Flowtrace
Run a task with AI as a flow of steps you keep, reuse, and refine, not a one-off chat.
Runssource: GitHubhomepageTypeScriptMITcommit 1571c76365c0
TypeScript, MIT licensed. The project labels itself: agent skills, agentic ai, ai, ai agent, ai agents, anthropic, claude and claude code.
Flowtrace runs. An Argusic agent installed it in 5 minutes and hit 1 error and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
flowtrace CLI builds, installs, passes all 49 tests, serves the web UI on port 3005, and manages traces (validate, lint, show, run lifecycle, step lifecycle, replies, deliverables) via its CLI and REST API.
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 100 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.
- Frontend build failed: @tailwindcss/oxide missing native binding on Node 18 (npm's optional dependencies bug)1 minute
- Install time
- 5 minutes
- Cold machine to finish
- 8 minutes
- Errors hit and fixed
- 1 hit, 1 fixed with no human help
- How the result was proved
- cargo test: 49/49 passed; flowtrace serve on port 3005 returned HTTP 200 and both traces in /api/traces JSON; flowtrace --version: 0.1.0
- Model tokens used
- 62,150
- Exact commit tested
- 1571c76365c0
- 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
The end of the recording
The last lines of the terminal session that decided this verdict, exactly as they were recorded.
- Built `nested-deps` reference trace (5-step diamond DAG, 38 git commits) - `flowtrace serve --port 3005 --scope ~/traces` → HTTP 200, `/api/traces` returned both traces wit… tokens used 62,150 All systems operational. Here's the summary: **Install**: Rust installed via rustup (1.99.1), frontend npm dependencies installed, `@tailwindcss… **Tests**: `cargo test` — 49/49 passed (19 in `flowtrace-cli`, 30 in `flowtrace-core`). **End-to-end verification**: - `flowtrace --version` → `flowtrace 0.1.0` - Built `minimal` reference trace: validated, linted, `show --fmt json|mermaid|dot`, `run new/renam… - Built `nested-deps` reference trace (5-step diamond DAG, 38 git commits) - `flowtrace serve --port 3005 --scope ~/traces` → HTTP 200, `/api/traces` returned both traces wit…
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
- Reached a running state on a clean machine, with the session recorded.
- Recovered from all 1 error without a human stepping in, which says the failures are documented well enough to solve.
- Ran without a GPU, so it does not need one to start.
- Licensed MIT, as reported by its host.
What did not, or is not known
- Took 5 minutes to install, slower than the median of the 127 comparable projects Argusic has measured.
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Of the 128 agent-skills projects Argusic has installed and timed, Flowtrace was the 86th fastest to reach a running state, and 96 of 128 reached one at all.
What it is a reasonable choice for
- Trying it on a laptop or a small server: it reached a running state without a GPU.
- A quick evaluation: it was running 5 minutes after the clone.
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
Topics (from GitHub)
agent-skillsagentic-aiaiai-agentai-agentsanthropicclaudeclaude-codeclaude-skillsclicodexcursordeveloper-toolsllm
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/flowtrace)Questions
- Does Flowtrace run?
- Yes. Flowtrace runs. Argusic installed and launched it on a clean machine in 5 minutes, hitting 1 error on the way, and recorded the session.
- How did Argusic test Flowtrace?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 1571c76365c0. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test Flowtrace?
- The run that produced this verdict cost $0.05: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does Flowtrace take to install?
- 5 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 Flowtrace need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing Flowtrace?
- 1 thing broke in the recorded run, and 1 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does Flowtrace compare with the alternatives?
- Of the 128 agent-skills projects Argusic has installed and timed, Flowtrace was the 86th fastest to reach a running state, and 96 of 128 reached one at all.
- Where is the evidence for Flowtrace?
- 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.