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/mission69b/t2000/claude-mdgit clone --depth 1 https://github.com/mission69b/t2000Wrote 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/mission69b/t2000/claude-md)<a href="https://agentmods.dev/instructions/mission69b/t2000/claude-md"><img src="https://agentmods.dev/badge/instructions/mission69b/t2000/claude-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 | $0.08224 | $0.08224 |
| Opus 5 | $0.04112 | $0.04112 |
| Sonnet 5 | $0.01645 | $0.01645 |
| Haiku 4.5 | $0.00822 | $0.00822 |
Grade A, and why
t2000 CLAUDE.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 5d 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 — 464 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file is loaded every turn. It is the highest-leverage configuration for any AI assistant working on this codebase.
Architecture — The Big Picture
What this monorepo is (product first)
t2000 the product = the agent marketplace (hire · work · earn in USDC) at
t2000.ai + Passport Connect at mcp.t2000.ai. Stage: traction / live mainnet.
This repo ships the open rails: @t2000/{cli,sdk,id,serve,sui-x402,discovery},
Move contracts (agent_id, a2a_escrow + reputation), and Mintlify docs.
The Next.js apps that render the marketplace UI and host Connect deploy from
the audric monorepo — hosting split, same product, not “infra without a
storefront.” Audric the brand is also AI you can put to work at audric.ai
(credit for chat/inference; USDC on Passport for the marketplace).
Do not describe this repo to outsiders as “CLI/SDK only” or “stage unclear.”
Public pitch copy: root README.md · PRODUCT.md · brandkit/VOICE.md.
Three brands / repos
t2000 (this repo) → Marketplace rails: CLI, SDK, contracts, docs (+ PRODUCT.md)
audric (separate) → Hosts t2000.ai + mcp.t2000.ai apps; also Audric AI (audric.ai)
suimpp (separate) → Protocol mirrors (historical / @suimpp/*)
This repo structure
t2000/
├── apps/docs ← Mintlify developer docs (docs.t2000.ai)
├── packages/cli ← @t2000/cli (npm)
├── packages/sdk ← @t2000/sdk (npm)
├── packages/id ← @t2000/id (npm) ← Agent ID — agent_id::registry client
├── packages/serve ← @t2000/serve (npm) ← Merchant-side x402 router
├── packages/x402 ← @t2000/sui-x402 (npm) ← x402 dialect for Sui
├── packages/discovery ← @t2000/discovery (npm) ← x402 probe + OpenAPI extract
├── contracts/ ← Move (agent_id, a2a_escrow, …)
├── t2000-skills/ ← Agent skill definitions
└── PRODUCT.md ← Product map SSOT
Planned package names (
store,models) may appear in internal roadmaps — they are not shipped and must not be described as half-built product.
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.
- 5d ago First seen · 464 lines · 8,224 tokens per session scan A 090e46b403fb
t2000 CLAUDE.md is an instructions file published in the GitHub repository mission69b/t2000 (23 stars, last pushed 2d ago), licensed MIT. It adds 8,224 tokens to every session, about $0.0411 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
mesh-connector copilot-instructions.md
Copilot instructions for RightOnPar-LLC/mesh-connector, covering editor-agent door — mesh-connector, 1 · this repo's identity, 2 · the two-system estate, 3 · the ring-fence and 4 · the four hard floors (never automatic — a human signs).
mesh-connector AGENTS.md
AGENTS.md instructions for RightOnPar-LLC/mesh-connector, covering editor-agent door — mesh-connector, 1 · this repo's identity, 2 · the two-system estate, 3 · the ring-fence and 4 · the four hard floors (never automatic — a human signs).
a2a CLAUDE.md
Claude Code instructions for mirni/a2a, covering development workflow: test-driven development (tdd), 1. red phase (failing test), 2. green phase (pass test), 3. refactor phase (clean up) and git/github workflow: feature branch model.
a2a AGENTS.md
AGENTS.md instructions for mirni/a2a, covering agents.md, for coding agents building other agents, install, quick start and capabilities.
authsome AGENTS.md
AGENTS.md instructions for agentrhq/authsome, covering agents.md, commands, install in editable mode (required before running anything), run all tests and run a single test file.
x402-stellar-kit AGENTS.md
AGENTS.md instructions for CodeStrux/x402-stellar-kit, covering working with x402-stellar-kit, the one invariant, production seams, bootstrapping accounts across a custody boundary and add x402 to an existing api.