Borrowing it
Nothing to install: this file belongs to stepankaiser/ccphoto. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/stepankaiser/ccphoto/main/CLAUDE.mdgit clone --depth 1 https://github.com/stepankaiser/ccphotoWrote 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/stepankaiser/ccphoto/claude-md)<a href="https://agentmods.dev/instructions/stepankaiser/ccphoto/claude-md"><img src="https://agentmods.dev/badge/instructions/stepankaiser/ccphoto/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/stepankaiser/ccphoto/claude-md"><img src="https://agentmods.dev/badge/instructions/stepankaiser/ccphoto/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00883 | $0.00883 |
| Opus 5.5 | $0.00353 | $0.00353 |
| Sonnet 5.5 | $0.00177 | $0.00177 |
| Haiku 4.5 | $0.00088 | $0.00088 |
Grade A, and why
ccphoto 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 2mo 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CCPhoto
Phone camera bridge for Claude Code — MCP server + standalone CLI.
Build & Run
npm run build # Compile TypeScript
npm test # Run tests (94 tests, requires tsx)
node dist/index.js # Run standalone server
node dist/index.js --mcp # Run as MCP server
Architecture
src/index.ts— CLI entry point, arg parsingsrc/mcp.ts— MCP server with 7 tools (capture_photo, wait_for_photo, get_latest_photo, list_photos, send_to_phone (supportsspeakparam for TTS), start_livestream, get_live_frame)src/server.ts— HTTP server (serves mobile page, handles uploads, SSE push)src/mobile-page.ts— Self-contained HTML for phone camera capture, annotation canvas, content displaysrc/storage.ts— Photo file management (save, list, get latest, get by filename)src/network.ts— Local IP detectionsrc/token.ts— Session token generation/validationsrc/cert.ts— Self-signed certificate generation for HTTPS livestreamsrc/types.ts— Shared interfaces
Tests
Tests use Node.js built-in test runner with tsx for TypeScript execution.
Co-located with source: src/*.test.ts. Run with npm test.
token.test.ts— Token generation, validation, timing-safe comparisonstorage.test.ts— File save, list, collision handling, filteringnetwork.test.ts— IPv4 detection contractmobile-page.test.ts— HTML rendering, element presence, token embeddingserver.test.ts— HTTP endpoints, auth, uploads, waitForPhoto, CORS, performancecert.test.ts— Certificate generation, validation, SAN matching
Key Patterns
- MCP server uses stderr for terminal output (stdout is JSON-RPC)
waitForPhoto()in server.ts provides Promise-based listener for MCP tool blockingpendingPhotobuffer handles race condition where photo arrives before listener registers- Server starts lazily on first
capture_photocall, stays running for session - SSE endpoint (
/events) pushesphoto-requestedevents to connected phones get_latest_photoaccepts optionalfilenameparam to retrieve specific photos- Photos stored in
~/.ccphoto/captures/by default (or CCPHOTO_DIR env var) - Mobile page is a self-contained HTML string (no static files)
sendToPhone()broadcasts content-push SSE events for bidirectional messaging- Annotation canvas composites drawings onto photos client-side before upload
- HTTPS server (port+1) enables getUserMedia for live camera streaming
- Live frames stored in memory only (not disk) for ephemeral video streaming
- Voice input via Web Speech API (SpeechRecognition) on phone, sent as UserAction to server
- TTS via SpeechSynthesis when
send_to_phoneincludesspeak: true - Two-tier server: HTTP for photos (no cert warning), HTTPS for live/voice (getUserMedia needs secure context)
- Generative UI:
send_to_phonewithui_specrenders JSON-to-DOM components on phone (12 types)
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.
- 2mo ago First seen · 75 lines · 883 tokens per session scan A a6a70ae227cb
ccphoto CLAUDE.md is an instructions file published in the GitHub repository stepankaiser/ccphoto (2 stars, last pushed 7mo ago), licensed MIT. It adds 883 tokens to every session, about $0.0035 per session on Opus 5.5. 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
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).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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 copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.