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/claude-mdgit clone --depth 1 https://github.com/jayparikh/agentvizWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/jayparikh/agentviz/claude-md)<a href="https://agentmods.dev/instructions/jayparikh/agentviz/claude-md"><img src="https://agentmods.dev/badge/instructions/jayparikh/agentviz/claude-md.svg" alt="Measured on agentmods" height="20"></a>What 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 | $0.02588 | $0.02588 |
| Opus 5 | $0.01294 | $0.01294 |
| Sonnet 5 | $0.00518 | $0.00518 |
| Haiku 4.5 | $0.00259 | $0.00259 |
Grade A, and why
agentviz 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 4d 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 — 171 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. Renders Claude Code, Codex, VS Code Copilot Chat, Copilot CLI, Copilot prompt exports, and ATIF / Harbor session logs as interactive timelines, with auto-detection of file format.
Stack
- React 18 + Vite 6
- No CSS framework, all inline styles
- Font: JetBrains Mono (loaded from Google Fonts in index.html)
- Mixed JS/TS: components and hooks are plain JSX, parsers and data libs are TypeScript
Architecture
src/
App.jsx # Default v2 mount + Classic UI fallback, theme wiring, session entry routing
AppV2.jsx # Default workflow shell: Find, Review, Investigate, Analyze, Compare, Improve
main.jsx # React entry point
contexts/
SessionProvider.jsx # Shared session loading, discovery, compare, live, export, and derived state
PlaybackContext.jsx # Playback, search, track filtering, and derived state provider
hooks/
usePlayback.js # Playback state: time, playing, speed, seek, playPause
useSearch.js # Debounced search with matchSet/matchedEntries
useKeyboardShortcuts.js # Centralized keyboard handler (ref-based, stable listener)
useQA.js # Session Q&A state: messages, classifier, SSE streaming, abort
useFeatureFlag.js # localStorage-backed feature flag evaluation
useSessionLoader.js # File parsing, live init from /api/file, session reset, hero state
useLiveStream.js # SSE EventSource hook with 500ms debounce for live mode
usePersistentState.js # localStorage-backed useState with debounced writes
useDiscoveredSessions.js # Auto-discovery of sessions via /api/sessions or ?manifest= URL
useHashRouter.js # Hash-based routing between inbox and session views
useAsyncStatus.js # Async operation state machine (idle/loading/success/error)
useBreakpoint.js # Shared compact/narrow/wide responsive breakpoint hook
useFocusTrap.js # Modal focus trap with Escape close and focus restoration
useReducedMotion.js # Shared prefers-reduced-motion hook for inline/SVG animation guards
lib/
theme.js # Design token system, TRACK_TYPES, AGENT_COLORS
theme.d.ts # TypeScript declarations for theme.js
constants.js # SAMPLE_EVENTS data for demo mode
parser.ts # parseClaudeCodeJSONL() - Claude Code JSONL parser
codexParser.ts # parseCodexJSONL() - Codex rollout JSONL parser
copilotCliParser.ts # parseCopilotCliJSONL() - Copilot CLI JSONL parser
copilotCostParser.ts # parseCopilotPromptsJSON() - Copilot prompt export parser for token/cost analysis
vscodeSessionParser.ts # parseVSCodeChatJSON() - VS Code Copilot Chat JSON parser
atifParser.ts # parseAtifJSON() - ATIF / Harbor trajectory JSON parser (schema_version ATIF-v1.6)
liveSessionParser.ts # Incremental live JSONL parser for appended session text
parseSession.ts # Auto-detect format router: detectFormat() + parseSession()
session.ts # Pure helpers: getSessionTotal, buildFilteredEventEntries, buildTurnStartMap
sessionLibrary.js # localStorage-backed session library with content persistence
sessionParsing.ts # Session parsing utilities and types
sessionTypes.ts # TypeScript type definitions for session data
cacheMetrics.ts # Shared cache hit rate helpers
skillExtractor.ts # Skill/capability lifecycle extractor (skills, instructions, agents, MCP servers, tools, prompts)
autonomyMetrics.js # Human response time, idle gaps, intervention scoring
projectConfig.js # Project config surface detection (CLAUDE.md, .github/, etc.)
aiCoachAgent.js # AI Coach powered by @github/copilot-sdk (gpt-4o)
qaClassifier.js # Session Q&A instant answer engine (9 patterns + model context)
qaAgent.js # Q&A agent powered by @github/copilot-sdk for model fallback
replayLayout.js # Estimated layout + binary search windowing for virtualized replay
commandPalette.js # Precomputed search index with scoring, legacy views, and v2 workflow commands
diffUtils.js # Diff detection (isFileEditEvent) + Myers line diff algorithm
waterfall.ts # Waterfall view helpers: item building, stats, layout, windowing
graphLayout.js # Graph view helpers: ELKjs DAG builder, layout runner, position merger
costAnalysis.js # Per-call cost, context, cache-miss, and token aggregation helpers
pricing.js # Claude and OpenAI/Copilot model pricing table and cost estimation
exportHtml.js # Self-contained HTML export for single sessions and comparisons
dataInspector.js # Payload summary and preview helpers for inspector panels
formatTime.js # Duration and date formatting utilities
landingSessions.js # Shared landing browser labels, filters, and format options
lazyImport.js # Dynamic import wrapper with stale-chunk reload recovery
playbackUtils.js # Playback state helpers
components/
InboxView.jsx # Session inbox with auto-discovery, sorting, refresh, and review priority
DashboardView.jsx # Landing dashboard card grid with shared landing controls, aggregate stats, and quick open
DebriefView.jsx # AI Coach panel with cached analysis and one-click apply
FileUploader.jsx # Drag-and-drop file input with error handling
Timeline.jsx # Scrubable playback bar with event markers, turn boundaries
ReplayView.jsx # Windowed event stream + resizable inspector sidebar
TracksView.jsx # DAW-style multi-track lanes with solo/mute
WaterfallView.jsx # Tool execution waterfall with nesting, inspector sidebar
GraphView.jsx # Interactive DAG of turns/tool calls with ELKjs layout, pan/zoom, animations
StatsView.jsx # Aggregate metrics, tool ranking, turn summary
CostView.jsx # Token spend, cache, and context-composition analysis
CompareView.jsx # Side-by-side session comparison: Scorecard + Tools tabs
CommandPalette.jsx # Cmd+K fuzzy search overlay (events, turns, views)
DiffViewer.jsx # Inline unified diff view for file-editing tool calls
DataInspector.jsx # Readable payload inspector with summaries and copy support
LiveIndicator.jsx # Pulsing LIVE badge shown in CLI streaming mode
ShortcutsModal.jsx # Keyboard shortcuts overlay
QADrawer.jsx # Session Q&A slide-over drawer with instant answers
RecentSessionsPicker.jsx # Recent sessions dropdown picker
SyntaxHighlight.jsx # Lightweight code syntax coloring for raw data
ResizablePanel.jsx # Drag-to-resize split panel utility
ErrorBoundary.jsx # React error boundary with resetKey for recovery
Icon.jsx # Lucide icon wrapper; all icons must be imported AND added to ICON_MAP
app/ # Shell components: AppHeader, AppLandingState, AppLoadingState, CompareLandingState, CompareShell (AppLandingState switches between inbox and dashboard landing modes)
ui/ # Shared primitives: BrandWordmark, ShellFrame, ToolbarButton, ToolbarSelect, ExportStatusButton, KeyboardHint
v2/ # Default workflow UI: FlowRail, V2Header, FindPortfolio, ReviewHub, InvestigateView, AnalyzeShell, InlineCompare, ImproveView, LiveSessionBanner
waterfall/ # Waterfall sub-components: WaterfallChart, WaterfallRow, WaterfallInspector, TimeAxis
routes/
sessions.js # Session discovery, file serving, SSE streaming
ai.js # Coach analysis, Q&A, model info (SSE streaming)
config.js # Project config surface detection, file preview, apply
bin/
agentviz.js # CLI entry point: finds free port, starts server, opens browser
mcp/
server.js # MCP server: launch_agentviz and close_agentviz tools
server.js # HTTP server: serves dist/ SPA + SSE /api/stream file tail
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.
- 4d ago First seen · 171 lines · 2,588 tokens per session scan A eab2c7bdbe95
agentviz CLAUDE.md is an instructions file published in the GitHub repository jayparikh/agentviz (95 stars, last pushed 4d ago), licensed MIT. It adds 2,588 tokens to every session, about $0.0129 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
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.