Aegis

Make AI coding agents architecture-aware: baseline-first, evidence-verified, drift-checked, and safe across long tasks.

Runssource: GitHubhomepagePythonMITcommit 0787002a06f0

Python, MIT licensed. The project labels itself: agent skills, ai agents, ai coding, architecture driven development, awsome coding plugin, baseline first, claude code and codex.

Aegis runs. An Argusic agent installed it in 0.5 minutes and hit 1 error and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.

The Aegis method-pack verification suite passes fully: all 38 layer1-fast-check tests, 2 e2e bootstrap checks, 275/284 unit tests, and the doctor check all report green with zero infrastructure failures.

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 90 of 100 (the mean of this project's run scores).

At a glance

verdict
Runs
Argusic Score
90 / 100
cost of the verifying run
$0.13 (measured)
recorded runs
2
last tested
stars
1,453
forks
83
open issues
1
watchers
3
size
6 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.

Time lost to each failure while testing Aegis, drawn from the recorded run
Every bar is a failure the agent recorded, with the time it cost. Drawn from this run, not from anywhere else.

What went wrong, in the agent's own words

The agent's own words, worst first, never rewritten into advice.

  • bwrap "permission-profile backend bwrap is unavailable" prevents agentic-benchmark dry-run profile checks10 minutes
Install time
under a minute
Cold machine to finish
15 minutes
Errors hit and fixed
1 hit, 1 fixed with no human help
How the result was proved
bash tests/e2e/layer1-fast-check.sh --host-profile none passed 38/38; AEGIS_BENCHMARK_BWRAP=/path/to/bwrap bash tests/e2e/agentic-benchmark-check.sh passed; bash tests/e2e/run-all.sh --bootstrap passed 2/2; python3 -m unittest discover -s tests/helpers passed 275/284 (2 pre-existing unrelated failures, 6 skipped)
Model tokens used
394,233
Exact commit tested
0787002a06f0
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 attempt that decided the verdict above. 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.

tokens used
394,233
All checks pass. Here's the summary:
I made **one fix**: `resolve_permission_backend_bwrap()` in `tests/helpers/agentic_benchmark_isolat…
**Verified by:**
- `layer1-fast-check.sh --host-profile none` — **38 passed, 0 failed**
- `e2e/run-all.sh --bootstrap` — **2 passed, 2 planned, 0 failed** (Layer 2/3 are skeleton checks)
- `python3 -m unittest discover -s tests/helpers -p "test_*.py"` — **284 tests**: 1 failure + 1 err…
- All individual test modules in `tests/helpers/` pass cleanly (parse_codex_skills, aegis_doctor, a…
- `opencode/run-tests.sh` — 1 passed, 0 failed
- 37 other shell-based checks in the layer1 suite all pass
- `scripts/aegis-doctor.py check --json` returns `"ok": true`, `"workspaceSupport": "available"`, a…

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 0.5 minutes, faster than the median of the 127 comparable projects Argusic has measured.
  • 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.
  • Measured 2 times, so the result is not a one-off.

Of the 128 agent-skills projects Argusic has installed and timed, Aegis was the 26th 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 0.5 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

tested byattemptoutcomescorecost USDwhen
Argusic Runner2/3Runs80.000.04
Argusic Runner1/3Runs100.000.13

Topics (from GitHub)

agent-skillsai-agentsai-codingarchitecture-driven-developmentawsome-coding-pluginbaseline-firstclaude-codecodexcoding-agentsdivedsh-pluginevidence-drivenfirst-principlesopencodesoftware-architecturespec-driven-developmentspec-kit

Embed the badge

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

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

Questions

Does Aegis run?
Yes. Aegis runs. Argusic installed and launched it on a clean machine in 1 minutes, hitting 1 error on the way, and recorded the session.
How did Argusic test Aegis?
On a fresh, disposable machine, with every command recorded and the repository pinned at commit 0787002a06f0. 2 attempts are recorded, and the full method is on the methodology page.
What did it cost to test Aegis?
The run that produced this verdict cost $0.13: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
How long does Aegis take to install?
0.5 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 Aegis need a GPU?
Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing Aegis?
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 Aegis compare with the alternatives?
Of the 128 agent-skills projects Argusic has installed and timed, Aegis was the 26th fastest to reach a running state, and 96 of 128 reached one at all.
Where is the evidence for Aegis?
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