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/saffron-health/opencode-gui/agents-mdgit clone --depth 1 https://github.com/saffron-health/opencode-guiWhat 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 | $0.00790 | $0.00790 |
| Opus 5 | $0.00395 | $0.00395 |
| Sonnet 5 | $0.00158 | $0.00158 |
| Haiku 4.5 | $0.00079 | $0.00079 |
Grade A, and why
opencode-gui 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 3d 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Commands
- Build:
pnpm build(builds extension + webview) - Watch:
pnpm watch(dev mode with hot reload) - Test:
pnpm test(runs vitest) - Single test:
pnpm test -- path/to/file.test.ts - E2E Tests:
pnpm test:e2e(runs playwright e2e tests with AI generation) - Package:
pnpm package(creates .vsix) - UI Kit:
pnpm uikit(opens component playground)
Architecture
VSCode extension with SolidJS webview. Two build targets:
- Extension (
src/extension.ts,OpenCodeService.ts,OpenCodeViewProvider.ts) - VSCode extension host - Webview (
src/webview/) - SolidJS chat UI communicating via@opencode-ai/sdk
Code Style
- TypeScript with strict mode, no
anytypes - SolidJS for webview components (signals, createMemo, Show/For)
- Functional components with hooks in
src/webview/hooks/ - CSS files colocated with components (App.css, uikit.css)
- Use VSCode API types from
@types/vscode - Prefer explicit imports, avoid barrel files
- Error handling: use VSCode's
window.showErrorMessageandLogOutputChannel
SolidJS Store Pitfall: createMemo + store proxy
NEVER wrap a store property lookup in createMemo if downstream consumers need to react to in-place mutations (e.g. produce, push, splice).
createMemo compares values with ===. A store proxy reference stays the same after in-place mutations, so the memo silently swallows the update. Use a plain function instead:
// ❌ BAD — createMemo returns same proxy ref, suppresses downstream updates
const messages = createMemo(() => store.message[sessionId()] ?? []);
// ✅ GOOD — plain function, consumers track the store proxy directly
const messages = () => store.message[sessionId()] ?? [];
createMemo is fine for derived computations that produce new values (e.g. .map(), new Map(...), arithmetic).
Publishing
Use the pnpm run publish script to publish the extension to the VSCode and OVSX marketplaces.
Logging into gcloud
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.
- 3d ago First seen · 61 lines · 790 tokens per session scan A 9ef055a3dc86
opencode-gui AGENTS.md is an instructions file published in the GitHub repository saffron-health/opencode-gui (57 stars, last pushed 5mo ago), licensed MIT. It adds 790 tokens to every session, about $0.0040 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
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.