agent-spec

`agent-spec` is an AI-native BDD/spec verification tool for task execution.

Runssource: GitHubhomepageRustMITcommit 2483398da89b

Rust, MIT licensed. The project labels itself: agent, ai coding, sdd and spec.

agent-spec runs. An Argusic agent installed it in 0.7 minutes and hit no errors on a clean machine with no GPU, and the whole session was recorded.

agent-spec 1.4.0 builds and all 1111 tests pass on Rust 1.98.1 with no modifications.

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

verdict
Runs
Argusic Score
100 / 100
cost of the verifying run
$0.01 (measured)
recorded runs
2
last tested
stars
456
forks
35
open issues
8
watchers
2
size
4 MB
created
last push

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.

Install time
under a minute
Cold machine to finish
3 minutes
Errors hit and fixed
0 hit, 0 fixed with no human help
How the result was proved
cargo test returned 1111 passed, 0 failed (871+1+13+226, doc-tests 0), and agent-spec --version returned 1.4.0
Model tokens used
35,219
Exact commit tested
2483398da89b
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

Watch the session

The whole run, from a clean machine, at the speed it actually happened. Nothing is cut and nothing is sped up.

A recording of attempt 1, run . The verdict above comes from a different attempt, so read this as one session and not as the current result. The terminal recording it was made from is the evidence, stored with a sha256 fingerprint; the video is a rendering of it. Nothing loads from the video host until you press play.

The end of the recording

The last lines of the terminal session that decided this verdict, exactly as they were recorded.

- CLI surface: `atlas build [--full] [--scip <index>]`, `atlas tree`, `atlas query <symbol>`, `atla…
- MCP tools added to the existing server: `atlas_tree`, `atlas_query`, `atlas_refs`, `atlas_impls`,…
Everything works. Let me compile the final result.
**Install:** Rust wasn't present — installed via `rustup` (8.9s). Then `cargo build` succeeded in 3…
**Verified how:** Ran the full test suite (`cargo test`). All 1111 tests across the workspace passe…
**No errors encountered** — the project compiled and tested cleanly on first try after installing R…
tokens used
35,219
Everything works. Let me compile the final result.
**Install:** Rust wasn't present — installed via `rustup` (8.9s). Then `cargo build` succeeded in 3…
**Verified how:** Ran the full test suite (`cargo test`). All 1111 tests across the workspace passe…
**No errors encountered** — the project compiled and tested cleanly on first try after installing R…

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 0.7 minutes, faster than the median of the 32 comparable projects Argusic has measured.
  • Nothing broke on the way: zero errors between clone and running.
  • 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.

Of the 33 agent projects Argusic has installed and timed, agent-spec was the 4th fastest to reach a running state, and 25 of 33 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 0.7 minutes after the clone.
  • Following its own README: the documented path worked with nothing to fix.

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 byattemptoutcomescorecost USDwhen
Argusic Runner2/3Runs100.000.01
Argusic Runner1/3Runs100.000.02

Topics (from GitHub)

agentai-codingsddspec

Embed the badge

Markdown for the project README. It links back here; terms on the terms page.

[![Tested by Argusic](https://argusic.com/badge/agent-spec.svg)](https://argusic.com/subject/agent-spec)

Questions

Does agent-spec run?
Yes. agent-spec runs. Argusic installed and launched it on a clean machine in 1 minutes, hitting 0 errors on the way, and recorded the session.
How did Argusic test agent-spec?
On a fresh, disposable machine, with every command recorded and the repository pinned at commit 2483398da89b. 2 attempts are recorded, and the full method is on the methodology page.
What did it cost to test agent-spec?
The run that produced this verdict cost $0.01: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
How long does agent-spec take to install?
0.7 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 agent-spec need a GPU?
Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing agent-spec?
Nothing did, in the recorded run: zero errors between clone and running.
How does agent-spec compare with the alternatives?
Of the 33 agent projects Argusic has installed and timed, agent-spec was the 4th fastest to reach a running state, and 25 of 33 reached one at all.
Where is the evidence for agent-spec?
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.

Discussion