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 skills/foundinblank/flashy/test-flashynpx skills add foundinblank/flashy --skill test-flashygit 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 | $0.00022 | $0.00545 |
| Opus 5 | $0.00011 | $0.00272 |
| Sonnet 5 | $0.00004 | $0.00109 |
| Haiku 4.5 | $0.00002 | $0.00055 |
Grade A, and why
test-flashy 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.
What it actually says
You are testing the Flashy plugin, which flashes the terminal background when Claude finishes a turn.
Note: since v0.2.0, Flashy suppresses the Stop flash if Claude Code reports background agents or scheduled crons still running. If you have any of those active in this session, you may not see the Step 1 flash — that's expected, not a bug.
Step 1 — Trigger a Stop event (1 flash)
Say exactly this and nothing else — do not add any other text, explanation, or follow-up:
⚡ Why did the flashlight go to school? Because it wanted to be a little brighter.
(You should have just seen 1 flash. That was a Stop event — I finished my turn.)
Then STOP. Do not continue. Wait for the user to respond.
Step 2 — After the user responds, present the quiz
Regardless of what they said, say exactly this and nothing else:
⚡⚡ Excellent. The flash dimension grows stronger.
"You have been chosen by the Flash. But first, you must answer..."
(You should see a double-flash soon - keep your eyes on the terminal for a few moments after the next question appears!)
Then immediately use AskUserQuestion with this question:
- question: "What is the speed of light in a dark-mode terminal?"
- header: "Flash quiz"
- options:
- label: "E=mc², obviously", description: "Mass times the speed of light squared"
- label: "GPU speed", description: "However fast my GPU renders it"
- label: "Doesn't matter", description: "I just mass-approve tool calls anyway"
Then STOP. Do not continue. Wait for the user to respond.
Step 3 — After the user picks, deliver the final verdict
Regardless of their choice, say exactly this and nothing else:
⚡⚡⚡ The terminal flickers. A voice echoes:
"Correct. You are worthy of the flash."
That was a Notification event — I was waiting for your input, and Flashy notified you with a double-flash.)
Want to see what happens when I'm waiting? Step away from your terminal for a minute — Claude Code will notice you're idle and fire another Notification event (2 pulses instead of 1).
Flashy is working! 🔦
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 · 55 lines · 22 tokens per session scan A 58ff6f3223bc
test-flashy is a skill published in the GitHub repository foundinblank/flashy (2 stars, last pushed 26d ago), licensed MIT. It adds 22 tokens to every session and 545 once invoked, about $0.0001 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…