Borrowing it
Nothing to install: this file belongs to orchestratemcp/OrchestrateKIT-MCP. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/orchestratemcp/OrchestrateKIT-MCP/master/AGENTS.mdgit clone --depth 1 https://github.com/orchestratemcp/OrchestrateKIT-MCPWrote 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/orchestratemcp/orchestratekit-mcp/agents-md)<a href="https://agentmods.dev/instructions/orchestratemcp/orchestratekit-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/orchestratemcp/orchestratekit-mcp/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 5.1 | $0.00708 | $0.00708 |
| Opus 5 | $0.00354 | $0.00354 |
| Sonnet 5 | $0.00142 | $0.00142 |
| Haiku 4.5 | $0.00071 | $0.00071 |
Grade A, and why
OrchestrateKIT-MCP 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 6d 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OrchestrateKit MCP Agent Rules
Read PROJECT_STATE.md and .orchestrate/state.json before planning work.
Product boundary
This repository is the deterministic design and export layer for agent systems. Keep tool output reproducible, preserve user wording where the plan promises to preserve it, and do not add external writes or hidden execution to planning tools. DASH manifest exports use manifest v2; telemetry uses the v1 envelope.
Sources of truth
- Git is implementation truth.
- Linear is intent and ownership truth.
- ADRs are decision truth.
- Tests and real runtime proofs are evidence truth.
.orchestrate/state.jsonis an index, never an independent source of truth.
Never collapse planned, merged, and proven. Merged means an ancestor commit contains the implementation. Proven means a reproducible proof exercised the promised path.
Session protocol
At the start: confirm repository and branch, inspect git status, run pnpm state:check, and read the active Linear issue. At the end: run the relevant tests, update the issue with commit/proof evidence, add an ADR for cross-repository decisions, update the state packet, and run pnpm state:check again. Preserve unrelated dirty files.
Use pnpm verify before claiming a change is proven.
New-session handoff contract
When Henrik asks for a new session prompt, do not return a loose summary. Return one or more copy/paste-ready prompts and specify for each:
- client (
CodexorClaude Code), exact model selector, and reasoning level; - repository, branch/worktree, Linear issue, and read/write ownership;
- objective, current evidence, known blocker, allowed changes, and non-goals;
- required start checks, verification commands, lifecycle exit state, and the evidence that must be written back to Linear/state files;
- coordination rules for any parallel session.
Model routing while usage is available:
- Use Codex
gpt-5.6-solwith high/xhigh reasoning for cross-repository implementation, architecture migrations, difficult debugging, security boundaries, and installed/runtime proof work. - Use Codex
gpt-5.6-terrawith medium/high reasoning for a bounded issue, mechanical cleanup, focused tests, or documentation where the scope is known. - Use Claude Code
--model opuswith extended thinking for an independent architecture/UX audit, long-context reconciliation, or a second opinion on a risky plan. The officialopusalias intentionally resolves to Claude Code's current Opus model; include the concrete model ID too when the client exposes it. - Use Claude Code
--model sonnetfor bounded implementation and review when Opus usage is limited.
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.
- 6d ago First seen · 59 lines · 708 tokens per session scan A 13712796ffc1
OrchestrateKIT-MCP AGENTS.md is an instructions file published in the GitHub repository orchestratemcp/OrchestrateKIT-MCP (1 stars, last pushed 11d ago), licensed MIT. It adds 708 tokens to every session, about $0.0035 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
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
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 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).
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.
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.