Argent is a toolkit that lets an AI assistant control and inspect iOS, Android, TV, Electron, and Chromium applications through simulators, emulators, physical devices, or desktop connections. It is for developers who want an agent to interact with interfaces, reproduce issues, test features, debug applications, or run profiling tasks. The catalogue add-ons expose Argent's device-control and development workflows to coding agents.
Borrowing it
Nothing to install: this file belongs to software-mansion/argent. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/software-mansion/argent/main/CLAUDE.mdgit clone --depth 1 https://github.com/software-mansion/argentWrote 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/software-mansion/argent/claude-md)<a href="https://agentmods.dev/instructions/software-mansion/argent/claude-md"><img src="https://agentmods.dev/badge/instructions/software-mansion/argent/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/software-mansion/argent/claude-md"><img src="https://agentmods.dev/badge/instructions/software-mansion/argent/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00233 | $0.00233 |
| Opus 5.5 | $0.00093 | $0.00093 |
| Sonnet 5.5 | $0.00047 | $0.00047 |
| Haiku 4.5 | $0.00023 | $0.00023 |
Grade A, and why
argent CLAUDE.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 17d 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.
What it actually says
argent
Documentation
The docs site lives in packages/docs/ and is published to docs.swmansion.com/argent.
See packages/docs/CLAUDE.md for writing style, front matter and checks.
The site documents two products. Argent, the toolkit in this repository, lives at the
root of packages/docs/docs/. Argent Cloud lives in packages/docs/docs/cloud/. The paths
below refer to the toolkit.
Update the docs in the same pull request as the change:
- MCP tools, CLI, config keys, e2e test files -> the matching page in
packages/docs/docs/reference/, plusdocs/features/if the user facing capability changed. - Install, platforms, editor setup, telemetry ->
packages/docs/docs/fundamentals/. - A new capability -> a
features/page and areference/entry.
If no docs update is needed, say so in the pull request description.
After editing docs, run npx docusaurus build in packages/docs/ and npm run format from the
repo root.
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.
- 17d ago Changed · +3 tokens per session e4ee25e739ca
- 1mo ago Changed · +4 lines · +46 tokens per session dcb991a350b8
- 2mo ago First seen · 20 lines · 184 tokens per session scan A 1ed92eeeef8a
argent CLAUDE.md is an instructions file published in the GitHub repository software-mansion/argent (3,164 stars, last pushed yesterday), licensed Apache-2.0. It adds 233 tokens to every session, about $0.0009 per session on Opus 5.5. 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.
argent CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| argent CLAUDE.mdsoftware-mansion/argent | Instructions file | 3.2k | yesterday | Apache-2.0 | A | 233 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |