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/jayparikh/agentviz/copilot-instructionsgit clone --depth 1 https://github.com/jayparikh/agentvizWhat 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 | $0.01103 | $0.01103 |
| Opus 5 | $0.00551 | $0.00551 |
| Sonnet 5 | $0.00221 | $0.00221 |
| Haiku 4.5 | $0.00110 | $0.00110 |
Grade A, and why
agentviz copilot-instructions.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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTVIZ
Session replay visualizer for AI agent workflows (Claude Code, VS Code Copilot Chat, Copilot CLI).
Stack
- React 18 + Vite 6, inline styles only, JetBrains Mono font
- Mixed JS/TS: components and hooks are plain JSX, parsers and data libs are TypeScript
- Design tokens in
src/lib/theme.js
Commands
npm run dev # Dev server
npm run build # Production build to dist/
npm test # Run tests via Vitest
npm run test:watch # Watch mode
npm run typecheck # tsc --noEmit
Rules
- Search existing code before writing new abstractions.
- Run tests after every non-trivial change.
- Prefer editing existing files over creating new ones.
- Never silently apply config changes — surface drafts first.
- Product name is always AGENTVIZ (all caps, no spaces). Never "AgentViz" or "Agentviz".
- All UI changes must conform to
docs/ui-ux-style-guide.md. Review the checklist at the bottom of that file before approving any PR that touches components, styles, or visual behavior.
Five-Artifact Sync Rule
Every UI change must update ALL FIVE of these before committing. Never let them drift:
README.md— feature descriptions, architecture section, file treedocs/ui-ux-style-guide.md— token values, patterns, rulesdocs/color-palette.html— visual swatch reference; hex values must matchtheme.jsand the style guidedocs/screenshots/— all 8 screenshots (see Screenshots section below)- Repo memory — store any new conventions with
store_memory
Screenshots
The README references 8 screenshot files in docs/screenshots/. All must be kept in sync.
Files: landing.png, session-hero.png, replay-view.png, tracks-view.png, waterfall-view.png, graph-view.png, stats-view.png, coach-view.png
Workflow (using Playwright MCP tools):
- Start dev server:
npm run dev - Navigate to
http://127.0.0.1:3000, resize to 1400x860 - Capture
landing.pngfrom the landing page (before loading a session) - Click "Load a demo session", then click each tab and capture: replay, tracks, waterfall, graph, stats
- For Coach: click the tab, hide the error banner with JS before capturing:
document.querySelectorAll('*').forEach(el => { if (el.children.length === 0 && el.textContent.trim().startsWith('AI analysis failed')) { let n = el; for (let i = 0; i < 6; i++) { if (n.parentElement?.textContent.trim().startsWith('AI analysis failed')) n = n.parentElement; else break; } n.style.display = 'none'; } }); - Copy
replay-view.pngtosession-hero.png(hero reuses replay image)
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 · 74 lines · 1,103 tokens per session scan A e69530120edb
agentviz copilot-instructions.md is an instructions file published in the GitHub repository jayparikh/agentviz (95 stars, last pushed 3d ago), licensed MIT. It adds 1,103 tokens to every session, about $0.0055 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
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.
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).
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.