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/foundinblank/flashy/claude-mdgit clone --depth 1 https://github.com/foundinblank/flashyWhat 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 | $0.00950 | $0.00950 |
| Opus 5 | $0.00475 | $0.00475 |
| Sonnet 5 | $0.00190 | $0.00190 |
| Haiku 4.5 | $0.00095 | $0.00095 |
Grade A, and why
flashy 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 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.
How it starts
The opening of the file, as written. The whole thing — 56 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.
Project Overview
Flashy is a Claude Code plugin written in pure Bash that pulses the terminal background color when Claude finishes a turn (Stop event) or sends a notification. It has zero external dependencies.
Architecture
.claude-plugin/plugin.json— Plugin metadata (name, version, author)hooks/hooks.json— Registers two Claude Code hook events (Stop, Notification), each callingflash.shwith the event name as$1. Notification is narrowed tomatcher: "permission_prompt|idle_prompt|agent_needs_input"; both entries carry a 2-secondtimeoutso a hung hook can't stall Claude Code.hooks/flash.sh— The entire implementation in one script:- Sources user config from
${XDG_CONFIG_HOME:-$HOME/.config}/flashy/config(if it exists), then applies bash parameter expansion defaults - For
stop, if stdin isn't a TTY, reads the hook's JSON and suppresses the pulse when Claude Code (v2.1.145+) reports non-emptybackground_tasksorsession_crons— see "Stop Suppression" below - Detects terminal background color via three-tier cascade: per-TTY color file → OSC 11 terminal query → static
FALLBACK_COLOR - Computes adaptive flash color by measuring luminance and shifting RGB toward white (dark themes) or black (light themes)
- Runs a pulse loop: set bg to flash color via OSC 11, sleep, restore original bg
- Sources user config from
config.default— Reference template for user config; not read at runtimeDESIGN.md— Detailed technical design documenttests/test_flash_stop_suppression.sh— Pure-bash automated test suite for the stop-suppression logic
Commands
No build system or linter. There is a pure-bash test suite for the stop-suppression logic, plus manual testing for the rest:
# Run the automated test suite (no jq/python/node required)
./tests/test_flash_stop_suppression.sh
# Test flash directly (must be run in a supported terminal, not VS Code)
./hooks/flash.sh stop
./hooks/flash.sh notification
# Install as Claude Code plugin
claude plugin add /path/to/flashy
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 · 56 lines · 950 tokens per session scan A 94356efaf888
flashy CLAUDE.md is an instructions file published in the GitHub repository foundinblank/flashy (2 stars, last pushed 26d ago), licensed MIT. It adds 950 tokens to every session, about $0.0047 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 2026-08-31.
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).
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.