claude-tap
Intercept and inspect Coding Agent API traffic from Claude Code, Codex CLI, Gemini CLI, Cursor CLI, OpenCode, Kimi/Kimi Code, Pi, and Hermes in a local trace viewer.
Runssource: GitHubPythonMITcommit 4cc867d2e968
Python, MIT licensed. The project labels itself: agent debugging, agent observability, ai agents, ai tools, api debugging, claude code, codex and codex cli.
claude-tap runs. An Argusic agent installed it in 10 minutes and hit 2 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
Editable pip install succeeded, all 1136 tests pass, ruff lint and format are clean
What the agent ended up with on a clean machine, in its own words. How this is measured
Measured by Argusic on a fresh machine every time. Every number links to its evidence. Argusic Score 100 of 100 (the mean of this project's run scores).
At a glance
Subject data from GitHub, linked at the top of this page, refreshed . Test data by Argusic (CC BY 4.0); every number links to a run page with the full log, the recording, and their sha256 hashes.
What was measured
From the run that decided this verdict. Every line is a recorded value, not an estimate.
What went wrong, in the agent's own words
The agent's own words, worst first, never rewritten into advice.
- test_dsh_client_forward_proxy_captures_local_gateway failed: Node v18.19.1 does not support --use-env-proxy flag3 minutes
- test_openclaw_reverse_env_falls_back_without_patchable_config failed: OPENROUTER_API_KEY env var in container changed fallback provider detection2 minutes
- Install time
- 10 minutes
- Cold machine to finish
- 6 minutes
- Errors hit and fixed
- 2 hit, 2 fixed with no human help
- How the result was proved
- pytest tests/ -x --timeout=60 exited 0, 1136 passed, 159 skipped
- Model tokens used
- 86,493
- Exact commit tested
- 4cc867d2e968
- Container image
- sha256:cdd920bce783
What was not measured
The other half, so you can see exactly how far this evidence goes. A gap is printed as a gap and never filled in.
- Peak GPU memory
- this ran on a CPU machine, so there was no GPU to sample
- Behaviour over a long run
- each attempt uses the smallest documented settings and a fixed time budget, so this measures whether it runs, not how it holds up under load
The end of the recording
The last lines of the terminal session that decided this verdict, exactly as they were recorded.
succeeded in 0ms: All checks passed! All 1136 tests pass, ruff lint and format are clean. Let me summarize the result. **Errors encountered & fixed:** 1. **test_openclaw_reverse_env_falls_back_without_patchable_config** — The container environment ha… 2. **test_dsh_client_forward_proxy_captures_local_gateway** — The system Node v18.19.1 doesn't supp… tokens used 86,493 All 1136 tests pass, ruff lint and format are clean. Let me summarize the result. **Errors encountered & fixed:** 1. **test_openclaw_reverse_env_falls_back_without_patchable_config** — The container environment ha… 2. **test_dsh_client_forward_proxy_captures_local_gateway** — The system Node v18.19.1 doesn't supp…
Replay the whole session, every command from a clean machine to this point.
How it was tested
One agent, one container, no human help. It installs the project the way its own documentation says to, runs it, and fixes what breaks. Everything below is recorded as it happened: the terminal session, the log and the exact commit. The full method.
Strengths and limits
Measured facts, not opinions. How this is written.
What went well
- Reached a running state on a clean machine, with the session recorded.
- Installed in 10 minutes.
- Recovered from all 2 errors without a human stepping in, which says the failures are documented well enough to solve.
- Ran without a GPU, so it does not need one to start.
- Licensed MIT, as reported by its host.
What did not, or is not known
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
What it is a reasonable choice for
- Trying it on a laptop or a small server: it reached a running state without a GPU.
- A quick evaluation: it was running 10 minutes after the clone.
Also tested, in the same area
Every one of these was installed and run by Argusic on a clean machine. Nothing appears here that was not tested.
Run history
Topics (from GitHub)
agent-debuggingagent-observabilityai-agentsai-toolsapi-debuggingclaude-codecodexcodex-clicursor-clideveloper-toolsgemini-clihermes-agentkimillmllm-proxyopencodepi-coding-agentproxytracetrace-viewer
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/claude-tap)Questions
- Does claude-tap run?
- Yes. claude-tap runs. Argusic installed and launched it on a clean machine in 10 minutes, hitting 2 errors on the way, and recorded the session.
- How did Argusic test claude-tap?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 4cc867d2e968. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test claude-tap?
- The run that produced this verdict cost $0.05: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does claude-tap take to install?
- 10 minutes in the run that decided this verdict, from a clean machine to a running state. That is one measured attempt, not an average.
- Does claude-tap need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing claude-tap?
- 2 things broke in the recorded run, and 2 were fixed without human help. Each one, and the time it cost, is listed on this page.
- Where is the evidence for claude-tap?
- The recorded run is on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.