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/sidrat2612/routesmith/copilot-instructionsgit clone --depth 1 https://github.com/sidrat2612/routesmithWrote 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/sidrat2612/routesmith/copilot-instructions)<a href="https://agentmods.dev/instructions/sidrat2612/routesmith/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/sidrat2612/routesmith/copilot-instructions.svg" alt="Measured on agentmods" 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 | $0.00634 | $0.00634 |
| Opus 5 | $0.00317 | $0.00317 |
| Sonnet 5 | $0.00127 | $0.00127 |
| Haiku 4.5 | $0.00063 | $0.00063 |
Grade A, and why
routesmith copilot-instructions.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 5d 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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
routesmith - Copilot Instructions
This repository contains routesmith, a host-aware auto-routing skill library for IDEs and coding agents.
Core Architecture Rule
routesmith is a HOST-AWARE skill layer, NOT a universal cross-provider broker.
- In Claude Code: only Claude-family models are managed.
- In Codex/OpenAI: only OpenAI-family models are managed.
- In Gemini CLI: only Gemini-family models are managed.
- In Copilot: model switching is host-controlled; use prompt optimization.
- Never assume a host can use models from another provider family.
Key Design Principles
- Auto mode is default — Users should not manually choose models per step.
- Capability-first routing — Map task types to capability classes, then resolve to host models.
- Truthful switching — Never claim a model was switched unless confirmed.
- Graceful fallback — If switching is unsupported, use prompt strategy.
- Deterministic planning — Planner works without API calls.
Versioning Rule
- Any code change must also update the package version in
pyproject.toml. - Do not leave behavior-changing code edits at the same published version.
- When making code changes, treat the version bump as part of the same change.
Description Alignment Rule
The package description must stay in sync across all three surfaces when releasing:
| Surface | Location | Current canonical description |
|---|---|---|
| PyPI | pyproject.toml → description field |
Auto-route coding agent tasks to the best model in your IDE. Python library + MCP server for Claude Code, Codex, Gemini CLI, Copilot, Cursor, and Aider. |
| GitHub repo | Repository description (set via gh api -X PATCH repos/sidrat2612/routesmith -f description='…') |
Host-aware model routing for coding agents. Python library + MCP server for Claude Code, Codex, Gemini CLI, Copilot, Cursor, and Aider. |
| GitHub topics | Repository topics (set via gh api -X PUT repos/sidrat2612/routesmith/topics) |
See current topic list in repo settings |
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.
- 5d ago First seen · 55 lines · 634 tokens per session scan A f5eda38b05da
routesmith copilot-instructions.md is an instructions file published in the GitHub repository sidrat2612/routesmith (4 stars, last pushed 3mo ago), licensed MIT. It adds 634 tokens to every session, about $0.0032 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 2026-08-31.
Other instructions, from other repositories
awesome-loop-engineering AGENTS.md
AGENTS.md instructions for ChaoYue0307/awesome-loop-engineering, covering repository guidance for ai agents, scope, editing rules, commit identity rule and entry format.
ai-engineering-skills AGENTS.md
Instructions for tmusser/ai-engineering-skills, covering agent instructions, route-first context loading and quality standards.
RepoResident AGENTS.md
Instructions for ychamel/RepoResident: Agent entry point: read CLAUDE.md in full — it is the operating manual — then follow its Session protocol. Everything else (state, workflows, project knowledge) is routed from there via the .agent/ directory.
multi-agent-loop-kit AGENTS.md
Instructions for anshulixyz/multi-agent-loop-kit, covering agents.md — multi-agent ownership registry, two meanings of “agent”, core rules, project lead / operator and beacon — loop intelligence agent.
agent-policykit copilot-instructions.md
Instructions for sidrat2612/agent-policykit, covering source of truth, project context, theme governance, engineering governance standard and operating principles.
agent-skills-lint AGENTS.md
Instructions for swarmclawai/agent-skills-lint, covering agent-skills-lint — agent-facing reference, global flags, json envelope, exit codes and commands.