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/alvarolorentedev/opencode-mobile/agents-mdgit clone --depth 1 https://github.com/alvarolorentedev/opencode-mobileWhat 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 | $0.01310 | $0.01310 |
| Opus 5 | $0.00655 | $0.00655 |
| Sonnet 5 | $0.00262 | $0.00262 |
| Haiku 4.5 | $0.00131 | $0.00131 |
Grade A, and why
opencode-mobile 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 2d 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 — 244 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Follow the current implementation docs in docs/. Do not invent a new architecture.
Read first:
docs/architecture.mddocs/state-and-data.mddocs/component-inventory.mddocs/testing-and-validation.md
Architecture Rule
This app is provider-centric.
providers/opencode-provider.tsxowns domain state and orchestration.app/owns routing and thin screen wiring.components/owns presentation and local UI state.providers/services/owns provider-facing API aggregation.lib/owns protocol, formatting, storage keys, notifications, and voice helpers.tests/fake-opencode/andtests/e2e/define the behavioral contract.
Do not move domain behavior into screens or presentational components.
Placement Rules
app/
Put:
- route entrypoints
- tab/layout wiring
- thin screen controllers
- calls into
useOpencode()
Do not put:
- fetch logic
- session orchestration
- capability reconciliation
- protocol shaping
components/
Put:
- rendering
- local UI state
- chat/settings UI composition
- surface-specific helpers
Do not put:
- API calls
- persistence
- shared domain state
- cross-session caches
providers/
Put:
- connection flow
- workspace/session state
- refresh logic
- permission/question handling
- capability reconciliation
- conversation mode state machine
- SSE and polling fallback
- persistence hydration and write-back
Shared behavior across tabs belongs here.
providers/services/
Put:
- session fetch helpers
- capability/config/provider discovery helpers
Services aggregate requests. They do not own app state.
lib/opencode/
Put:
- client construction
- endpoint wrappers
- protocol types
- message formatting
- transcript transformation
Raw server-shape handling belongs here, not in UI code.
lib/
Put:
- notifications
- speech input/output
- storage keys
- platform integration helpers
Platform side effects should start here or from the root shell, not from arbitrary components.
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.
- 2d ago First seen · 244 lines · 1,310 tokens per session scan A 1949f8e2a171
opencode-mobile AGENTS.md is an instructions file published in the GitHub repository alvarolorentedev/opencode-mobile (154 stars, last pushed 19d ago), licensed Apache-2.0. It adds 1,310 tokens to every session, about $0.0066 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
paseo AGENTS.md
AGENTS.md instructions for getpaseo/paseo, a project described as: Orchestrate multiple coding agents from desktop and mobile.
CodeAgentsMobile AGENTS.md
Instructions for eugenepyvovarov/CodeAgentsMobile, covering repository guidelines, runtime note (important), chatviewmodel module map, runtime service files and retired claude chat stack.
codewalk AGENTS.md
AGENTS.md instructions for verseles/codewalk, covering codewalk project rules, tracking, project context, required context and documentation.
build-brief AGENTS.md
Instructions for static-var/build-brief, covering contributor instructions, setup and verification, architecture and safety.
opencode-mobile AGENTS.md
Instructions for Shahfarzane/opencode-mobile, covering openchamber - ai agent & contributor reference, tech stack, structure, where to look and architecture.
agent-of-empires CLAUDE.md
Claude Code instructions for agent-of-empires/agent-of-empires, a project described as: Manage multiple Claude Code, OpenCode agents from either TUI or Web for easy access on mobile. Also supports Mistral Vibe, Codex CLI, Gemini CLI, Pi.dev, Copilot CLI, Factory Droid Coding.