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/ryder-mhumble/meldwork/agents-mdgit clone --depth 1 https://github.com/Ryder-MHumble/MeldworkWrote 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/ryder-mhumble/meldwork/agents-md)<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>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 | $0.00429 | $0.00429 |
| Opus 5 | $0.00215 | $0.00215 |
| Sonnet 5 | $0.00086 | $0.00086 |
| Haiku 4.5 | $0.00043 | $0.00043 |
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.
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 buildandnpm --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.
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.
- 5d ago First seen · 39 lines · 429 tokens per session scan A 07a06616d5f2
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.
Other instructions, from other repositories
solo AGENTS.md
AGENTS.md instructions for solo-agent/solo, covering project testing rules and project service lifecycle rules.
research-os AGENTS.md
Instructions for lxinfei5/research-os, covering researchos — constitution, §0 what this is, §1 directory discipline, §2 half-life (innovation 1) — memory design and §3 behavior pillars (innovations 2–5).
foundry-local python-cffi-pointer-types.instructions.md
Use when working on the Python SDK's native bindings (cffi), especially when defining new Item subclasses, working with flItemQueue, or extending Request/Session methods that pass native handles.
lime AGENTS.md
AGENTS.md instructions for limecloud/lime, covering lime 源码仓库指南, 事实源, 工程约束, 协议与质量 and 执行方式.
archilles CLAUDE.md
Claude Code instructions for kasssandr/archilles, covering claude.md, project overview, commands, installation and indexing.
AI-System-Design-Consultant CLAUDE.md
Claude Code instructions for deepanshu2711/AI-System-Design-Consultant, covering claude.md, what this is, running it, load-bearing typos — do not "fix" these paths and agent node pattern.