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/codex-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/codex-e2e-test)<a href="https://agentmods.dev/skills/liaohch3/claude-tap/codex-e2e-test"><img src="https://agentmods.dev/badge/skills/liaohch3/claude-tap/codex-e2e-test/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/liaohch3/claude-tap/codex-e2e-test"><img src="https://agentmods.dev/badge/skills/liaohch3/claude-tap/codex-e2e-test.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Excessive Agency · line 27 Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
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 | $0.00042 | $0.03071 |
| Opus 5.5 | $0.00017 | $0.01228 |
| Sonnet 5.5 | $0.00008 | $0.00614 |
| Haiku 4.5 | $0.00004 | $0.00307 |
Grade A, and why
codex-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 1mo 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 — 313 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codex E2E Test Skill
Run real end-to-end validation that starts claude-tap from local source,
connects to the real Codex CLI via OAuth, captures OpenAI Responses API traces,
and produces viewer screenshots suitable for PR evidence.
Use this skill for every PR that changes capture, proxying, viewer rendering, session/dashboard behavior, client launch logic, trace ordering, content blocks, tools, token usage, or screenshot/demo assets. If a PR cannot run this flow, state why in the PR and cover the same risk with another real client trace.
Prerequisites
codexCLI installed (npm install -g @openai/codex) and authenticated via OAuth- Python dev dependencies:
uv sync --extra dev - Playwright installed:
uv run playwright install chromium
Verify OAuth works:
codex exec "say hello" --dangerously-bypass-approvals-and-sandbox
If it fails with token errors, re-authenticate:
codex auth login
Key Difference from Claude E2E
Codex uses the OpenAI Responses API (/v1/responses) instead of Anthropic Messages API.
With OAuth authentication, the upstream is https://chatgpt.com/backend-api/codex,
not https://api.openai.com.
The proxy must be told the correct target with --tap-target.
Run a Real Codex E2E Trace
Prefer the resume + multimodal flow below for PR evidence. The simple commands are only smoke tests for checking local setup.
Simple (single tool call)
claude-tap --tap-client codex \
--tap-target https://chatgpt.com/backend-api/codex \
--tap-output-dir /tmp/codex-e2e \
--tap-no-open \
-- exec "say hello" \
--dangerously-bypass-approvals-and-sandbox
Multi-call (triggers multiple API requests)
Use a task that requires shell tool use — this forces the agent to make multiple Responses API calls (models lookup + actual responses):
claude-tap --tap-client codex \
--tap-target https://chatgpt.com/backend-api/codex \
--tap-output-dir /tmp/codex-e2e \
--tap-no-open \
-- exec "Read pyproject.toml and tell me the project name and version" \
--dangerously-bypass-approvals-and-sandbox
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.
- 1mo ago First seen · 313 lines · 42 tokens per session scan A 605bc9665cc9
codex-e2e-test is a skill published in the GitHub repository liaohch3/claude-tap (3,311 stars, last pushed today), licensed MIT. It adds 42 tokens to every session and 3,071 once invoked, about $0.0002 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 2026-08-30.
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…
behavioral-a11y
Load this skill when writing, reviewing, or interpreting behavioral accessibility automation — tests that manipulate a rendered page (resizing the viewport, pressing real keys, capturing and comparing screenshots) rather than only inspecting static markup or a single computed accessibility tree. Covers Reflow risk (SC…
axe-rules
Load this skill when configuring axe-core scans, reviewing automated accessibility test results, or writing tests that use @axe-core/playwright, @axe-core/react, or similar integrations. Provides a quick reference to axe 4.x rule IDs, their WCAG mapping, and default severity levels.
cli-audit
Audit live URLs using Playwright and Axe combined with WCAG skills.
test-e2e
Generates end-to-end tests for a user flow using Playwright or Cypress.
qa
QA Specialist Agent for smoke testing production deployments. Runs Playwright-based smoke tests against live URLs to verify health, auth flows, protected routes, and core UI. Use when validating a deploy, checking if a production app is working, or when asked to run QA on a project.