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/moira-mcp/moira/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.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 | $0.03583 | $0.03583 |
| Opus 5 | $0.01792 | $0.01792 |
| Sonnet 5 | $0.00717 | $0.00717 |
| Haiku 4.5 | $0.00358 | $0.00358 |
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 — 332 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Agent guide for the Moira repository. Read this before making changes. Claude Code
reads CLAUDE.md, which imports this file with @AGENTS.md.
Before beginning any development work, read CONTRIBUTING.md completely. It is the
source of truth for coordinating work through GitHub issues, claiming or releasing
an issue, pull-request linkage, and the contributor/maintainer handoff. Do not start
implementation from an issue until that contract says the issue is available and
the claim has been confirmed.
What Moira Is
Moira is a node-graph Agent Workflow Engine. It guides AI agents (Claude, GPT, custom agents) through multi-step processes via the MCP protocol, giving each step a clear directive (what to do) and a completion condition (when it's done), validated before the agent may proceed. The primary users are AI agents; the Web UI is a supplementary tool for managing workflows.
See docs/VISION.md for the full product vision.
Repository Layout
npm-workspace monorepo:
packages/
├── workflow-engine/ # Core node-graph execution engine
├── mcp-server/ # MCP protocol HTTP server (the MCP tools)
├── web-backend/ # Express API for workflow management
├── web-frontend/ # React UI for workflow visualization
├── shared/ # Database (Drizzle), Better Auth, logging, config
└── docs/ # Astro 5 + Starlight documentation site (EN + RU)
workflows/ # Bundled workflow catalog (workflows/production/public/)
config/ # Dockerfile, nginx, supervisord, prompts
scripts/ # DB init, migrations, secret bootstrap, health checks
tests/ # unit / workflow / integration / api / e2e / mcp-tools
docs/ # Internal developer documentation
For where each topic is documented, see the Documentation Map in README.md.
Build & Run (fresh clone)
The app runs as a single Docker container built from a baked image — there is no
live-source mode. Code changes (engine, MCP server, backend, frontend, bundled
workflow catalog) reach a running instance only by rebuilding the image and
recreating the container; docker restart keeps the old build. Check which commit an
image was built from with docker exec <container> cat /app/BUILD_INFO. Ports are
env-driven (MOIRA_PORT, default 8080).
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 · 332 lines · 3,583 tokens per session scan A 9def5c95eaf2
moira AGENTS.md is an instructions file published in the GitHub repository moira-mcp/moira (114 stars, last pushed 4d ago), licensed Apache-2.0. It adds 3,583 tokens to every session, about $0.0179 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.
Other instructions, from other repositories
mcpelevator CLAUDE.md
Instructions for pacnpal/mcpelevator, covering commands, architecture, conventions, agent skills and issue tracker.
mcpelevator AGENTS.md
Instructions for pacnpal/mcpelevator, covering commands, architecture and conventions.
ODS CLAUDE.md
Claude Code instructions for Osmantic/ODS, covering claude.md, project overview, repository structure, build & development commands and linting and validation.
tianji AGENTS.md
AGENTS.md instructions for msgbyte/tianji, covering contributor guide, development tips, translation files, audit logs and testing instructions.
meme-search CLAUDE.md
Instructions for neonwatty/meme-search, covering claude.md, 📁 file organization guidelines, 🤖 task agent usage guidelines, when to use task agents and documentation lookup pattern.
sandboxd AGENTS.md
AGENTS.md instructions for tastyeffectco/sandboxd, covering agents.md — operating sandboxd, what this is, prerequisites, install and core api.