Borrowing it
Nothing to install: this file belongs to 0xkuze/add-dir-opencode. 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/0xkuze/add-dir-opencode/main/AGENTS.mdgit clone --depth 1 https://github.com/0xkuze/add-dir-opencodeWrote 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/0xkuze/add-dir-opencode/agents-md)<a href="https://agentmods.dev/instructions/0xkuze/add-dir-opencode/agents-md"><img src="https://agentmods.dev/badge/instructions/0xkuze/add-dir-opencode/agents-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/0xkuze/add-dir-opencode/agents-md"><img src="https://agentmods.dev/badge/instructions/0xkuze/add-dir-opencode/agents-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 | $0.02062 | $0.02062 |
| Opus 5.5 | $0.00825 | $0.00825 |
| Sonnet 5.5 | $0.00412 | $0.00412 |
| Haiku 4.5 | $0.00206 | $0.00206 |
Grade A, and why
add-dir-opencode 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 1mo 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 — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Guidance for AI agents working in this repository.
What this repo is
opencode-add-dir — an OpenCode plugin that adds Claude Code-style /add-dir
functionality: users can add external working directories to their session and
the plugin auto-approves external_directory permission checks for those
directories, plus injects them into the system prompt.
- npm package:
opencode-add-dir, MIT, published via semantic-release on push tomain. - Runtime: Bun (build, test, package manager). TypeScript, ESM only.
- Upstream:
github.com/0xkuze/add-dir-opencode(npmopencode-add-dir).
Dual V1/V2 OpenCode support (important)
The package deliberately ships both OpenCode 1 and OpenCode 2 plugin implementations from one set of entrypoints, following the dual-export pattern in https://opencode.ai/v2/docs/build/plugins/migrate-v1#support-v1:
- OpenCode 2 reads
id+setup()on the default export and ignores everything else. It also auto-loads the./tuiexport beside the main entry. - OpenCode 1 (>= 1.18.29) calls
server()(server entry) andtui()(TUI entry) and ignoressetup(). The V1 object entrypoint shape is why the dev dependency on@opencode-ai/pluginshould stay on a recent 1.x version.
Do not delete the V1 code paths when touching V2 code (or vice versa) unless
explicitly asked — backwards compatibility is intentional. Keep both sides
working: test/plugin.test.ts covers V1, test/v2-plugin.test.ts covers V2,
and test/package.test.ts verifies the built artifacts export both shapes.
Entry points
| File | Role |
|---|---|
src/index.ts |
Server entry. Default export: { ...AddDirServerV2, server: AddDirPlugin } |
src/v2-plugin.ts |
V2 server plugin: Plugin.define({ id, setup }) from @opencode/plugin |
src/plugin.ts |
V1 server plugin (Plugin from @opencode-ai/plugin) — config, tool.execute.before, event, experimental.chat.system.transform hooks |
src/tui-plugin.tsx |
V1 TUI plugin (JSX, @opencode-ai/plugin/tui + @opentui/solid) + dual default export { ...AddDirTuiV2, tui } |
src/v2-tui.ts |
V2 CLI plugin from @opencode/plugin/tui: keymap-layer slash commands (registered from an app slot render — see the gotcha below), promise-based dialogs, and a select-dialog directory browser |
src/tui-state.ts |
Shared TUI state helpers (paths, validate, add/remove) used by both TUI implementations |
src/state.ts |
Shared server state: directories.json / session-dirs.json persistence, mtime cache, path matching, V1 tui.json self-registration (ensureTuiConfig) |
src/permissions.ts |
V1 permission hacks (session grant prompt, permission.asked auto-approve) |
src/context.ts |
System-prompt injection (collectAgentContext), used by both V1 and V2 |
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.
- 1mo ago First seen · 133 lines · 2,062 tokens per session scan A 495a82664379
add-dir-opencode AGENTS.md is an instructions file published in the GitHub repository 0xkuze/add-dir-opencode (21 stars, last pushed 1mo ago), licensed MIT. It adds 2,062 tokens to every session, about $0.0082 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 2026-10-01.
add-dir-opencode AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| add-dir-opencode AGENTS.md0xkuze/add-dir-opencode | Instructions file | 21 | 1mo ago | MIT | A | 2,062 | Codex, OpenCode |
| 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 |