facadecode
The multi-agent orchestrator for VS Code. Run Claude Code, Codex, and other agent CLIs that start, message, and operate each other across windows and machines.
Runs with mockssource: GitHubTypeScriptMITcommit d630a3dc904e
TypeScript, MIT licensed. The project labels itself: agent orchestration, agentic coding, ai agents, antigravity, claude code, claude code extension, codex and codex cli.
facadecode runs, with stand-ins for the services it depends on. An Argusic agent installed it in 3 minutes and hit 3 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
Extension compiles, bundles, packages into a VSIX, and passes nearly all unit tests (2 cleanup timeout failures). IDE cannot install dependencies due to missing system library (kerberos/gssapi) unavailable without root. All extension operations verified with Node 24.22.2 on Linux x64.
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. 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.
- npm test hangs on glob expansion; individual file runs succeed15 minutes
- npm run test for extension: 2 timeout failures in execution.test.js (1) and ptyd.test.js (1) - cleanup hooks timing out after successful test assertions3 minutes
- IDE npm install fails: kerberos native module requires gssapi/gssapi.h (libkrb5-dev system package), not installable without root3 minutes
- Install time
- 3 minutes
- Cold machine to finish
- 32 minutes
- Errors hit and fixed
- 3 hit, 3 fixed with no human help
- How the result was proved
- npm run compile succeeded; npm run bundle produced 6 bundles; npm run package produced facadecode-linux-x64-0.1.1.vsix (91 files, 745.93 KB); npm run test:package passed 12/12; mocha unit tests ran on 98 test files (~1,500+ passing, 87 pending, 2 timeout failures); node scripts/l10n.mjs check passed: 325+58 strings in 11 languages
- Model tokens used
- 468,647
- Exact commit tested
- d630a3dc904e
- 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.
1. **Extension build**: Fully successful - `npm ci` - success - `npm run compile` - success - `npm run bundle` - success - `npm run package` - success (created `facadecode-linux-x64-0.1.1.vsix`) - `npm run test:package` - 12/12 passing - `node scripts/l10n.mjs check` - success (325 runtime texts + 58 manifest strings complete in 1… 2. **Extension tests**: Ran all 98 test files - Total: approximately 1,500+ tests passing, ~87 pending, 2 failing (timeouts in `execution.test… 3. **IDE build**: Failed due to missing system dependency (`libkrb5-dev` / `gssapi.h`). This is a k… 4. **Third-party keys**: The extension tests require no third-party keys - they set up isolated tem… Let me format the final result.
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 3 minutes, faster than the median of the 18 comparable projects Argusic has measured.
- 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.
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Of the 19 agent-orchestration projects Argusic has installed and timed, facadecode was the 4th fastest to reach a running state, and 13 of 19 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 | 0.20 |
Topics (from GitHub)
agent-orchestrationagentic-codingai-agentsantigravityclaude-codeclaude-code-extensioncodexcodex-clicoding-agentsgit-worktreeidemcpmulti-agentmulti-agent-orchestrationmulti-agent-systemsopencoderemote-sshvscodevscode-extensionvscode-fork
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/facadecode)Questions
- Does facadecode run?
- facadecode runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 3 minutes, hitting 3 errors on the way, and recorded the session.
- How did Argusic test facadecode?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit d630a3dc904e. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test facadecode?
- The run that produced this verdict cost $0.20: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does facadecode take to install?
- 3 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 facadecode need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing facadecode?
- 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 facadecode compare with the alternatives?
- Of the 19 agent-orchestration projects Argusic has installed and timed, facadecode was the 4th fastest to reach a running state, and 13 of 19 reached one at all.
- Where is the evidence for facadecode?
- 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.