machine-front-door

Rules for maintaining the machine-readable instructions and service manifest for t2000. A machine-readable playbook is a page written for software agents, while a manifest lists the available skills.

In plain words
What is it for?
Updating t2000’s agent instructions, well-known discovery routes, connection details, or skills manifest when a machine-facing contract changes.
Why use it?
They keep API paths, authentication, discovery links, signing rules, and the published skills list consistent across the product.

Cursor rule for Cursor

Install

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.

agentmods
npx agentmods add rules/mission69b/t2000/machine-front-door
Clone the repo
git clone --depth 1 https://github.com/mission69b/t2000

Made for: Cursor.

Per session 78 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 333 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00078 $0.00333
Opus 5 $0.00039 $0.00167
Sonnet 5 $0.00016 $0.00067
Haiku 4.5 $0.00008 $0.00033

Measured 2d ago against content hash 6ae74d296e53, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

machine-front-door 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 2d 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.

.cursor/rules/machine-front-door.mdc · 23 lines

What it actually says

Machine Front Door → .claude/skills/t2000-machine-front-door/SKILL.md

The invariant: t2000.ai/llms.txt (served from audric/apps/console/app/llms.txt/route.ts) is the single machine playbook — never create a second SSOT. Update it only when a machine contract changes (public api.t2000.ai/v1/* shapes, CLI marketplace/wallet verbs, Connect auth model or connector URL, discovery URLs, who can sign, earn-first/fee/open-reject locks) — never for UI polish. Connect always signs as Passport, never a local key. The skills manifest enumerates from t2000-skills/feed.json, gated by validate.ts in CI.

Read the full rule before editing llms.txt, well-known routes, or agent-discovery copy: .claude/skills/t2000-machine-front-door/SKILL.md — gate list, facts that must stay true, verify curls.

(Pointer only — do not re-inline the content here; same pattern as env-validation-gate.mdc so Cursor and Claude Code cannot drift.)

Changes

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.

  1. 2d ago First seen · 23 lines · 78 tokens per session scan A 6ae74d296e53

Subscribe to this mod's changes

machine-front-door is a cursor rule published in the GitHub repository mission69b/t2000 (23 stars, last pushed 2d ago), licensed MIT. It adds 78 tokens to every session and 333 once invoked, about $0.0004 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.