Meldwork AGENTS.md

Meldwork AGENTS.md is an instructions file for Codex, OpenCode from Ryder-MHumble/Meldwork. It costs 429 tokens per session, scanned A, original, Apache-2.0.

Development rules for Meldwork, a desktop application that keeps conversations and workspaces on the user's computer and runs AI agents locally.

In plain words
What is it for?
Use it when changing Meldwork's Electron desktop code, its user interface, agent execution, secure storage, or workspace and conversation behavior.
Why use it?
It sets boundaries that protect secrets, limit workspace changes, and avoid accidentally adding required cloud or server services. It also makes code changes easier to review by keeping them small and explicit.

Instructions file for CodexOpenCode

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/ryder-mhumble/meldwork/agents-md
Clone the repo
git clone --depth 1 https://github.com/Ryder-MHumble/Meldwork

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 Meldwork AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/ryder-mhumble/meldwork/agents-md.svg)](https://agentmods.dev/instructions/ryder-mhumble/meldwork/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/ryder-mhumble/meldwork/agents-md"><img src="https://agentmods.dev/badge/instructions/ryder-mhumble/meldwork/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 429 This file is loaded in full into every session.
When invoked 429 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 $0.00429 $0.00429
Opus 5 $0.00215 $0.00215
Sonnet 5 $0.00086 $0.00086
Haiku 4.5 $0.00043 $0.00043

Measured 5d ago against content hash 07a06616d5f2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Meldwork 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 · 39 lines

How it starts

The opening of the file, as written. The whole thing — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Meldwork Development Rules

Working Style

  • Read the relevant code path before editing and state assumptions when behavior is unclear.
  • Keep changes small and directly tied to the request. Do not refactor adjacent code without a concrete need.
  • Before editing, name the files you will change and why. Use patch-based edits for reviewable changes.
  • Do not place screenshots, logs, generated packages, or temporary files in the repository root.

Product Boundaries

  • Meldwork is a local-first desktop application. Do not introduce a required server, container, or cluster dependency unless the task explicitly calls for it.
  • Keep Agent execution in the Electron main process. Renderer access must go through narrow, validated preload APIs.
  • Never expose executable paths, tokens, provider credentials, or unrestricted shell execution to renderer code.
  • Store secrets only through operating-system-backed secure storage. Do not add plaintext fallbacks.
  • Keep workspace write access opt-in. Conversations and groups stay local; do not add remote participants, cloud channels, or remote conversation storage.

Frontend And Desktop

  • User-visible text must support both Chinese and English through the existing i18n system.
  • Changes to chat behavior must be checked in Electron desktop mode.
  • New overlays must support Escape/back dismissal and prevent background scroll where applicable.
  • Preserve the existing visual language and responsive behavior; avoid unrelated redesigns.

Verification

  • Frontend tests: npm --prefix frontend test
  • Frontend builds: npm --prefix frontend run build and npm --prefix frontend run build:desktop
  • Desktop tests: npm --prefix desktop test
  • Desktop package validation: npm --prefix desktop run pack
  • Add or update focused tests when changing behavior, security boundaries, output structures, or conditional logic.
  • Report commands run and any verification that could not be completed.

Git Hygiene

  • Preserve unrelated user changes and never use destructive Git commands without explicit approval.
  • Commit messages should explain what changed, why it changed, and which checks were run.
  • Do not add generated dependencies, build output, credentials, or release artifacts to version control.

Read the full file on GitHub · 39 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 · 39 lines · 429 tokens per session scan A 07a06616d5f2

Subscribe to this mod's changes

Meldwork AGENTS.md is an instructions file published in the GitHub repository Ryder-MHumble/Meldwork (127 stars, last pushed 7d ago), licensed Apache-2.0. It adds 429 tokens to every session, about $0.0021 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.