semantic-router copilot-instructions.md

Instructions for reviewing changes in the Semantic Router project with GitHub Copilot. They identify the required starting documents, review priorities, and repository commands for generating and validating an agent report.

In plain words
What is it for?
Use them when reviewing a change, generating the repository's agent report, checking affected end-to-end tests, or running the full validation process.
Why use it?
They give reviewers a consistent order for finding correctness, security, compatibility, testing, and documentation problems.

Instructions file for GitHub Copilot

Install

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.

agentmods
npx agentmods add instructions/vllm-project/semantic-router/copilot-instructions
Clone the repo
git clone --depth 1 https://github.com/vllm-project/semantic-router

Made for: GitHub Copilot.

Per session 304 This file is loaded in full into every session.
When invoked 304 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00304 $0.00304
Opus 5 $0.00152 $0.00152
Sonnet 5 $0.00061 $0.00061
Haiku 4.5 $0.00030 $0.00030

Measured yesterday against content hash 97a3d7936fbf, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

semantic-router 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 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.

.github/copilot-instructions.md · 39 lines

What it actually says

GitHub Copilot Instructions

Use the repository harness for reviews and code suggestions.

Start Here

  1. Read AGENTS.md and tools/agent/docs/README.md.

  2. Resolve the task before proposing changes:

    make agent-report ENV=cpu CHANGED_FILES="path/to/file ..."
    
  3. Follow the reported primary skill, context, nearest local AGENTS.md, and validation commands.

tools/agent/docs/ is the human-readable contract. Manifests, scripts, Make targets, and workflows are the executable contract. Keep them aligned instead of restating their rules here.

Review Priorities

Report concrete, file-specific findings in this order:

  1. correctness, security, and behavior regressions;
  2. public API or configuration compatibility;
  3. missing tests or affected E2E coverage;
  4. module-boundary and hotspot growth;
  5. drift between documentation and executable rules.

Behavior-visible routing, startup, config, Docker, CLI, or API changes normally need E2E coverage. Harness changes need make agent-validate. Use the full gate reported by make agent-report before describing a change as complete.

Keep suggestions within the requested subsystem, preserve DCO sign-off, and do not copy branch notes, AI/tool attribution, credentials, private paths, or test receipts into durable documentation.

Changes

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.

  1. yesterday First seen · 39 lines · 304 tokens per session scan A 97a3d7936fbf

Subscribe to this mod's changes

semantic-router copilot-instructions.md is an instructions file published in the GitHub repository vllm-project/semantic-router (5,423 stars, last pushed 2d ago), licensed Apache-2.0. It adds 304 tokens to every session, about $0.0015 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.