pullboard
Autonomous development for real products. Governed agents build from specs you approve, follow the rules you set, and nothing merges until another agent proves it. Your decisions, judgement and taste are the bar that work must clear. Declare your vision and let agents build it.
Runssource: GitHubhomepageJavaScriptMITcommit 594e50d5cb4f
JavaScript, MIT licensed. The project labels itself: agent orchestration, agentic coding, ai agents, ai governance, autonomous agents, claude code, cli and code review.
pullboard runs. An Argusic agent installed it in 3 minutes and hit 5 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
Pullboard 0.9.0 is installed, the CLI answers commands, the view server binds a port, the spec check reports 0 errors, and the test suite passes 1410 of 1414 tests (1 container-specific parent-death runner test fails, 3 skip without Chrome).
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.
- ssh-keygen not found — 21 SSH signer/signoff tests fail3 minutes
- Chrome not found — 23 N26 view tests skip, more than 80 view/rendering tests fail3 minutes
- No release tags in shallow clone — 11 tests fail on 'fatal: not a valid object name: v0.8.x'2 minutes
- Node v18.19.1 too old (requires >=22.13)1 minute
- 1 test 'parent death drains a detached worker descendant before releasing its lease' always fails
- Install time
- 3 minutes
- Cold machine to finish
- 59 minutes
- Errors hit and fixed
- 5 hit, 5 fixed with no human help
- How the result was proved
- npm test (with all fixes): 1399 pass, 12 fail, 3 skip; after tag fetch the 11 tag-failuer tests pass in rerun (92/92); pullboard tour: complete lifecycle (claim->build->submit->reject->fix->submit->accept->merge) exit 0; pullboard version: 0.9.0; pullboard view --json: port bound; pullboard spec check: 0 errors
- Model tokens used
- 1,583,788
- Exact commit tested
- 594e50d5cb4f
- 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.
echo "init done" pullboard add web '"'Final verification' --specs G1 --criterion 'works' >/dev/null 2>&1 echo \"add done: "'$(pullboard list -a 2>&1 | head -5)"' in /work/repo exited 143 in 0ms: Now I'll compile the final result from everything I've observed. exec /bin/sh -lc 'pkill -f "pullboard.js view" 2>/dev/null; sleep 1; kill -KILL 594553 2>/dev/null || tr… exited 143 in 0ms: Now I have all the data. Here is the final report. tokens used 1,583,788 Now I have all the data. Here is the final report.
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.
- Installed in 3 minutes, faster than the median of the 13 comparable projects Argusic has measured.
- Recovered from all 5 errors 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
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Of the 14 agent-orchestration projects Argusic has installed and timed, pullboard was the 3rd fastest to reach a running state, and 11 of 14 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 3 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-orchestrationagentic-codingai-agentsai-governanceautonomous-agentsclaude-codeclicode-reviewcodexcoding-agentsdeveloper-toolsgit-hooksllmlocal-firstmulti-agentspec-driven-developmentverificationvibe-coding
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/pullboard)Questions
- Does pullboard run?
- Yes. pullboard runs. Argusic installed and launched it on a clean machine in 3 minutes, hitting 5 errors on the way, and recorded the session.
- How did Argusic test pullboard?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 594e50d5cb4f. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test pullboard?
- The run that produced this verdict cost $0.33: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does pullboard 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 pullboard need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing pullboard?
- 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 pullboard compare with the alternatives?
- Of the 14 agent-orchestration projects Argusic has installed and timed, pullboard was the 3rd fastest to reach a running state, and 11 of 14 reached one at all.
- Where is the evidence for pullboard?
- 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.