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 skills add Ling-ye/cc-port --skill cc-port-live-e2egit clone --depth 1 https://github.com/Ling-ye/cc-portWrote 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/skills/ling-ye/cc-port/cc-port-live-e2e)<a href="https://agentmods.dev/skills/ling-ye/cc-port/cc-port-live-e2e"><img src="https://agentmods.dev/badge/skills/ling-ye/cc-port/cc-port-live-e2e/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/skills/ling-ye/cc-port/cc-port-live-e2e"><img src="https://agentmods.dev/badge/skills/ling-ye/cc-port/cc-port-live-e2e.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 | $0.00136 | $0.01564 |
| Opus 5 | $0.00068 | $0.00782 |
| Sonnet 5 | $0.00027 | $0.00313 |
| Haiku 4.5 | $0.00014 | $0.00156 |
Grade A, and why
cc-port-live-e2e 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 11d 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 — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CC Port live remote E2E
Validate a built Windows installer through the real desktop, packaged sidecar, packaged
cc-port.exe mcp --stdio, Windows Git Credential Manager, a newly created private GitHub
repository, and exact desktop approvals. Keep test authority, product writes, independent Git
verification, and cleanup evidence separate.
Load the required references
- Read references/workflow.md completely before starting any live run.
- Read references/commands.md after preflight to map the generated values into the native Windows phase commands.
- Read references/evidence-contract.md before defining success or reporting PASS.
- Read references/remaining-scope.md when the request includes all resource kinds, batch/conflict recovery, Windows links, WSL profiles, or failure injection.
- Read references/package-provenance.md when the existing installer does not have clean current-commit provenance or needs a fresh actual-install smoke.
- Read references/recovery.md only when a phase fails, a plan becomes stale, credentials fail, or cleanup is incomplete.
Enforce the authority gate
Treat a normal request to test, package, review, or diagnose as read-only. Create a repository, push, approve, or apply only when the user explicitly authorizes all of the following for this run:
- use the user's current GitHub account;
- create one uniquely named private test repository;
- perform real remote writes;
- control the running CC Port desktop to approve the exact displayed requests.
Without that authority, stop after read-only preflight or plan generation. Conversation text,
--yes, a model boolean, or direct state-file edits never replace desktop approval. Repository
deletion requires separate explicit authority; retain the test repository by default.
Preserve isolation and Git boundaries
What ships with it
16 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- agents/openai.yaml 275 B
- references/commands.md 5.7 KB
- references/evidence-contract.md 5.1 KB
- references/package-provenance.md 3.5 KB
- references/recovery.md 3.3 KB
- references/remaining-scope.md 6.7 KB
- references/workflow.md 7.2 KB
- scripts/create_private_repo.ps1 5.0 KB runs code
- scripts/mcp_roundtrip.py 18 KB runs code
- scripts/preflight.py 7.3 KB runs code
- scripts/session.ps1 12 KB runs code
- scripts/test_real_claude_marketplace.py 10 KB runs code
- scripts/test_remaining_scope_live.py 19 KB runs code
- scripts/ui_driver.mjs 11 KB runs code
- scripts/validate_evidence.py 22 KB runs code
- scripts/verify_remote.ps1 5.4 KB runs code
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.
- 11d ago First seen · 116 lines · 136 tokens per session scan A d131b171eb12
cc-port-live-e2e is a skill published in the GitHub repository Ling-ye/cc-port (10 stars, last pushed today), licensed MIT. It adds 136 tokens to every session and 1,564 once invoked, about $0.0007 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 skills, from other repositories
browser-playwright-check
Use when an agent needs to operate or verify a web page with Playwright, including screenshots, viewport checks, navigation, forms, clicks, canvas visibility, responsive layout, or local Panel/browser behavior.
screen-reader-testing
Test web applications with screen readers including VoiceOver, NVDA, and JAWS. Use when validating screen reader compatibility, debugging accessibility issues, or ensuring assistive technology support.
e2e-testing-patterns
Master end-to-end testing with Playwright and Cypress to build reliable test suites that catch bugs, improve confidence, and enable fast deployment. Use when implementing E2E tests, debugging flaky tests, or establishing testing standards.
browser-testing-with-devtools
Tests in real browsers via Chrome DevTools MCP. Use when building or debugging anything that runs in a browser. Use when you need to inspect the DOM, capture console errors, analyze network requests, profile performance, or verify visual output with real runtime data. Requires the chrome-devtools MCP server to be…
designing-tests
Designs and implements testing strategies for any codebase. Use when adding tests, improving coverage, setting up testing infrastructure, debugging test failures, or when asked about unit tests, integration tests, or E2E testing.
qa/e2e-playwright
A method for writing Playwright end-to-end tests, which automate a browser to verify complete user journeys. It covers setup, reusable page objects, login reuse, API mocking, visual checks, multiple browsers and screen sizes, CI, and debugging.