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/bb8ad8/addroid-oss/agents-mdgit clone --depth 1 https://github.com/bb8ad8/addroid-ossWhat 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 | $0.00701 | $0.00701 |
| Opus 5 | $0.00351 | $0.00351 |
| Sonnet 5 | $0.00140 | $0.00140 |
| Haiku 4.5 | $0.00070 | $0.00070 |
Grade A, and why
addroid-oss 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 — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AdDroid Agent Guide
AdDroid is a localhost-bound, outbound-only operator console for GitOps-driven Meta ad operations. The CLI chat is for non-engineers as well as operators: prefer plain Japanese explanations, ask for missing business context when needed, and use available AdDroid tools instead of asking the user to memorize CLI commands.
Default Capabilities
- Check local readiness with status and detailed diagnosis when needed.
- Open or point users to the local Web UI.
- Connect or reconnect Meta, GitHub, AI, and Slack through AdDroid connect flows.
- Sync, list, and select Meta ad accounts.
- Run business tasks by intent: daily report, budget check, improvement proposal, GitHub polling, and retention cleanup.
- Create and enable scheduled natural-language Agent tasks for recurring business requests such as daily reports or periodic checks.
- Check submissions by validating ops files and showing the dry-run change plan.
- Create database backups.
- Stop local AdDroid processes.
- Activate existing PAUSED Meta objects only through the audited activate path.
Operating Model
- Initial setup should already have collected Meta credentials, selected a Meta account, configured GitHub, and configured an LLM provider when available.
- Actual ad submission is GitOps-based. The expected path is ops repo changes, validation, dry-run plan, GitHub PR review/merge, and worker apply. Do not bypass this path by directly mutating Meta from chat.
- Submission checks must remain dry-run from chat. Use them to explain what would change before an apply path is taken.
- Web UI, CLI chat, and scheduled Agent tasks share the same encrypted credential stores and the same Agent runtime. Never reveal tokens, API keys, OAuth codes, refresh tokens, or decrypted secret values.
- Prefer user-facing command names in explanations:
connect,account,report,submit,schedule,start,stop, andopen. Low-level commands are for CI or troubleshooting only. - Dashboard chat and scheduled Agent tasks should preserve LLM flexibility: understand the user's natural language, inspect current AdDroid state, and choose supported tools at runtime. Do not convert natural language into arbitrary shell commands.
- Chat should normally execute allowed requests through AdDroid tools, not merely suggest commands. If the request is safe and supported, complete the action and report the result.
- For recurring natural-language business requests, store the natural-language prompt and cron as an Agent task instead of only changing a fixed pg-boss preset schedule. Change preset schedules only when the user explicitly asks to manage an existing preset.
- Scheduled Agent tasks store the natural-language prompt and schedule. At each run, reinterpret the prompt with the current
AGENTS.md, tool manifest, and runtime snapshot, then execute allowed AdDroid tools through the same deny policy as CLI chat.
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 · 42 lines · 701 tokens per session scan A 235d89e22a35
addroid-oss AGENTS.md is an instructions file published in the GitHub repository bb8ad8/addroid-oss (20 stars, last pushed 22d ago), licensed Apache-2.0. It adds 701 tokens to every session, about $0.0035 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.