moonbridge AGENTS.md

moonbridge AGENTS.md is an instructions file for Codex, OpenCode from briandconnelly/moonbridge. It costs 3,031 tokens per session, scanned A, original, MIT.

Repository instructions for working on Moonbridge, a Claude Code and Codex plugin that calls the Kimi Code command-line tool through an MCP server. It documents the project’s tooling, conventions, and completion checks.

In plain words
What is it for?
Running the project with uv, checking formatting and types, running tests, and validating GitHub Actions changes.
Why use it?
It gives agents and people one place to learn how to change and verify this repository correctly.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: reads .claude/ paths; mentions Claude Code; mentions Codex.

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/briandconnelly/moonbridge/agents-md
Clone the repo
git clone --depth 1 https://github.com/briandconnelly/moonbridge

Made for: Codex, OpenCode.

Wrote 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.

agentmods badge for moonbridge AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/briandconnelly/moonbridge/agents-md.svg)](https://agentmods.dev/instructions/briandconnelly/moonbridge/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/briandconnelly/moonbridge/agents-md"><img src="https://agentmods.dev/badge/instructions/briandconnelly/moonbridge/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 3,031 This file is loaded in full into every session.
When invoked 3,031 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 5.1 $0.03031 $0.03031
Opus 5 $0.01515 $0.01515
Sonnet 5 $0.00606 $0.00606
Haiku 4.5 $0.00303 $0.00303

Measured 5d ago against content hash cde539b9eccd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

moonbridge 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 5d 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 · 198 lines

How it starts

The opening of the file, as written. The whole thing — 198 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent working conventions

Conventions for any agent (or human) working in this repository.

What this is

A Claude Code and Codex plugin that calls the Kimi Code CLI via an MCP server. The Python package is moonbridge under src/. Generic, CLI-agnostic machinery lives in the shared pontonier library (pontonier.core), which this package consumes as a dependency — the extraction this section used to plan happened.

  • Rule: this bridge pins its externally visible core knobs explicitly (config.WORKTREE_CONFIG: worktree prefix, baseline-commit identity, and the handshake-dir diff exclusion) rather than inheriting pontonier defaults; changing them is a behavior change, not a refactor.

Tooling

  • Use uv for everything: uv sync, uv run pytest, uv run <cmd>. Never pip/poetry.

  • The gate. This is the repo's single definition of it; every other doc links here rather than restating it. A change is not done until it passes:

    uv run ruff check . && uv run ruff format --check . && uv run ty check && uv run pytest
    

    If you touched .github/workflows/, also run uv run python scripts/check_github_actions_pinning.py — CI runs it ahead of the four above, and the prek pre-commit hook runs it too once installed (see below). CI (.github/workflows/test.yml) is the authoritative gate and runs all of this on every supported Python version.

  • Tests use pytest; the coverage floor and integration-test markers are defined in Testing below.

  • Local Git hooks are configured in prek.toml and run via prek (a dev dependency). One-time setup: uv run prek install --prepare-hooks. Hooks mirror the CI gate — pre-commit runs file hygiene + ruff/ty/Actions-pinning/uv lock --check; pre-push runs pytest; commit-msg validates Conventional Commits via scripts/check_commit_message.py. prek is a local convenience; CI (test.yml) remains the authoritative gate and does not run the builtin file-hygiene hooks.

  • When changing the allowed commit types or scopes, update scripts/check_commit_message.py and CONTRIBUTING.md → Conventions in the same change — they mirror each other.

Read the full file on GitHub · 198 lines

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. 5d ago First seen · 198 lines · 3,031 tokens per session scan A cde539b9eccd

Subscribe to this mod's changes

moonbridge AGENTS.md is an instructions file published in the GitHub repository briandconnelly/moonbridge (0 stars, last pushed 3d ago), licensed MIT. It adds 3,031 tokens to every session, about $0.0152 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.

Related

Other instructions, from other repositories