gpt-promo-scanner

ChatGPT Team(Business) 促销码自动扫描工具, 批量发现/验证/价格收集,支持 17 国 34 个码,最高折扣 71% | ChatGPT Business promo code scanner, batch discovery, validation, price collection, 34 codes across 17 countries, up to 71% off

Runs with mockssource: GitHubPythonMITcommit be528fef2d59

Python, MIT licensed. The project labels itself: chatgpt, chatgpt business, chatgpt team, clash, cloudflare bypass, curl cffi, discount and openai.

gpt-promo-scanner runs, with stand-ins for the services it depends on. An Argusic agent installed it in 43 minutes and hit 2 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.

Repo installs cleanly and every scanning script (auto_scan, discover_codes, verify, open_stripe, partner_scan, and the us/mega/uk scanners) ran and produced valid output against the local mock of the ChatGPT API and Clash proxy; open_stripe.py works after switching its hardcoded proxy to the project config-driven proxy.

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 56 of 100 (the mean of this project's run scores).

At a glance

verdict
Runs with mocks
Argusic Score
56 / 100
cost of the verifying run
$0.89 (measured)
recorded runs
2
last tested
stars
948
forks
169
open issues
7
watchers
1
size
0 MB
created
last push

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.

Time lost to each failure while testing gpt-promo-scanner, drawn from the recorded run
Every bar is a failure the agent recorded, with the time it cost. Drawn from this run, not from anywhere else.

What went wrong, in the agent's own words

The agent's own words, worst first, never rewritten into advice.

  • open_stripe.py hardcoded proxy http://127.0.0.1:7890 (closed in container) instead of using config/env proxy, always failing with curl(7) connect error15 minutes
  • Project requires a ChatGPT accessToken and a Clash proxy; none exist in the container, so real chatgpt.com calls return 40315 minutes
Install time
43 minutes
Cold machine to finish
43 minutes
Errors hit and fixed
2 hit, 2 fixed with no human help
How the result was proved
.venv/bin/python discover_codes.py --cross exited 0 (490 tested, 11 ELIGIBLE, 15 EXISTS, 0 errors); .venv/bin/python auto_scan.py exited 0 (11 working codes, scan_results.json and stripe_urls.txt written); .venv/bin/python open_stripe.py thealloynetwork US eyJmock123 exited 0 and printed https://checkout.stripe.com/c/pay/cs_test_mock123
Model tokens used
4,194,736
Exact commit tested
be528fef2d59
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
Behaviour against real services
this run was verified against stand-in services only

The end of the recording

The last lines of the terminal session that decided this verdict, exactly as they were recorded.

- The project builds and runs: `pip install -r requirements.txt` succeeded inside `.venv` (Python 3…
- Because the real Argusic API requires a ChatGPT accessToken plus a Clash proxy, I stood up a sche…
- Results observed: `discover_codes.py --cross` → exit 0, 490 tested, 11 ELIGIBLE / 15 EXISTS / 0 e…
- One real defect found and fixed (only code change in the tree): `open_stripe.py` hardcoded its pr…
tokens used
4,194,736
Approximately 43 minutes elapsed, well within the 90-minute limit.
**Final report**
- The project builds and runs: `pip install -r requirements.txt` succeeded inside `.venv` (Python 3…
- Because the real Argusic API requires a ChatGPT accessToken plus a Clash proxy, I stood up a sche…
- Results observed: `discover_codes.py --cross` → exit 0, 490 tested, 11 ELIGIBLE / 15 EXISTS / 0 e…
- One real defect found and fixed (only code change in the tree): `open_stripe.py` hardcoded its pr…

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

  • Recovered from all 2 errors without a human stepping in, which says the failures are documented well enough to solve.
  • Licensed MIT, as reported by its host.
  • Measured 2 times, so the result is not a one-off.

What did not, or is not known

  • Only reached a running state against stand-in services, so nothing here proves it works against the real ones.
  • Took 43 minutes to install, slower than the median of the 4 comparable projects Argusic has measured.

Of the 5 chatgpt projects Argusic has installed and timed, gpt-promo-scanner was the 5th fastest to reach a running state, and 3 of 5 reached one at all.

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

tested byattemptoutcomescorecost USDwhen
Argusic Runner2/3Did not run20.000.07
Argusic Runner1/3Runs with mocks92.000.89

Topics (from GitHub)

chatgptchatgpt-businesschatgpt-teamclashcloudflare-bypasscurl-cffidiscountopenaipromo-codepromo-codesproxypythonstripeweb-scraping

Embed the badge

Markdown for the project README. It links back here; terms on the terms page.

[![Tested by Argusic](https://argusic.com/badge/gpt-promo-scanner.svg)](https://argusic.com/subject/gpt-promo-scanner)

Questions

Does gpt-promo-scanner run?
gpt-promo-scanner runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 43 minutes, hitting 2 errors on the way, and recorded the session.
How did Argusic test gpt-promo-scanner?
On a fresh, disposable machine, with every command recorded and the repository pinned at commit be528fef2d59. 2 attempts are recorded, and the full method is on the methodology page.
What did it cost to test gpt-promo-scanner?
The run that produced this verdict cost $0.89: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
How long does gpt-promo-scanner take to install?
43 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 gpt-promo-scanner need a GPU?
Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing gpt-promo-scanner?
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.
How does gpt-promo-scanner compare with the alternatives?
Of the 5 chatgpt projects Argusic has installed and timed, gpt-promo-scanner was the 5th fastest to reach a running state, and 3 of 5 reached one at all.
Where is the evidence for gpt-promo-scanner?
All 2 recorded runs are on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.

Discussion