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/lexfrei/ccc/billynpx skills add lexfrei/ccc --skill billygit clone --depth 1 https://github.com/lexfrei/cccWhat 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 | $0.00020 | $0.00751 |
| Opus 5 | $0.00010 | $0.00376 |
| Sonnet 5 | $0.00004 | $0.00150 |
| Haiku 4.5 | $0.00002 | $0.00075 |
Grade A, and why
billy 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.
- **Network**: `curl` endpoints, check connectivity, DNS resolution, port availability How it starts
The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Where's the proof, Billy? We need proof!
Someone made a claim. Stop everything and investigate. No proof — no trust.
Input
The argument is a claim that needs verification. Examples:
/billy "the runner is dead"/billy "this endpoint returns 500 on empty body"/billy "the migration broke prod"/billy "node memory is leaking"
Rules
- Do NOT take the claim at face value. Assume nothing. Verify everything.
- Do NOT stop at the first piece of evidence. Keep digging until you have a conclusive answer.
- Do NOT suggest — investigate. Run commands, read logs, check code, query APIs. Produce evidence.
- Do NOT fix anything. This is investigation only. Report findings, never apply changes.
Process
Launch an Agent (model: opus) to perform the investigation. The agent must:
Phase 1: Understand the claim
Parse the assertion. Identify:
- Subject: what system/component/process is involved
- Predicate: what is being claimed about it (dead, broken, leaking, failing, etc.)
- Implicit scope: timeframe, environment, context from the current conversation
Phase 2: Gather evidence
Use every available tool to collect evidence. Prioritize direct observation over inference:
- Processes and services:
ps,systemctl status,docker ps,kubectl get pods, health endpoints - Logs: application logs, system logs, journal, container logs,
dmesg - Code and config: read source code, check recent changes (
git log,git diff), review config files - Network:
curlendpoints, check connectivity, DNS resolution, port availability - Resources: disk space, memory, CPU, file descriptors, connection pools
- External systems: CI/CD status (
gh run list), monitoring dashboards, database state - History: git blame, recent deploys, recent config changes, cron jobs
Collect at least 3 independent pieces of evidence before forming a conclusion.
Phase 3: Attempt to reproduce
If the claim describes a failure or behavior:
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 · 97 lines · 0 tokens per session scan A 8c5a1c5f99de
billy is a skill published in the GitHub repository lexfrei/ccc (9 stars, last pushed 2d ago), licensed BSD-3-Clause. It adds 20 tokens to every session and 751 once invoked, about $0.0001 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 2026-08-31.
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…