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/nnemirovsky/iwdp-mcp/claude-mdgit clone --depth 1 https://github.com/nnemirovsky/iwdp-mcpWhat 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 | $0.01855 | $0.01855 |
| Opus 5 | $0.00928 | $0.00928 |
| Sonnet 5 | $0.00371 | $0.00371 |
| Haiku 4.5 | $0.00186 | $0.00186 |
Grade A, and why
iwdp-mcp 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 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 — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Build & Dev Commands
go build ./... # Compile (quick check)
make build # Compile to bin/iwdp-mcp + bin/iwdp-cli
make install # Install both binaries via go install
make test # Run unit + smoke tests (go test ./... -v -count=1)
make test-e2e # Run e2e tests (boots iOS Sim + iwdp, tests ALL tools)
make test-coverage # Run tests with coverage → coverage.html
make sim-setup # Boot iOS Simulator + iwdp (prints IWDP_SIM_WS_URL)
make sim-teardown # Shut down simulator + iwdp
make fmt # gofumpt -w . (format all Go files)
make lint # golangci-lint run ./...
make tidy # go mod tidy
make clean # Remove bin/ and coverage files
Pre-commit
Before committing, always run make fmt and make lint and fix any issues.
How ios-webkit-debug-proxy Works
- Port 9221 — listing port:
http://localhost:9221/jsonreturns connected devices - Port 9222+ — each device gets an incremented port starting at 9222
http://localhost:9222/json→ pages for first devicehttp://localhost:9223/json→ pages for second device, etc.
- Each page has a
webSocketDebuggerUrlfor WebSocket connection - The WebSocket speaks WebKit Inspector Protocol
Target-Based Message Routing
iwdp uses Target routing — you cannot send domain commands directly on the WebSocket. On connect, iwdp sends a Target.targetCreated event with a targetId. All subsequent commands must be wrapped in Target.sendMessageToTarget:
Client → Target.sendMessageToTarget { targetId, message: JSON-stringified inner command }
iwdp → WebKit
WebKit → Target.dispatchMessageFromTarget { targetId, message: JSON-stringified response }
iwdp → Client
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 · 147 lines · 1,855 tokens per session scan A 228f5fc1e5f7
iwdp-mcp CLAUDE.md is an instructions file published in the GitHub repository nnemirovsky/iwdp-mcp (14 stars, last pushed 4mo ago), licensed MIT. It adds 1,855 tokens to every session, about $0.0093 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
cua AGENTS.md
Instructions for trycua/cua, covering repository agent guidance, contributor authorship, issue and pull request workflow, polling for work and cross-platform cua driver behavior.
claude-code-apple-skills CLAUDE.md
Instructions for rshankras/claude-code-apple-skills, covering claude.md, repository purpose, architecture, skill structure and yaml frontmatter (required).
the-unofficial-swift-programming-language-skill CLAUDE.md
Instructions for kylehughes/the-unofficial-swift-programming-language-skill, covering claude.md, repository purpose, build commands, generate the skill package and build options.
apple-dev-skills AGENTS.md
Instructions for markdavidgan/apple-dev-skills, covering apple dev skills — agent guide (codex / kimi / cross-cli), quick reference, repository rules, project-local consumer convention and checkpoint compaction protocol.
wwdc-sessions AGENTS.md
Instructions for guitaripod/wwdc-sessions, covering agent guide, layout, locating a session — do not derive paths from the id, recommended access patterns and apple documentation as markdown (sosumi).
claude-apple-bridges CLAUDE.md
Instructions for more-io/claude-apple-bridges, covering claude apple bridges — developer notes, compile all bridges, reminders, contacts and calendar.