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/phodal/routa/agents-mdgit clone --depth 1 https://github.com/phodal/routaWhat 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 | $0.01834 | $0.01834 |
| Opus 5 | $0.00917 | $0.00917 |
| Sonnet 5 | $0.00367 | $0.00367 |
| Haiku 4.5 | $0.00183 | $0.00183 |
Grade A, and why
routa 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 — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Routa.js — Multi-agent coordination platform with dual-backend architecture (Next.js + Rust/Axum).
Routa.js is a workspace-first multi-agent coordination platform with two runtime surfaces:
- Web: Next.js app and API in
src/ - Desktop: Tauri app in
apps/desktop/backed by Axum incrates/routa-server/
The project is intentionally not "two separate products". Web and desktop differ in deployment model and storage, but they are expected to preserve the same domain semantics, API shape, and agent-coordination behavior.
docs/ARCHITECTURE.md: Canonical architecture boundaries, domain model, protocol stack, and cross-backend invariants.docs/adr/: Durable architectural decisions. Start here for "why".docs/design-docs/: Human-reviewed design intent and normalized decisions migrated from.kiro/specs/.
Coding Standards
- General coding style guidance lives in
docs/coding-style.md; keep this file focused on routing and repo-level guardrails. - Source of truth for executable gates is
docs/fitness/+entrix; do not restate tool-level checks here. - Frontend and desktop API calls in
src/appandsrc/clientshould useresolveApiPath+desktopAwareFetchfor统一的后端路径组装：resolveApiPath（src/client/config/backend.ts）：统一补全/api前缀并在需要时拼接后端 base URL。desktopAwareFetch（src/client/utils/diagnostics.ts）：在 Tauri 桌面静态运行时自动落到http://127.0.0.1:3210或配置的后端地址。- 避免在前端/桌面再次直接写
fetch('/api/...')。
- For long behavior-heavy files, prefer orchestration shell + domain hooks over UI-only slicing.
- Apply the same pattern to oversized API routes: thin top-level route, extract workflow branches (session creation, streaming, provider dispatch, etc.).
- Split route refactors by workflow branch before shared helpers; avoid premature generic
utils. - Before large behavior refactors, add or extend characterization tests that lock routing/lifecycle/persistence/recovery behavior.
- All UI-facing strings must go through the i18n system (e.g.,
t('key')). Do not hardcode English or Chinese literals in 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.
- 3d ago First seen · 121 lines · 1,834 tokens per session scan A 0d9a551bc71e
routa AGENTS.md is an instructions file published in the GitHub repository phodal/routa (1,808 stars, last pushed 20d ago), licensed MIT. It adds 1,834 tokens to every session, about $0.0092 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.