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/tetracoralla/state-machine/agents-mdgit clone --depth 1 https://github.com/tetracoralla/state-machineWrote 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/tetracoralla/state-machine/agents-md)<a href="https://agentmods.dev/instructions/tetracoralla/state-machine/agents-md"><img src="https://agentmods.dev/badge/instructions/tetracoralla/state-machine/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 | $0.00463 | $0.00463 |
| Opus 5 | $0.00231 | $0.00231 |
| Sonnet 5 | $0.00093 | $0.00093 |
| Haiku 4.5 | $0.00046 | $0.00046 |
Grade A, and why
state-machine 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 — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Step Switch repository contract
Before any review, read docs/REVIEW_CONTRACT.md. A plain owner request to
review, audit, 审核, or 复核 invokes that contract end to end; treat it as the
minimum scope and report tools-dev workspace escalations without asking the
owner for another checklist.
Product boundary
This repository owns a deterministic finite-state transition kernel and two thin surfaces: a technical human editor/simulator and read-only Agent tools. It does not own production workflow orchestration, arbitrary expression evaluation, policy judgment, external side effects, or a complete statechart runtime.
The canonical product model is docs/PRODUCT_MODEL.md. Executable Zod schemas
in src/model/schemas.ts own the runtime, CLI, MCP, examples, UI, and published
schema contract.
Invariants
stepis a pure function of machine, snapshot, event, and explicit guard outcomes. The kernel never executes user code or external effects.- Effects are symbolic intents. Simulation returns them; a host decides whether a separately authorized executor may act on them.
- Guards are named symbols. The caller supplies their boolean outcomes; the kernel does not recreate the Decision Table or expression interpreter.
- Context assignment uses the tagged
literal,event, andcontextvalue sources only. Reject unknown fields and unsafe prototype-path segments. - One state/event pair owns at most one transition in v0.1. An absent transition is an ordinary deterministic rejection, not an inferred action.
- Final states cannot have outgoing transitions. Every target, event, and guard reference must exist.
- MCP tools accept inline data only and are read-only, idempotent, bounded, and closed-world. Do not add ambient filesystem access.
- Apply request-wide state, transition, event-sequence, depth, byte, and response limits cumulatively.
Validation lanes
Run npm run check for development regression. Separately exercise the built
CLI, MCP stdio transport, and browser editor/simulator before claiming those
runtime surfaces work. Business/experience acceptance remains the owner's
judgment after opening the current interface.
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 · 47 lines · 463 tokens per session scan A 00362d8f588d
state-machine AGENTS.md is an instructions file published in the GitHub repository tetracoralla/state-machine (0 stars, last pushed yesterday), licensed Apache-2.0. It adds 463 tokens to every session, about $0.0023 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 2026-08-31.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.