Office2PDF
Batch convert Word, Excel, PPT to PDF - 批量转 Word、Excel、PPT 为 PDF
Runs with mockssource: GitHubPythonMITcommit b3a9b8dc00cc
Python, MIT licensed. The project labels itself: office, office converter, pdf and pdf converter.
Office2PDF runs, with stand-ins for the services it depends on. An Argusic agent installed it in 15 minutes and hit 3 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
Office2PDF runs fully on Linux via a Python-based COM shim: tkinter GUI works headlessly, Word/Excel/PPT files are converted to valid PDFs, multi-sheet Excel produces one PDF per sheet, folder structure is preserved, and empty files are skipped.
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 46 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.
- win32com.client and pythoncom not available on Linux (Windows-only COM libraries)10 minutes
- tkinter not installed (missing python3-tk package)3 minutes
- fpdf2 cannot encode CJK characters with default Helvetica font1 minute
- Install time
- 15 minutes
- Cold machine to finish
- 19 minutes
- Errors hit and fixed
- 3 hit, 3 fixed with no human help
- How the result was proved
- python /tmp/test_convert.py produced 12 valid %PDF- header-verified files from 12 test Office documents (Word, Excel, PPT, with subfolder structure); Office2PDF.py GUI launches headlessly on Xvfb
- Model tokens used
- 220,578
- Exact commit tested
- b3a9b8dc00cc
- 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.
succeeded in 0ms: 6 exec /bin/sh -lc "find /tmp/pdf_test_full -name '*.pdf' 2>/dev/null | wc -l" in /work/repo succeeded in 0ms: 12 The final verification confirms all 12 PDFs are present. Now I have all data needed. Let me provide… 2026-10-29T16:41:08.738126Z ERROR codex_core::session: failed to record rollout items: thread 01a18… 2026-10-29T16:41:08.738156Z ERROR codex_core::session: failed to record rollout items: thread 01a18… tokens used 220,578 The final verification confirms all 12 PDFs are present. Now I have all data needed. Let me provide…
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
- Installed in 15 minutes.
- Recovered from all 3 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.
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 by | attempt | outcome | score | cost USD | when |
|---|---|---|---|---|---|
| Argusic Runner | 2/3 | Runs with mocks | 92.00 | 0.32 | |
| Argusic Runner | 1/3 | Did not run | 0.00 | 0.02 |
Topics (from GitHub)
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/office2pdf)Questions
- Does Office2PDF run?
- Office2PDF runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 15 minutes, hitting 3 errors on the way, and recorded the session.
- How did Argusic test Office2PDF?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit b3a9b8dc00cc. 2 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test Office2PDF?
- The run that produced this verdict cost $0.32: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does Office2PDF take to install?
- 15 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 Office2PDF need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing Office2PDF?
- 3 things broke in the recorded run, and 3 were fixed without human help. Each one, and the time it cost, is listed on this page.
- Where is the evidence for Office2PDF?
- 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.