agentmods.dev

mantle AGENTS.md

Project instructions for contributing to Mantle, an SDK for building agent-ready content-management systems, admin screens, and Cloudflare support.

In plain words
What is it for?
Use them when creating Mantle applications, modifying the SDK, reviewing changes, or preparing a release.
Why use it?
They help contributors make changes in the right repository areas, follow project decisions, and run suitable checks.

Instructions file for CodexOpenCode

4 6d ago A scan 232 tokens original Apache-2.0
View the source file aotter/mantle
Install

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.

agentmods
npx agentmods add instructions/aotter/mantle/agents-md
Clone the repo
git clone --depth 1 https://github.com/aotter/mantle

Made for: Codex, OpenCode.

Per session 232 This file is loaded in full into every session.
When invoked 232 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00232 $0.00232
Opus 5 $0.00116 $0.00116
Sonnet 5 $0.00046 $0.00046
Haiku 4.5 $0.00023 $0.00023

Measured 2d ago against content hash f51f63ac1ee7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mantle 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 2d 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.

AGENTS.md · 22 lines

What it actually says

Mantle contributor router

  • To create or continue a Mantle application, use the version-matched consumer skills under skills/ and materialize a project outside this SDK checkout.
  • To change or review this SDK, read CONTRIBUTING.md and the relevant accepted ADRs before editing.
  • To version, publish, tag, or fan out a release, additionally read the canonical release skill. Do not release unless the user explicitly asks.

Repository safety gates:

  • Branch from and open PRs against develop; preserve merge commits.
  • Keep Runtime adapter-neutral and the v0.1 manifest grammar closed.
  • Use the narrowest relevant check while editing; run pnpm check for broad changes.

CLAUDE.md is a compatibility pointer, not a second instruction authority. Generated applications receive their own version-matched instructions from aotter/mantle-starters.

Changes

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.

  1. 2d ago First seen · 22 lines · 232 tokens per session scan A f51f63ac1ee7

Subscribe to this mod's changes

mantle AGENTS.md is an instructions file published in the GitHub repository aotter/mantle (4 stars, last pushed 6d ago), licensed Apache-2.0. It adds 232 tokens to every session, about $0.0012 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.

DevOps and cloudFrontendGit and workflowagent-nativeai-agentsai-cmsai-website-buildermcpmodel-context-protocol
Related

Other instructions, from other repositories

ic-skills AGENTS.md

AGENTS.md instructions for Immersive-commons/ic-skills, covering agents.md — calling immersive commons directly, what immersive commons is, the mcp server (recommended transport), the 10 public tools (no token required) and authentication.

Immersive-commons/ic-skills · 2,165 tokens

ic-skills CLAUDE.md

Claude Code instructions for Immersive-commons/ic-skills, a project described as: Agent skills, SDKs, and integration docs for Immersive Commons (immersivecommons.com) - Floor 10, Frontier Tower SF. Includes .claude/, .cursor/, .windsurf/ agent configs.

Immersive-commons/ic-skills · 248 tokens

llm-context.py CLAUDE.md

Instructions for cyberchitta/llm-context.py, covering claude.md, working notes (gitignored) and draining the field notes.

cyberchitta/llm-context.py · 582 tokens

openrouter-mcp-multimodal AGENTS.md

Instructions for stabgan/openrouter-mcp-multimodal, covering agent instructions, before you ship, releasing (read this before publishing), short version and version files (must all match package.json).

stabgan/openrouter-mcp-multimodal · 783 tokens

seekstone CLAUDE.md

Instructions for shaqmughal/seekstone, covering claude.md, what this repo is, commands, the harness itself (run after npm install) and architecture.

shaqmughal/seekstone · 1,116 tokens

Plonk AGENTS.md

Instructions for ostapondo/Plonk, covering agent rules, layout, adding a module, build & verify and code style.

ostapondo/Plonk · 3,557 tokens