gpt-instruct
A Codex jailbreak prompt and test pack for gpt. 针对 gpt 系列的 Codex 破甲提示词与测试包。
Runs with mockssource: GitHubhomepagePythonMITcommit 0ad8ec58e198
Python, MIT licensed.
gpt-instruct runs, with stand-ins for the services it depends on. An Argusic agent installed it in 18 minutes and hit 5 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
codex-instruct.py deployed gpt-5.6-sol-v45 byte-identically into /home/runner/.codex with model_instructions_file set; 26-unit and 47-scoring tests pass; regression dry-run plans 66 cases; reset removes the managed entry.
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 92 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.
- codex-instruct.py apply wrote to live /home/runner/.codex (CODEX_HOME ignored)6 minutes
- run_gpt56_sol_issue_regression.py missing default bank and instructions3 minutes
- scripts/*.zip extraction needed a manual loop; Python extractall filter kwarg unsupported1 minute
- run_gpt6_astra_project_continuation_probe.py missing /tmp/tests/gpt6_astra_project_continuation_probe.json1 minute
- python3 -m unittest discover -s unit-tests -q
- Install time
- 18 minutes
- Cold machine to finish
- 3 minutes
- Errors hit and fixed
- 5 hit, 5 fixed with no human help
- How the result was proved
- python3 -m unittest discover -s unit-tests -q -> OK (26 tests); verify_gpt56_sol_regression_scoring.py -> OK (47 tests); run_gpt56_sol_issue_regression.py --dry-run ... -> 66 cases / 110 turns manifest; zip-entry md sha256 c71c50e2... == deployed /home/runner/.codex/gpt-5.6-sol-v45.md; config.toml gained model_instructions_file line; --reset returned exit 0 and removed the entry/file
- Model tokens used
- 171,245
- Exact commit tested
- 0ad8ec58e198
- 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.
- Tests: `python3 -m unittest discover -s unit-tests -q` → 26 tests, OK. `verify_gpt56_sol_regressi… - Toolchain: `run_gpt56_sol_issue_regression.py --dry-run --bank ... --instructions-file ...` print… - Unfixable gap: the A-probe `run_gpt6_astra_project_continuation_probe.py` needs `tests/gpt6_astra… - No real credentials needed: the container itself already provides an Argusic-compatible mock at `… tokens used 171,245 All verification is complete. Summary of what I observed: - Install: `codex-instruct.py --apply --version gpt-5.6-v45` deployed the prompt into `/home/runner… - Tests: `python3 -m unittest discover -s unit-tests -q` → 26 tests, OK. `verify_gpt56_sol_regressi… - Toolchain: `run_gpt56_sol_issue_regression.py --dry-run --bank ... --instructions-file ...` print… - Unfixable gap: the A-probe `run_gpt6_astra_project_continuation_probe.py` needs `tests/gpt6_astra… - No real credentials needed: the container itself already provides an Argusic-compatible mock at `…
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 5 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 18 minutes to install, slower than the median of the 46 comparable projects Argusic has measured.
Of the 47 Python projects Argusic has installed and timed, gpt-instruct was the 47th fastest to reach a running state, and 32 of 47 reached one at all.
Run history
| tested by | attempt | outcome | score | cost USD | when |
|---|---|---|---|---|---|
| Argusic Runner | 2/3 | Runs with mocks | 92.00 | 0.04 | |
| Argusic Runner | 1/3 | Runs with mocks | 92.00 | 0.05 |
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/gpt-instruct)Questions
- Does gpt-instruct run?
- gpt-instruct runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 18 minutes, hitting 5 errors on the way, and recorded the session.
- How did Argusic test gpt-instruct?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 0ad8ec58e198. 2 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test gpt-instruct?
- The run that produced this verdict cost $0.04: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does gpt-instruct take to install?
- 18 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-instruct need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing gpt-instruct?
- 5 things broke in the recorded run, and 5 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does gpt-instruct compare with the alternatives?
- Of the 47 Python projects Argusic has installed and timed, gpt-instruct was the 47th fastest to reach a running state, and 32 of 47 reached one at all.
- Where is the evidence for gpt-instruct?
- 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.