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/bradygaster/squad/squad-routing-guardgit clone --depth 1 https://github.com/bradygaster/squadWhat 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 | $0.01073 | $0.01073 |
| Opus 5 | $0.00536 | $0.00536 |
| Sonnet 5 | $0.00215 | $0.00215 |
| Haiku 4.5 | $0.00107 | $0.00107 |
Grade A, and why
squad squad-routing-guard.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 yesterday.
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 — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
🚦 Squad Routing Guard
Read this before handling ANY non-trivial task in this repository.
If you are a generic Copilot session (not a named squad agent), your first job is to route — not to act. Specialist squad agents own well-defined domains. Taking over their work produces inconsistent results and loses their accumulated context.
Step 1 — Am I Already a Named Agent?
If you were spawned as a named Squad agent (any cast name in .squad/casting/registry.json), skip this file — your charter governs you. Proceed with your charter from .squad/agents/{your-name}/charter.md.
If you are a generic Copilot CLI session, continue reading.
Step 2 — Routing Decision Tree
Is this a trivial one-off question (no code/file changes needed)?
└─ YES → Answer directly. No routing required.
└─ NO → Continue ↓
Does the issue/PR/task have a squad:{name} label?
└─ YES → That agent owns it. Do NOT handle it. Route it. (See §4)
└─ NO → Continue ↓
Does the work type match a specialist domain? (See §3 + .squad/routing.md)
└─ YES → Route to that specialist. (See §4)
└─ NO → Handle it yourself as a generic task.
Step 3 — Routing Table
Read .squad/routing.md for the project-specific routing table. For generic Squad questions:
| Work type | Route to | Examples |
|---|---|---|
| Core runtime, adapter, spawn orchestration | EECOM | CopilotClient, session pool, tools module |
| Prompt architecture, coordinator logic | Procedures | Agent charters, spawn templates, response tier selection |
| Type system, TypeScript strictness | CONTROL | Discriminated unions, generics, tsconfig |
| SDK integration | CAPCOM | @github/copilot-sdk usage, CopilotSession lifecycle |
| Tests & quality, CI/CD | FIDO | Test coverage, Vitest, edge cases, CI/CD gates |
| Docs, README, API docs | PAO | README, getting-started, demos, contributor recognition |
| Architecture, product direction, review | Flight | Architectural decisions, code review, scope/trade-offs |
| Session logging, decision merge, DispatchGuard audit | Scribe | Auto — never needs explicit routing |
| Work queue, backlog, DispatchGuard verdict alerts | Ralph | GitHub issues, PR state, idle-watch, violations |
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.
- yesterday First seen · 114 lines · 1,073 tokens per session scan A ffc63efb2896
squad squad-routing-guard.instructions.md is an instructions file published in the GitHub repository bradygaster/squad (3,140 stars, last pushed 2d ago), licensed MIT. It adds 1,073 tokens to every session, about $0.0054 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-unify-chat-provider AGENTS.md
Instructions for smallmain/vscode-unify-chat-provider, a project described as: Integrate multiple LLM API providers into VS Code's GitHub Copilot Chat using the Language Model API. One-click use of your Claude Code, Gemini CLI, Antigravity, Github Copilot, OpenAI Codex (ChatGPT Plus/Pro), xAI Grok (SuperGrok / X…
apex-accelerator agent-skills.instructions.md
Guidelines for creating high-quality Agent Skills for GitHub Copilot.
apex-accelerator context-optimization.instructions.md
Context window optimization rules for agent definitions, skills, and instruction files.
apex-accelerator no-interactive-shell.instructions.md
Prevents interactive shell prompts and long-output terminal replays from being injected into chat. Forbids -i flags on mv/rm/cp, read -p, and confirm prompts (incl. inside bash -c '...'). Pipe long output to files. Scoped to chat-context-loaded files; skill references/ and templates/ are exempt because they hold…
apex-accelerator github-actions.instructions.md
Project-specific standards for GitHub Actions workflows in this repository.
apex-accelerator iac-terraform-best-practices.instructions.md
Terraform-specific IaC best practices for Azure templates. AVM-first, CAF naming, security baseline, provider pins.