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/claude-mdgit clone --depth 1 https://github.com/Community-Access/quillWrote 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/community-access/quill/claude-md)<a href="https://agentmods.dev/instructions/community-access/quill/claude-md"><img src="https://agentmods.dev/badge/instructions/community-access/quill/claude-md.svg" alt="Measured on agentmods" 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 | $0.03187 | $0.03187 |
| Opus 5 | $0.01594 | $0.01594 |
| Sonnet 5 | $0.00637 | $0.00637 |
| Haiku 4.5 | $0.00319 | $0.00319 |
Grade A, and why
quill CLAUDE.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 4d 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 — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Commands
# Install
pip install -e ".[ui,dev]"
# Install, fast (uv resolves/installs the same extras in seconds; dev-only
# tooling — releases still build with pip + the pinned system Python)
uv pip install -e ".[ui,dev]"
# Run the app
python -m quill
# Tests (standard)
pytest -q
# Tests, parallel (~5.5 min vs ~9; wx/UI tests stay on one worker — see
# tests/conftest.py pytest_collection_modifyitems for why loadgroup)
pytest -q -n 8 --dist loadgroup
# Fast smoke subset (high-signal core checks; seconds, not minutes)
pytest -m smoke -q
# Single test
pytest tests/unit/core/test_paths.py -x -q
# Run unit + stability
pytest tests/unit/ tests/stability/ -q
# Lint
ruff check .
ruff format --check .
# Scoped type-check (always scoped — never run unscoped mypy)
mypy quill\core quill\io
# Quillin self-lint
python -m quill.tools.quillin_lint <dir> --strict
# Agent standards lint (default: bundled agents dir; pass a path to lint one)
python -m quill.tools.agent_lint quill/core/ai/agents --strict
# Every gate at once, as one accessible scorecard (exit != 0 on any failure)
python -m quill.tools.platform_report
# App icons (regenerate all; --check fails on drift, --preview writes 256/16 PNGs)
python scripts/build_app_icons.py
The tests/conftest.py fixture sets quill.core.paths._DEV_BUILD = True for the whole test session. Any test that sets QUILL_DATA_DIR for isolation depends on this; do not remove it.
Architecture
QUILL is a layered wxPython desktop application with strict import boundaries:
quill/core— pure domain logic (documents, command registry, settings, keymap, storage, AI sessions, recovery). Nowximports. Strict-typed; always in scope formypy.quill/io— format readers/writers (read(path) -> Document,write(doc, path)). Nowx. Strict-typed.quill/ui— wxPython shell.main_frame.pyis the primary entry point (~27k lines and still the largest module by far); decomposition into feature mixins (seemain_frame_vault.py,main_frame_speech.py,main_frame_braille.py, etc.) is the preferred home for new command handlers — add to a mixin, not tomain_frame.py. Gradual typing (excluded frommypy).quill/platform/windows— Windows-specific bridges:prism_bridge.py(screen-reader announcements via Prism/pyttsx3),sr_detect.py,dpapi.py,credential_manager.py.quill/stability— cross-cutting runtime safety:safe_subprocess.py,crash_report.py(diagnostic bundles),redaction.py(secret scrubbing),task_manager.py,wx_heartbeat.py,safe_mode.py.quill/tools— internal CI gates:check_banned_patterns.py,module_size_budget.py,network_egress_audit.py,dialog_inventory.py,dialog_button_contract.py,quillin_lint.py,error_code_audit.py.quill/plugins— plugin-facing API surfaces and Quillin (extension) manifest model.
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.
- 4d ago First seen · 111 lines · 3,187 tokens per session scan A ae5b064a9fb7
quill CLAUDE.md is an instructions file published in the GitHub repository Community-Access/quill (43 stars, last pushed 4d ago), licensed MIT. It adds 3,187 tokens to every session, about $0.0159 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.