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/moru-ai/moru/agents-mdgit clone --depth 1 https://github.com/moru-ai/moruWrote 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/moru-ai/moru/agents-md)<a href="https://agentmods.dev/instructions/moru-ai/moru/agents-md"><img src="https://agentmods.dev/badge/instructions/moru-ai/moru/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 | $0.02147 | $0.02147 |
| Opus 5 | $0.01073 | $0.01073 |
| Sonnet 5 | $0.00429 | $0.00429 |
| Haiku 4.5 | $0.00215 | $0.00215 |
Grade A, and why
moru 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- moru CLAUDE.md — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 355 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Moru SDKs
This repository contains all Moru SDKs (JS, Python, CLI) managed as a pnpm workspace.
Version Management with Changesets
We use Changesets for automated version management and releases.
Core Principle: Flexible
You just need changesets before releasing. Commit freely during development, and add changesets when you're ready to release.
When Changesets Are Needed
The following changes require changesets when included in a release:
- ✅ Features: New functionality
- ✅ Bug Fixes: Bug corrections
- ✅ Breaking Changes: Changes that break API compatibility
- ✅ Performance: Performance improvements
- ✅ Dependencies: Dependency updates affecting users
When Changesets Are NOT Needed
Skip changesets for:
- ❌ Documentation-only changes (README, comments)
- ❌ Test-only changes
- ❌ CI/CD configuration changes
- ❌ Internal tooling changes
Workflow (Flexible Approach)
Approach 1: Add as you develop (Recommended - won't forget)
# 1. Make code changes
git add <files>
git commit -m "feat: add new feature X"
# 2. Add changeset
pnpm changeset
# - Which packages? (select with spacebar)
# - Version type? (patch/minor/major)
# - Summary? (description for CHANGELOG)
git add .changeset/
git commit -m "chore: add changeset"
git push
Approach 2: Add later (More flexible)
# 1. Commit multiple changes freely
git commit -m "feat: add feature A"
git commit -m "fix: bug B"
git commit -m "feat: add feature C"
git push
# 2. Add changeset before release
git log --oneline -10 # Review recent changes
pnpm changeset # "Add features A and C, fix bug B"
git add .changeset/
git commit -m "chore: add changeset for v0.3.3"
git push
Either approach works. Choose what fits your team/personal preference.
Choosing the Right Version Type
Follow Semantic Versioning:
patch (0.3.1 → 0.3.2)
- Bug fixes with no API changes
- Performance improvements
- Internal refactoring
- Documentation updates affecting functionality
- Dependency patches
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 · 355 lines · 2,147 tokens per session scan A e7e309c3e478
moru AGENTS.md is an instructions file published in the GitHub repository moru-ai/moru (78 stars, last pushed 6mo ago), licensed Apache-2.0. It adds 2,147 tokens to every session, about $0.0107 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
best-claude-hud AGENTS.md
Instructions for GaoSSR/best-claude-hud, covering project agent instructions and release work.
cetus AGENTS.md
Instructions for drewnekota/cetus, covering repository instructions and releases.
OpenMicro AGENTS.md
Instructions for stephenleo/OpenMicro, covering openmicro — project conventions and releases.
mcp AGENTS.md
Instructions for shipstatic/mcp: Read CLAUDE.md (same directory). It is the single source of truth for this repo's instructions; everything in it applies to every agent, not just Claude. Do not duplicate its content here.
Product-Marketing-Skills CLAUDE.md
Instructions for stefanoskarakasis/Product-Marketing-Skills, covering claude.md, versioning & releases, release procedure (manual, until ci enforcement exists) and after any repo change.
claude-code-hubs CLAUDE.md
Instructions for pigfoot/claude-code-hubs, covering plugin version management, for each plugin (e.g., nano-banana), checklist template, 1. update plugin.json and 2. update readme.md - add new section at top.