Borrowing it
Nothing to install: this file belongs to moira-mcp/moira. 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/moira-mcp/moira/master/AGENTS.mdgit clone --depth 1 https://github.com/moira-mcp/moiraWrote 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/moira-mcp/moira/agents-md)<a href="https://agentmods.dev/instructions/moira-mcp/moira/agents-md"><img src="https://agentmods.dev/badge/instructions/moira-mcp/moira/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/moira-mcp/moira/agents-md"><img src="https://agentmods.dev/badge/instructions/moira-mcp/moira/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.01202 | $0.01202 |
| Opus 5.5 | $0.00481 | $0.00481 |
| Sonnet 5.5 | $0.00240 | $0.00240 |
| Haiku 4.5 | $0.00120 | $0.00120 |
Grade A, and why
moira 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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Working in Moira
Read CONTRIBUTING.md completely before implementation. It owns issue
availability, claims, branch and pull-request coordination, DCO and maintainer handoff.
CLAUDE.md imports this file; keep one agent contract.
Moira is a node-graph workflow engine exposed through the Model Context Protocol (MCP), with a browser interface for authoring and observing workflows. The engine validates answer structure and controls progression; agents and reviewers verify the underlying facts. Start with the documentation index, then read the relevant source and contract before changing behavior.
Architecture and reuse
Use the current architecture and project map. The engine owns authored types, graph semantics, validation and execution. Shared foundation primitives must not import application composition or engine runtime through a barrel. Persistence owns SQL transactions; application services compose canonical engine operations. Browser authored types use the type-only engine facade, while browser/API representations remain local.
Local and GitHub environments use the same workspace-service payload. Cloud routing, controller lifecycle, guest commands and original-operation receipts have distinct owners; preserve the workspace contracts. Copy returned references unchanged. A lost reply requires collecting the original operation, not inventing IDs, refreshing proof or replaying a mutation. Direct guest readiness is independent of remote enrollment. Runtime fixtures do not prove native VM isolation.
Prefer an existing primitive and composition to a parallel implementation. For browser work, follow Web UI architecture and UI patterns, including retained results, private admission, drafts, accessibility and both languages.
Build and verification
Node.js 24 and root npm entrypoints are the supported contributor path. Follow getting started for setup and the distinction between persistent self-host Compose and the disposable contributor Docker helper. The application image is baked: restarting an old container does not load source edits. Do not replace another user's running instance or assume a helper targets your MCP server.
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 Changed · -340 lines · -4,158 tokens per session 30f2d1142883
- 6d ago Changed · +20 lines · +355 tokens per session 141400617df8
- 12d ago Changed · +8 lines · +122 tokens per session 6c5feb6bdd7d
- 14d ago Changed · +8 lines · +122 tokens per session 125099580390
- 22d ago Changed · +16 lines · +179 tokens per session f0764a2feb55
- 1mo ago Changed · +7 tokens per session f4440627f8d2
- 1mo ago Changed · +1 lines · +12 tokens per session 4b0e5b3e6862
- 1mo ago Changed · +8 lines · +190 tokens per session 6c04ec868094
- 1mo ago Changed · +1 lines · +7 tokens per session 986f89cbba26
- 1mo ago First seen · 380 lines · 4,366 tokens per session scan A cc605e595dbe
moira AGENTS.md is an instructions file published in the GitHub repository moira-mcp/moira (128 stars, last pushed today), licensed Apache-2.0. It adds 1,202 tokens to every session, about $0.0048 per session on Opus 5.5. 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
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
vscode model-prompts.instructions.md
Model-specific prompt authoring and registry guidelines.