res
Agent skill to reverse engineer a SaaS product through the browser into a knowledge base for rebuilding it: screens, rules, data model, design tokens and production barriers, without touching production data.
Runs with mockssource: GitHubhomepageJavaScriptMITcommit 1d05d9c4a9f9
JavaScript, MIT licensed. The project labels itself: agent skills, ai agents, browser automation, claude code, knowledge base, reverse engineering and saas.
res runs, with stand-ins for the services it depends on. An Argusic agent installed it in 8 minutes and hit 3 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
All 32 automated tests pass under Node.js v22.14.0 and Playwright Chromium headless; all 4 CLI scripts exit 0 with correct usage and the end-to-end workflow (init, check, build-report, pack) produces valid output.
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.
- System Node.js is v18 but project requires >=22 (Playwright needs >=20)3 minutes
- Playwright browsers not installed (chromium was missing)3 minutes
- Node.js v22.0.0 has a test runner bug where before() hooks don't await async operations before tests2 minutes
- Install time
- 8 minutes
- Cold machine to finish
- 8 minutes
- Errors hit and fixed
- 3 hit, 3 fixed with no human help
- How the result was proved
- node --test tests/*.test.mjs with Node v22.14.0: 32 passed, 0 failed (26 kb-scripts + 6 page-scripts). CLI workflow: init-kb created 37 files, check-kb reported OK with warnings, build-report generated REPORT.html, pack-kb created handoff zip, all exited 0.
- Model tokens used
- 283,091
- Exact commit tested
- 1d05d9c4a9f9
- 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 is the **RES (Reverse Engineering SaaS)** repository — a collection of Node.js scripts … **What I observed:** 1. **Install (`npm install`)**: completed with only engine warnings (system Node is v18, project ne… 2. **Test suite (32 tests total)**: - `tests/kb-scripts.test.mjs`: **26/26 pass** — tests for `init-kb.mjs`, `check-kb.mjs`, `build-… - `tests/page-scripts.test.mjs`: **6/6 pass** — tests for Playwright page scripts (`inventory.js… 3. **CLI scripts**: All four scripts work end-to-end — `init-kb.mjs --help`, `check-kb.mjs --help`,… 4. **Errors found and fixed**: - **Node.js v18 is too old**: project requires >=22. Fix: downloaded v22.14.0 prebuilt binary. - **Playwright browsers not installed**: `npx playwright install chromium` via the new Node bina… - **Node.js v22.0.0 has a before-hook bug**: the test runner's `before` hook didn't await async … No third-party API keys were needed; all tests use mocked HTTP routes and a local fixture HTML file.
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 3 errors without a human stepping in, which says the failures are documented well enough to solve.
- Licensed MIT, as reported by its host.
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 8 minutes to install, slower than the median of the 99 comparable projects Argusic has measured.
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Of the 100 agent-skills projects Argusic has installed and timed, res was the 74th fastest to reach a running state, and 71 of 100 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 by | attempt | outcome | score | cost USD | when |
|---|---|---|---|---|---|
| Argusic Runner | 1/3 | Runs with mocks | 92.00 | 0.04 |
Topics (from GitHub)
agent-skillsai-agentsbrowser-automationclaude-codeknowledge-basereverse-engineeringsaas
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/res)Questions
- Does res run?
- res runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 8 minutes, hitting 3 errors on the way, and recorded the session.
- How did Argusic test res?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 1d05d9c4a9f9. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test res?
- 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 res take to install?
- 8 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 res need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing res?
- 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.
- How does res compare with the alternatives?
- Of the 100 agent-skills projects Argusic has installed and timed, res was the 74th fastest to reach a running state, and 71 of 100 reached one at all.
- Where is the evidence for res?
- 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.