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/antaresqaq/voxmesh/agents-mdgit clone --depth 1 https://github.com/AntaresQAQ/VoxMeshWrote 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/antaresqaq/voxmesh/agents-md)<a href="https://agentmods.dev/instructions/antaresqaq/voxmesh/agents-md"><img src="https://agentmods.dev/badge/instructions/antaresqaq/voxmesh/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 | $0.00587 | $0.00587 |
| Opus 5 | $0.00293 | $0.00293 |
| Sonnet 5 | $0.00117 | $0.00117 |
| Haiku 4.5 | $0.00059 | $0.00059 |
Grade A, and why
VoxMesh 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.
How it starts
The opening of the file, as written. The whole thing — 38 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Instructions for Coding Agents
These instructions apply to Codex and any other coding agent that reads AGENTS.md.
Required Reading
Before planning or changing this repository, read:
docs/DEVELOPMENT_RULES.md is mandatory and is the canonical source for engineering workflow, testing, security, review, Git, and release requirements.
Mandatory Workflow
- Communicate with the user in English or Chinese according to their preference.
- Write all repository content, documentation, comments, test names, logs, and user-facing text in English.
- Discuss requirements, behavior, scope, risks, acceptance criteria, and testing before implementing a functional change.
- Do not write behavior-changing code until the user explicitly confirms the proposed functional change.
- Never edit directly on
main; create a dedicated<type>/<short-description>branch from the latestmain. - Deliver every change to
mainthrough a reviewed pull request with passing required CI. - Use English Conventional Commit-style commit messages and PR titles such as
feat: ...,fix: ..., ordocs: .... - Split unrelated concerns and different change types into focused, reviewable commits instead of one catch-all commit.
- Keep changes strictly within the confirmed scope and preserve existing user changes.
- Do not commit, amend, rebase, tag, push, force-push, create a pull request, merge, or release without explicit confirmation for that specific operation.
- Every functional change must include complete unit, integration where applicable, and end-to-end tests.
- Add thorough English developer documentation for features, packages, APIs, configuration, architecture boundaries, failure behavior, and extension points.
- Add concise JSDoc and reasoning comments for public contracts, security-sensitive behavior, state machines, invariants, workarounds, and non-obvious decisions; never add comments that merely restate code.
- Keep Web Console components small and single-purpose; decompose pages into focused feature and shared components.
- Add focused behavioral unit tests for every new or changed Web Console component.
- Meet WCAG 2.2 AA; verify keyboard navigation, visible focus, semantic HTML, form announcements, responsive zoom, and required contrast in English/Chinese and Light/Dark themes.
- Run jsx-a11y linting and representative Playwright axe scans; never suppress accessibility failures without explicit approval and tracking.
- Run all applicable formatting, linting, type-checking, testing, and production-build checks before reporting work as complete.
- Never expose or commit secrets, credentials, tokens, personal data, or machine-specific configuration.
- Preserve the platform-independent architecture and dependency direction defined in
docs/MVP.md.
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 · 38 lines · 587 tokens per session scan A 928ac7492538
VoxMesh AGENTS.md is an instructions file published in the GitHub repository AntaresQAQ/VoxMesh (1 stars, last pushed 2d ago), licensed MIT. It adds 587 tokens to every session, about $0.0029 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.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.