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/sepivip/claude-code-visualizer/claude-mdgit clone --depth 1 https://github.com/sepivip/claude-code-visualizerWhat 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 | $0.00747 | $0.00747 |
| Opus 5 | $0.00374 | $0.00374 |
| Sonnet 5 | $0.00149 | $0.00149 |
| Haiku 4.5 | $0.00075 | $0.00075 |
Grade A, and why
claude-code-visualizer 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 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 — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — project conventions
Context for any AI/dev session working in this repo. Keep it short and current.
Project: cckeys — "Claude Code — Interactive Trainer". A static, terminal-styled React/TS app teaching the Claude Code CLI (shortcuts, slash commands, settings, live keyboard map). Open source. Live at https://cckeys.work · repo sepivip/claude-code-visualizer.
Versioning (IMPORTANT — keep this updated)
- Single source of truth: the
versionfield inpackage.json(semver). - It is injected at build time by Vite
define→ the global__APP_VERSION__(seevite.config.tsandsrc/global.d.ts) and displayed in the app header (top-right, next to the GitHub icon), linking to the repo's/releases. - Bump it when shipping a notable change before/with the deploy:
- patch (
0.1.x) — bug fixes / small tweaks - minor (
0.x.0) — new features (e.g. Quiz, guided track) - major (
x.0.0) — big/breaking redesigns
- patch (
- That's the only step — no other file needs editing; the header updates automatically on deploy. Consider tagging a matching GitHub release when bumping a minor/major.
Deploy
- Push to
main→ GitHub Actions runs the tests, and only if they pass, deploys to GitHub Pages → https://cckeys.work. Every push tomainauto-deploys. Branches/PRs run CI too. - Custom domain is pinned by
public/CNAME(cckeys.work). Vitebaseis'./'(relative) so the build works at the apex domain and the legacy project subpath — do not change it back to an absolute base. DNS forcckeys.workis on Cloudflare (A records → GitHub Pages IPs,wwwCNAME →sepivip.github.io, all DNS-only).
Working conventions
- Stack: Vite · React 18 · TypeScript (strict, no
any) · Tailwind v4 · Vitest · Playwright · pnpm. - Work on a feature branch, keep
pnpm test+pnpm buildgreen, then fast-forward merge tomain. - Verify visual/UI changes in a real browser (Playwright screenshot) before merging — this repo
cares about looking seamless. Aesthetic: dark terminal, coral accent
#D97757, JetBrains Mono. - Content lives in
content/cc-catalog.raw.json→ generated tosrc/data/catalog.tsviapnpm build:catalog. The keyboard derives chords at runtime; multi-stroke sequences (e.g.Ctrl+X Ctrl+E) are intentionally not mapped to a single key.
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 · 47 lines · 747 tokens per session scan A 256c2233b5ae
claude-code-visualizer CLAUDE.md is an instructions file published in the GitHub repository sepivip/claude-code-visualizer (2 stars, last pushed 2mo ago), licensed MIT. It adds 747 tokens to every session, about $0.0037 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
cheaters-generator AGENTS.md
Instructions for aplaceforallmystuff/cheaters-generator, covering agents.md - cheaters-generator, usage and constraints.
csharp-cheatsheet CLAUDE.md
Claude Code instructions for LabinatorSolutions/csharp-cheatsheet, covering claude.md, stack, commands and seo & geo.
cheaters-generator CLAUDE.md
Instructions for aplaceforallmystuff/cheaters-generator, a project described as: Claude Code plugin for generating personalized cheatsheet systems.
cheaters-generator GEMINI.md
Instructions for aplaceforallmystuff/cheaters-generator, a project described as: Claude Code plugin for generating personalized cheatsheet systems.
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.