az-scout plugin-api.instructions.md

Rules for the core plugin interface: the contract that lets add-ons provide routes, tools, pages, chat modes, and navigation actions to az-scout.

In plain words
What is it for?
Use them when changing the plugin protocol, its version, compatibility checks, or shared plugin data structures.
Why use it?
They keep the interface compatible so existing add-ons continue to load after core changes.

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/az-scout/az-scout/plugin-api
Clone the repo
git clone --depth 1 https://github.com/az-scout/az-scout

Made for: GitHub Copilot.

Per session 856 This file is loaded in full into every session.
When invoked 856 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 $0.00856 $0.00856
Opus 5 $0.00428 $0.00428
Sonnet 5 $0.00171 $0.00171
Haiku 4.5 $0.00086 $0.00086

Measured 2d ago against content hash 72093f3e8824, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

az-scout plugin-api.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 2d 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.

.github/instructions/plugin-api.instructions.md · 89 lines

How it starts

The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Plugin API (core side)

Audience: core maintainers changing the plugin contract. For plugin authors implementing a plugin, see plugin-author.instructions.md.

Compatibility

  • PLUGIN_API_VERSION lives in azure_api/__init__.py. Bump it for any breaking change to the protocol, dataclasses, or shared helpers.
  • The plugin manager guard refuses to load plugins declaring an incompatible major version — keep the guard in sync.
  • Document every bump in CHANGELOG.md under ### Changed with a migration note.

Plugin protocol

from az_scout.plugin_api import AzScoutPlugin, TabDefinition, ChatMode, NavbarAction

class MyPlugin:
    name = "my-plugin"       # unique identifier
    version = "0.1.0"

    def get_router(self) -> APIRouter | None: ...
    def get_mcp_tools(self) -> list[Callable] | None: ...
    def get_static_dir(self) -> Path | None: ...
    def get_tabs(self) -> list[TabDefinition] | None: ...
    def get_chat_modes(self) -> list[ChatMode] | None: ...
    def get_navbar_actions(self) -> list[NavbarAction] | None: ...

All methods optional — return None to skip.

Conventions

  • Package layout: src-layout (src/az_scout_myplugin/) with hatchling
  • Naming: Package az-scout-plugin-{name}, module az_scout_{name}
  • Entry point: [project.entry-points."az_scout.plugins"]
  • Lazy imports: Inside methods to avoid circular imports at discovery time
  • Static dir: Path(__file__).parent / "static" at module level

AI completion helpers

from az_scout.plugin_api import is_ai_enabled, plugin_ai_complete

if is_ai_enabled():
    result = await plugin_ai_complete(
        "Analyse this data...",
        system_prompt="You are an expert.",
        region="eastus",
        cache_ttl=600,  # 10 min cache, 0 to bypass
    )
    # result = {"content": "...", "tool_calls": [...]}

JS: if (aiEnabled) { const r = await aiComplete("...", {cacheTtl: 600}); }

Isolation rules

  • Fully self-contained — no global state mutation
  • No circular imports — use lazy imports
  • No heavy imports at module import time
  • Respect core authentication and context model
  • Never override built-in routes

Read the full file on GitHub · 89 lines

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. 2d ago First seen · 89 lines · 856 tokens per session scan A 72093f3e8824

Subscribe to this mod's changes

az-scout plugin-api.instructions.md is an instructions file published in the GitHub repository az-scout/az-scout (11 stars, last pushed 21d ago), licensed MIT. It adds 856 tokens to every session, about $0.0043 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.