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/edgar-durand/codeagent-mobile-clients/claude-mdgit clone --depth 1 https://github.com/edgar-durand/codeagent-mobile-clientsWrote 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/edgar-durand/codeagent-mobile-clients/claude-md)<a href="https://agentmods.dev/instructions/edgar-durand/codeagent-mobile-clients/claude-md"><img src="https://agentmods.dev/badge/instructions/edgar-durand/codeagent-mobile-clients/claude-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 | $0.12310 | $0.12310 |
| Opus 5 | $0.06155 | $0.06155 |
| Sonnet 5 | $0.02462 | $0.02462 |
| Haiku 4.5 | $0.01231 | $0.01231 |
Grade B, and why
codeagent-mobile-clients CLAUDE.md scanned grade B with 2 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
### Headroom provisioning — resolve an installer by LEAST PRIVILEGE, never assume sudo `apps/cli/src/commands/host/os-packages.ts` **`ensurePythonInstaller`** (renamed from `ensurePip` in Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
3. Package manager + (root OR passwordless sudo) → install python3+pip+ca-certificates+curl. How it starts
The opening of the file, as written. The whole thing — 628 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Guidance for Claude Code (claude.ai/code) when working inside this repository.
Overview
This repo holds the client-side pieces of CodeAgent Mobile:
apps/cli—codeam-cli, the Node.js CLI that spawns Claude Code under a PTY and relays mobile prompts. Published to npm.apps/vsc-plugin— The VS Code / Cursor / Windsurf extension. Published to VS Code Marketplace and Open VSX.apps/jetbrains-plugin— The IntelliJ-family plugin (IntelliJ IDEA, WebStorm, PyCharm, Rider, GoLand, …). Published to JetBrains Marketplace (stable channel) by the tag-triggered release workflow.packages/shared—@codeam/shared, pure-TypeScript modules (chunk-protocol parser, Anthropic pricing tables) bundled into the CLI and the VS Code extension at build time.
The backend, mobile app, and web dashboard are maintained elsewhere and are not in scope here.
Cuestiona lo que se te pide cuando veas algo mejor
Si el usuario propone A y ves que B es mejor, DILO antes de construir A. No te calles una opción mejor por ser obediente: callársela es una decisión, y es la peor de las dos.
Cómo hacerlo sin frenar el trabajo:
- Di la alternativa y por qué, en dos frases. Lo que gana, lo que cuesta. Nada de encuestas de opciones ni de "podríamos considerar".
- Recomienda una. Si te preguntan qué harías, ya tienes la respuesta.
- Si es reversible y claramente mejor, hazlo y dilo — el usuario lo ve en el resultado y puede pedirte que vuelvas. Si es difícil de deshacer, cambia el alcance, o depende de algo que solo el usuario sabe, pregunta ANTES.
- Si te reafirma su idea, esa es la decisión. Constrúyela entera y sin reproches; ya dijiste lo tuyo.
Un ejemplo real de por qué existe esta regla (2026-08-27): se pidió mover la cabecera a un raíl lateral para que el simulador cupiera entero. Mover la cabecera ganaba ~48 px, pero el marco medía ~869 px de alto y en un portátil seguía sin caber: sin escalarlo al alto disponible, el objetivo no se alcanzaba igual. Decirlo con la aritmética delante ahorró una ronda entera.
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 · 628 lines · 12,310 tokens per session scan B ebc82983e2df
codeagent-mobile-clients CLAUDE.md is an instructions file published in the GitHub repository edgar-durand/codeagent-mobile-clients (9 stars, last pushed today), licensed MIT. It adds 12,310 tokens to every session, about $0.0616 per session on Opus 5. A static security scan graded it B with 2 findings (asks for root, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
mcp-unity AGENTS.md
Instructions for CoderGamester/mcp-unity, covering mcp unity — ai agent guide (mcp package), purpose (what this repo is), how it works (high-level data flow), key defaults & invariants and repo layout (where to change what).
rails-ai-context AGENTS.md
AGENTS.md instructions for crisnahine/rails-ai-context, covering rails-ai-context, agent skills, issue tracker, triage labels and domain docs.
plugin-files-mode
Rosetta Plugin Mode Bootstrap.
inspecto CLAUDE.md
Instructions for inspecto-dev/inspecto, covering inspecto — claude code development guide, project overview, monorepo structure, development phases (load each file as needed) and key architectural decisions.
skill.color-expert CLAUDE.md
Claude Code instructions for meodai/skill.color-expert, covering claude.md, project overview, architecture, no build/test/lint and editing guidelines.
imagine-mcp AGENTS.md
AGENTS.md instructions for n24q02m/imagine-mcp, covering imagine-mcp, architecture, tool signatures, model selection and transport modes.