armory

Curated, production-grade skills for AI coding agents. Battle-tested workflows for developers who use AI seriously.

Runssource: GitHubhomepagePythonMITcommit ca902da10b1e

Python, MIT licensed. The project labels itself: ai agents, claude code, coding agents, open source and skills.

armory runs. An Argusic agent installed it in 2 minutes and hit no errors on a clean machine with no GPU, and the whole session was recorded.

uv sync installs all dependencies, 369 repo-level and 348 package-level tests pass, all 145 packages install to ~/.claude/, eval validation and search scripts operate correctly, templates are in sync.

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
1
last tested
stars
343
forks
55
open issues
7
watchers
2
size
7 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
2 minutes
Cold machine to finish
3 minutes
Errors hit and fixed
0 hit, 0 fixed with no human help
How the result was proved
uv run python -m pytest tests/ -q exited 0, 369 passed; uv run python scripts/validate_evals.py exited 0, all 137 packages validated; uv run python -m pytest skills/concept-to-video/tests skills/decision-map/tests skills/opus-4-7-migration/tests skills/architecture-diagram/engine/tests -q exited 0, 348 passed
Model tokens used
96,532
Exact commit tested
ca902da10b1e
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.

- Installed `uv` via the official installer script
- Ran `uv sync` — 49 packages resolved and installed cleanly; no build errors
- Ran `scripts/install.py` with `all` selection — all 145 packages installed to `~/.claude/`
**Verification**
- 369 repo-level tests all passed (8.3s)
- 4 package-level test suites ran: `skills/concept-to-video` (93 passed), `skills/decision-map` (15…
- `scripts/validate_evals.py` passed: "Validated 84 skills, 17 agents, 9 hooks, 6 rules, 10 command…
- `scripts/search.py` successfully returns structured results
- `scripts/sync_templates.py` reports "All templates in sync"
- `scripts/model_fit.py` correctly fails because `claude` CLI is not installed (expected — Claude C…
**Errors encountered**: None. Everything worked on first attempt.
**Notable**: The `model_fit.py` dry-run needs `claude --version`, which requires Claude Code to be …

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 2 minutes, faster than the median of the 123 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.

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 124 ai-agents projects Argusic has installed and timed, armory was the 36th fastest to reach a running state, and 96 of 124 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 2 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 Runner1/3Runs100.000.01

Topics (from GitHub)

ai-agentsclaude-codecoding-agentsopen-sourceskills

Embed the badge

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

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

Questions

Does armory run?
Yes. armory runs. Argusic installed and launched it on a clean machine in 2 minutes, hitting 0 errors on the way, and recorded the session.
How did Argusic test armory?
On a fresh, disposable machine, with every command recorded and the repository pinned at commit ca902da10b1e. One attempt is recorded, and the full method is on the methodology page.
What did it cost to test armory?
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 armory take to install?
2 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 armory need a GPU?
Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing armory?
Nothing did, in the recorded run: zero errors between clone and running.
How does armory compare with the alternatives?
Of the 124 ai-agents projects Argusic has installed and timed, armory was the 36th fastest to reach a running state, and 96 of 124 reached one at all.
Where is the evidence for armory?
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.

Discussion