Borrowing it
Nothing to install: this file belongs to saajunaid/caddis-plugin. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/saajunaid/caddis-plugin/main/.github/copilot-instructions.mdgit clone --depth 1 https://github.com/saajunaid/caddis-pluginWrote 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/saajunaid/caddis-plugin/copilot-instructions)<a href="https://agentmods.dev/instructions/saajunaid/caddis-plugin/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/saajunaid/caddis-plugin/copilot-instructions/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/saajunaid/caddis-plugin/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/saajunaid/caddis-plugin/copilot-instructions.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.02330 | $0.02330 |
| Opus 5.5 | $0.00932 | $0.00932 |
| Sonnet 5.5 | $0.00466 | $0.00466 |
| Haiku 4.5 | $0.00233 | $0.00233 |
Grade A, and why
caddis-plugin copilot-instructions.md scanned grade A with 1 finding 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 1mo 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
**MCP server runtime:** `server.py` uses `uv run` (PEP 723 inline deps) — no local `.venv` install needed. `stdin=asyncio.subprocess.DEVNULL` on all subprocess spawns prevents stdio pipe inheritance deadlock (critical fi How it starts
The opening of the file, as written. The whole thing — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Instructions
This file is yours. The junai extension manages only the
<!-- junai:start -->…<!-- junai:end -->section below; everything else is never read, modified, or deleted by the extension.junai system documentation (25 agents, pipeline flow, MCP tools, routing conventions) is automatically provided by
.github/instructions/junai-system.instructions.md.
Project Overview
agent-sandbox is the authoring and source-of-truth repository for the junai agent pipeline system. Not a deployed application — this is where all 25 agent definitions, skills, prompts, and tooling are authored, tested, and compiled into runtime-specific project resources via the junai VS Code extension (junai-labs.junai).
Everything in .github/ here is the canonical source. Runtime-specific resources for Copilot, Claude, and Codex are exported from that source into project-local folders during packaging.
agent-sandbox/
├── .github/
│ ├── agents/ ← 25 agent definition files (*.agent.md)
│ ├── skills/ ← Reusable skill bundles (domain knowledge packs)
│ ├── prompts/ ← Reusable prompt files
│ ├── instructions/ ← Coding convention files (*.instructions.md)
│ ├── tools/
│ │ └── mcp-server/
│ │ └── server.py ← FastMCP server (9 tools, PEP 723 uv runtime)
│ ├── agent-docs/
│ │ ├── ARTIFACTS.md ← Artefact registry (inter-agent working files)
│ │ └── *.md ← Pipeline schema docs, artefact templates
│ ├── plans/ ← Implementation plans produced by the Planner agent
│ ├── handoffs/ ← Agent-to-agent handoff templates
│ ├── diagrams/ ← Architecture and workflow reference diagrams
│ ├── pipeline-state.json ← Live pipeline state (gates, routing, artefacts)
│ └── project-config.md ← Project-specific token definitions
├── validate_agents.py ← Pre-publish gate: checks 25 agents + MCP smoke test
├── export_runtime_resources.py ← Builds project-local `.github/`, `.claude/`, `.codex/` exports from canonical `.github/`
├── sync.ps1 ← junai-pull / junai-push sync functions
└── project-config.md ← Workspace-level config
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.
- 1mo ago First seen · 161 lines · 2,330 tokens per session scan A 4e9561139d30
caddis-plugin copilot-instructions.md is an instructions file published in the GitHub repository saajunaid/caddis-plugin (0 stars, last pushed today), licensed MIT. It adds 2,330 tokens to every session, about $0.0093 per session on Opus 5.5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
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).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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 copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.