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/statecli/mcp-server/agents-mdgit clone --depth 1 https://github.com/statecli/mcp-serverWhat 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 | $0.03054 | $0.03054 |
| Opus 5 | $0.01527 | $0.01527 |
| Sonnet 5 | $0.00611 | $0.00611 |
| Haiku 4.5 | $0.00305 | $0.00305 |
Grade A, and why
mcp-server 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 yesterday.
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 — 250 lines — stays where its author put it; the contents beside it link to each section on GitHub.
StateCLI - AI Agent Instructions
This file helps AI coding agents (like Cascade, Cursor, Claude) understand and use StateCLI.
Core Rules
STATECLI AGENT RULES — READ BEFORE ANY ACTION
You are operating in a stateful, reversible environment.
Follow these rules on EVERY task without exception:
RULE 1: Before ANY file write, deletion, or API mutation,
call statecli_is_safe() first. If not safe, checkpoint first.
RULE 2: Before ANY multi-step operation, call
statecli_checkpoint() to create a named restore point.
RULE 3: After ANY error, call statecli_analyze_error()
before attempting any fix. Never guess. Always analyze.
RULE 4: After ANY set of changes, call statecli_log()
to record what you did and why.
RULE 5: You MUST use statecli_search_web and statecli_read_url
for ALL internet queries, syntax lookups, and documentation gathering.
Skipping these steps makes your actions irreversible.
Complete Tool Listing (31 Tools)
statecli_track
[CORE] Records any agent action with full metadata so it can be replayed, audited, or reversed later. Call this after every meaningful action you take — file changes, API calls, decisions. If you don't track it, you cannot undo it. 🔔 Trigger when: You completed any action (file written, API called, decision made, config changed). Think of this as your action journal. 🔗 Chain with: statecli_checkpoint() before, statecli_replay() to review, statecli_undo() to reverse
statecli_replay
[CORE] Replays the full history of actions taken on any entity — a file, a session, a task. Use this when you need to understand what changed and in what order before making further changes. Essential before debugging. 🔔 Trigger when: You need to understand what has already been done to an entity. You're about to debug. A human asks 'what did you change?' 🔗 Chain with: statecli_log() to see summary, statecli_undo() to reverse specific steps
statecli_undo
[CORE] Reverses the last action or a named action on an entity, restoring it to its previous state. This is your safety net. Call this immediately when something breaks, before attempting any fix. 🔔 Trigger when: Something broke. A test failed after your change. A human says 'revert that'. You made a mistake and need to roll back. 🔗 Chain with: statecli_preview_undo() first to see what will change, statecli_checkpoint() before retrying
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.
- yesterday First seen · 250 lines · 3,054 tokens per session scan A 0a93a1c4f21c
mcp-server AGENTS.md is an instructions file published in the GitHub repository statecli/mcp-server (2 stars, last pushed 4mo ago), licensed MIT. It adds 3,054 tokens to every session, about $0.0153 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
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.
buildNext
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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
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).
spec-kit 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.
langchain 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.