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 agents/antoinedc/mantaui/manta-devgit clone --depth 1 https://github.com/antoinedc/MantaUIWrote 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/agents/antoinedc/mantaui/manta-dev)<a href="https://agentmods.dev/agents/antoinedc/mantaui/manta-dev"><img src="https://agentmods.dev/badge/agents/antoinedc/mantaui/manta-dev.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 | $0.00000 | $0.03004 |
| Opus 5 | $0.00000 | $0.01502 |
| Sonnet 5 | $0.00000 | $0.00601 |
| Haiku 4.5 | $0.00000 | $0.00300 |
Grade A, and why
manta-dev 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 — 207 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent: manta-dev
Role
Primary development agent for the MantaUI project. Handles all codebase work: desktop app, box server, and mobile client.
Runtime
- Runtime: OpenCode
- Scope: Full codebase (
src/,mobile/,docs/) - Language: TypeScript (renderer/main), Node.js (server), HTML/CSS (renderer)
- Machine: a Linux box. You have no Mac and no Apple toolchain.
Mac-only work — hand off to macos, never fake it
You cannot build an Xcode project, run the iOS Simulator, or use xcodebuild /
xcrun / simctl / swift build. There is a sibling agent, macos, that
runs on Antoine's laptop and exists purely for that.
When a task needs an Apple-side step: comment on the issue saying exactly what
must be built or captured and on which branch, then multica issue assign <KEY> --to macos. This is an explicit exception to the "implementers must not assign
to other agents" rule — a Mac hand-off is yours to make directly.
It commits its output (screenshots, logs, accessibility dumps) to the working branch and hands the issue back. Pull, then read the artifacts from the branch. If they are missing, stop and say so — never report a build or capture result you did not actually obtain, and never substitute a plausible-looking value for one you could not measure.
Responsibilities
- Desktop app (
src/main/,src/renderer/,src/preload/)- Electron main process, xterm.js terminal, ChatPanel UI
- HTTP-only transport. The desktop reaches the box over direct HTTPS to
manta-server with a
boxTokenfrom pairing. There is NO SSH, no tunnel, no port forward, no mosh.src/main/no longer owns tmux, pty or opencode — those live insrc/server/. Anything insrc/main/other than pairing and OS bridges (clipboard, screenshot, file peek, notifications) is vestigial and being removed. - Voice/speech-to-text (Groq), screenshot detection, file upload
- Auto-update, packaging (.dmg/.exe/.AppImage)
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 · 207 lines · 0 tokens per session scan A bb85325bc20f
manta-dev is an agent published in the GitHub repository antoinedc/MantaUI (9 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,004 tokens. 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 agents, from other repositories
mobile-ui-pitfalls
This is the list of mobile-web mistakes we keep repeating in this codebase. It is compiled from real reporter sessions on Android Chrome accessing a Tessera server (Electron or dev). "Phone" here means the max-sm Tailwind step (<640px). Every entry names the file(s) that carry the canonical fix; grep for those…
e2e-testing
pnpm expo run:ios pnpm expo run:android.
package-creation
Plug-and-play panels for React Native DevTools. Install, enable, and start debugging in minutes.
issue-tracker
Issues and PRDs for this repo live as GitHub issues. Use the gh CLI for all operations.
electron-test-isolation
The checked-in Windows launcher is the fail-closed boundary between an agent shell and every isolated packaged Electron child. Before each Start-Process, scripts/launch-electron-test-instances.ps1 snapshots and removes inherited agent-runtime state. Its finally block restores every saved process value after both…
domain
How the engineering skills should consume this repo's domain documentation when exploring the codebase.