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/microsoft/autosaddler/copilot-instructionsgit clone --depth 1 https://github.com/microsoft/AutoSaddlerWhat 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 | $0.00764 | $0.00764 |
| Opus 5 | $0.00382 | $0.00382 |
| Sonnet 5 | $0.00153 | $0.00153 |
| Haiku 4.5 | $0.00076 | $0.00076 |
Grade A, and why
AutoSaddler 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 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- Only skip `uv` wrapping for common non-Python shell commands like: `ls`, `cd`, `cat`, `echo`, `pwd`, `git ...`, `mkdir`, `rm`, `cp`, `mv`, `sed`, `awk`, `curl`, `wget` (unless they are part of a Python workflow step). How it starts
The opening of the file, as written. The whole thing — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GitHub Copilot instructions (repo-wide)
Environment & command execution (IMPORTANT)
- This repo uses a Python environment managed by
uv. - Before running any Python-related command (anything that invokes
python,pip,pytest,ruff,mypy,alembic,django-admin,flask,uvicorn,gunicorn,mkdocs, etc.), always run it inside the uv environment. - Prefer these patterns (pick the most direct one):
uv run <command ...>(preferred for one-off commands)- If an interactive shell is needed:
uv venv && source .venv/bin/activate(or platform equivalent), then run commands.
- Do not assume the env is already active.
- Only skip
uvwrapping for common non-Python shell commands like:ls,cd,cat,echo,pwd,git ...,mkdir,rm,cp,mv,sed,awk,curl,wget(unless they are part of a Python workflow step).
Examples
- ✅
uv run python -m pytest -q - ✅
uv run ruff check . - ✅
uv run python -m mypy src/ - ✅
uv run python scripts/sync_data.py --dry-run - ✅
git status(nouvneeded) - ✅
ls -la(nouvneeded) - ❌
pytest(should beuv run pytest) - ❌
python script.py(should beuv run python script.py)
Dependency management
- Add/remove deps using
uv add <pkg>/uv remove <pkg>(or whatever standard this repo uses). - If a lockfile is present, keep it updated consistently with
uvworkflows.
Documentation & consistency (IMPORTANT)
- After any code changes, always check and update relevant documentation (
docs/,README.md), output-related files (docstring, config references), and log/result schemas to reflect the latest changes. - If inconsistencies are found between code and documentation, always correct them. If unsure how to resolve an inconsistency, ask the user before proceeding.
- Keep CLI help text, config file comments, and doc examples in sync with actual implementations.
Testing (IMPORTANT)
- Always run the test suite after significant code changes (
uv run python -m pytest tests/ -v --tb=short). - Do not consider a task complete until tests pass.
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.
- 2d ago First seen · 46 lines · 764 tokens per session scan A 54fd825234d7
AutoSaddler copilot-instructions.md is an instructions file published in the GitHub repository microsoft/AutoSaddler (165 stars, last pushed 8d ago), licensed MIT. It adds 764 tokens to every session, about $0.0038 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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 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).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
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 oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.