Backlog.md
Backlog.md - A tool for managing project collaboration between humans and AI Agents in a git ecosystem
Runssource: GitHubhomepageTypeScriptMITcommit c310b7087c3d
TypeScript, MIT licensed. The project labels itself: agent, agentic ai, management, markdown, project, task manager and tasks.
Backlog.md runs. An Argusic agent installed it in 25 minutes and hit 2 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
The backlog.md CLI installs, the repo builds, type-checks, lints, and passes the full CI test suite, and a fresh project initializes with task create/list/view/search/board plus a web server answering 200 on / and JSON on /api/tasks.
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.
- test 'preserves commit.gpgSign for selected-path auto-commits' failed: ssh-keygen binary missing in container (no root to install openssh-client)15 minutes
- npm global install EACCES on /usr/local/lib/node_modules (no root in container)2 minutes
- Install time
- 25 minutes
- Cold machine to finish
- 32 minutes
- Errors hit and fixed
- 2 hit, 2 fixed with no human help
- How the result was proved
- bun scripts/run-ci-tests.ts --profile=full ... --test-name-pattern=... exited 0 with 2583+313 pass, 8 skip, 0 fail across 290 files; build+typecheck+lint clean; browser GET / returned 200 and /api/tasks returned TASK-1 JSON
- Model tokens used
- 526,212
- Exact commit tested
- c310b7087c3d
- 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.
- Standard install path from the README: `npm i -g backlog.md` → failed with `EACCES` on `/usr/loca… - Repo bootstrap: installed the CI-pinned runtime `[email protected]` (user-prefix, no root available) and… - End-to-end launch: built CLI `init` on a fresh git repo, then `task create` (→ `TASK-1`), `task l… - Browser: `backlog browser --no-open` served `127.0.0.1`; `GET /` → `200`, `GET /api/tasks` return… **Errors met** 1. `npm i -g backlog.md` → `EACCES /usr/local/lib/node_modules` — fixed via user-level npm prefix. 2. Bad substitution in my own capture command (fixed by not relying on `$PIPESTATUS`). 3. `bun: command not found: xdg-open` when auto-opening the browser — fixed by `--no-open`; not a r… 4. The only failing test: `tui-task-composer.test.ts > preserves commit.gpgSign for selected-path a… **Test provenance** - Full CI-style run (`scripts/run-ci-tests.ts --profile=full`): parallel pass **2583 pass / 8 skip … - One additional quirk: the very first full run hit `error: disk full` inside a deliberate fault-in…
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 2 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.
- Measured 2 times, so the result is not a one-off.
What did not, or is not known
- Took 25 minutes to install, slower than the median of the 137 comparable projects Argusic has measured.
Of the 138 agent projects Argusic has installed and timed, Backlog.md was the 122nd fastest to reach a running state, and 92 of 138 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.
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)
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/backlog-md)Questions
- Does Backlog.md run?
- Yes. Backlog.md runs. Argusic installed and launched it on a clean machine in 25 minutes, hitting 2 errors on the way, and recorded the session.
- How did Argusic test Backlog.md?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit c310b7087c3d. 2 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test Backlog.md?
- The run that produced this verdict cost $0.16: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does Backlog.md take to install?
- 25 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 Backlog.md need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing Backlog.md?
- 2 things broke in the recorded run, and 2 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does Backlog.md compare with the alternatives?
- Of the 138 agent projects Argusic has installed and timed, Backlog.md was the 122nd fastest to reach a running state, and 92 of 138 reached one at all.
- Where is the evidence for Backlog.md?
- 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.