claude-tap is a local proxy and trace viewer for AI coding agents, recording and displaying their API requests, prompts, tool calls, responses, context, and token usage. It helps developers inspect and compare agent runs from tools such as Claude Code, Codex CLI, Gemini CLI, Cursor CLI, and others, while the catalogue skills and instruction support work with the project.
Borrowing it
Nothing to install: this file belongs to liaohch3/claude-tap. 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/liaohch3/claude-tap/main/.agents/skills/real-e2e-test/SKILL.mdgit clone --depth 1 https://github.com/liaohch3/claude-tapWrote 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/liaohch3/claude-tap/real-e2e-test)<a href="https://agentmods.dev/skills/liaohch3/claude-tap/real-e2e-test"><img src="https://agentmods.dev/badge/skills/liaohch3/claude-tap/real-e2e-test.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00021 | $0.00736 |
| Opus 5 | $0.00010 | $0.00368 |
| Sonnet 5 | $0.00004 | $0.00147 |
| Haiku 4.5 | $0.00002 | $0.00074 |
Grade A, and why
real-e2e-test 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 8d 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Real E2E Test Skill
Run real end-to-end tests that start claude-tap from local source, connect to the
real Claude CLI, and verify trace output.
Prerequisites
claudeCLI installed and authenticated- Python dev dependencies installed:
uv sync --extra dev tmuxinstalled for interactive mode (brew install tmux)
Mode 1: Pytest Real E2E (7 test cases)
Run all real E2E tests
uv run pytest tests/e2e/ --run-real-e2e --timeout=300 -v
Run a single test
uv run pytest tests/e2e/test_real_proxy.py::TestRealProxy::test_single_turn --run-real-e2e --timeout=180 -v -s
Run with debug output
uv run pytest tests/e2e/ --run-real-e2e --timeout=300 -v -s --tb=long
Mode 2: tmux Interactive Real E2E
Use this when you need to validate non--p interactive behavior in Claude Code TUI.
scripts/run_real_e2e_tmux.sh
Optional overrides:
PROMPT_ONE="Use the shell tool to run command ls in the current directory, then reply with any 5 filenames only." \
PROMPT_TWO="Thank you." \
SUBMIT_KEY="Enter" \
PERMISSION_MODE="bypassPermissions" \
scripts/run_real_e2e_tmux.sh
Important tmux interaction notes:
- Submit key is
Enterfor Claude Code TUI in tmux (confirmed working). PROMPT_ONEshould intentionally trigger tool use.- For portability, use
grep -Finstead ofrgin shell assertions (rgmay be unavailable).
Verification Checklist (for both modes)
- Latest trace
.jsonlcontains both prompts (PROMPT_ONE,PROMPT_TWO) - At least 2 requests hit
/v1/messages - At least one response content block has
"type": "tool_use" - HTML viewer file is generated (
trace_*.html)
Notes
- Real E2E tests are skipped by default;
--run-real-e2eis required. - Each pytest case starts a fresh proxy server and trace directory.
- Timeouts are intentionally generous because real API calls are involved.
- tmux mode includes retry logic for prompt submission and post-run JSONL assertions.
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.
- 8d ago First seen · 84 lines · 21 tokens per session scan A 9fec704a2ff1
real-e2e-test is a skill published in the GitHub repository liaohch3/claude-tap (3,177 stars, last pushed 12d ago), licensed MIT. It adds 21 tokens to every session and 736 once invoked, about $0.0001 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 skills, from other repositories
prodtest
Senior-QA test pass on a newly implemented feature. Detects the project's real test stack, writes unit and functional/integration tests, then drives the running app with Playwright for end-to-end coverage, saving screenshots to a gitignored folder for human review. Asks upfront whether found bugs should be fixed or…
atf-testing
Build ServiceNow Automated Test Framework tests and suites — impersonation, form steps, assertions, server-side script steps, test parameters, and execution via snowcreateatftest / snowexecuteatftest.
lamina-verify
Verify graph-backed product Missions after ordinary implementation work or when explicitly invoked as lamina-verify. Run isolated Persona and live UI audits; explicit verification is source-read-only.
recipe-eval-prompt
Compares original and optimized prompts through repeated blind paired execution in git worktrees. Use when evaluating prompt improvement effects or learning prompt engineering through concrete examples.
acceptance
A skill for writing, running, and repairing human-written acceptance checks stored in an `acceptance/ACCEPTANCE.md` file. Acceptance checks are executable tests of whether the finished result matches the requested outcome.
rpi-explore-release
Run independent fresh-context exploratory charters against a fixed authorized release candidate, preserving the eight-maneuver safety and evidence contract.