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/community-access/quill/copilot-instructionsgit clone --depth 1 https://github.com/Community-Access/quillWhat 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 | $0.03570 | $0.03570 |
| Opus 5 | $0.01785 | $0.01785 |
| Sonnet 5 | $0.00714 | $0.00714 |
| Haiku 4.5 | $0.00357 | $0.00357 |
Grade A, and why
quill 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 3d 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.
How it starts
The opening of the file, as written. The whole thing — 264 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Copilot instructions for this repository
Repository state
This repository contains the implementation source tree together with the product requirements document under docs/Product Requirement Documents and Specifications/QUILL-PRD.md and docs/QUILL-PRD.html.
When generating code or task plans, treat the PRD as the source of truth for intended architecture and conventions.
For the detailed day-to-day command and invariant reference, read
CLAUDE.md; keep this file as the concise, always-on guide.
Build, test, and lint commands
The project has a runnable test suite and CI gates. Use focused tests while developing, then run the narrowest applicable quality checks:
# Environment setup
uv python install 3.12
uv sync --all-extras
pre-commit install
# Fast test paths
pytest -m smoke -q
pytest tests\unit\path\to\test_file.py::test_name -q
pytest -q -n 8 --dist loadgroup
# Lint + strict type-check
ruff check .
ruff format --check .
mypy quill\core quill\io
# Optional suites
RUN_PERF=1 pytest -m perf -q
$env:QUILL_UIA_TESTS = "1"; pytest -m uia -q
tests/conftest.py forces quill.core.paths._DEV_BUILD = True and puts the
pytest temp root under the user home directory. This is what makes per-test
QUILL_DATA_DIR overrides safe; preserve it and use tmp_path for isolated
persistence tests. The parallel command above serializes tests/unit/ui on
one worker because wx, clipboard, hotkey, and screen-reader resources are
process-global.
quill/core and quill/io are strict and wx-free. Keep mypy scoped to those
layers; quill/ui is gradually typed. Before changing the UI dependency, note
that wxPython is exactly pinned in pyproject.toml because screen-reader
acceptance covers that tested build, not every upstream wx release.
High-level architecture (from PRD)
Quill is designed as a screen-reader-first Windows desktop app in Python + wxPython, with a strict separation between UI, core logic, I/O format handlers, platform bindings, and optional AI providers.
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.
- 3d ago First seen · 264 lines · 3,570 tokens per session scan A be449c61bf14
quill copilot-instructions.md is an instructions file published in the GitHub repository Community-Access/quill (43 stars, last pushed 3d ago), licensed MIT. It adds 3,570 tokens to every session, about $0.0178 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 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.