/@[email protected]/node_modules/@tanstack/start-client-core/skills/start-core/execution-model/SKILL.md"
- task: "SSR, deployment to Cloudflare Workers, static prerendering, or SPA mode" load: "node_modules/.bun/@[email protected]/node_modules/@tanstack/start-client-core/skills/start-core/deployment/SKILL.md"
- task: "Server-side runtime, createStartHandler, request/response utilities, setCookie, useSession" load: "node_modules/.bun/@[email protected]/node_modules/@tanstack/start-server-core/skills/start-server-core/SKILL.md"
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.
- 4d ago First seen · 75 lines · 1,404 tokens per session scan A 13cc56dc7b38
meet-ai AGENTS.md is an instructions file published in the GitHub repository SoftWare-A-G/meet-ai (22 stars, last pushed 3mo ago), licensed MIT. It adds 1,404 tokens to every session, about $0.0070 per session on Opus 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 instructions, from other repositories
relay AGENTS.md
AGENTS.md instructions for AgentWorkforce/relay, covering git workflow rules, never push directly to main, correct workflow, ... do work .. and stop here - let user merge.
nutrition-mcp CLAUDE.md
Claude Code instructions for akutishevsky/nutrition-mcp, covering claude.md, project overview, deploying, publishing to the registry and commands.
Ornn CLAUDE.md
Instructions for ChronoAIProject/Ornn, covering claude.md — chrono-ornn, product positioning, tech stack, architecture and code standards.
cldcde CLAUDE.md
Instructions for aegntic/cldcde, covering claude.md, commands, development, database and architecture.
agenttool AGENTS.md
AGENTS.md instructions for cambridgetcg/agenttool, covering agents.md, in one paragraph, setup, common commands and xenia–helly exact common ground atlas.
zangia-mcp-ai CLAUDE.md
Instructions for enkhbold470/zangia-mcp-ai, covering claude.md — zangia ai & mcp server (typescript), quick commands, mcp stdio (claude code / codex / cursor / any mcp host), local clone and landing page + api (proxy: vite :3000 → hono :4000 /api).