ECC
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
Runssource: GitHubhomepageJavaScriptMITcommit e482e579415f
JavaScript, MIT licensed. The project labels itself: ai agents, anthropic, claude, claude code, developer tools, llm, mcp and productivity.
ECC runs. An Argusic agent installed it in 1 minute and hit 2 errors on a clean machine with no GPU, and the whole session was recorded.
npm install completed, all 10 CI validators pass, 4876 of 4906 tests pass; the only fix applied was guarding plan.adapter access in codex-user-config.js and ownership-guard.js to prevent TypeError when tests call applyInstallPlan without an adapter field
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 85 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.
- 1 test failure in install-apply.test.js: isCodexUserConfig accessed plan.adapter.id when adapter was undefined5 minutes
- 30 pre-existing test failures across 8 test files not caused by our changes
- Install time
- 1 minutes
- Cold machine to finish
- 42 minutes
- Errors hit and fixed
- 2 hit, 1 fixed with no human help
- How the result was proved
- npm install exited 0; all 10 CI validators passed (unicode-safety, agents, commands, rules, skills, hooks, schema-keys, install-manifests, personal-paths, catalog, command-registry); test suite ran via node tests/run-all.js: 4876 passed, 30 failed (all 30 pre-existing failures: plan-canvas-e2e needs browser, scope-migration/setup have CLI-arg mismatches, codex-hooks needs pytest, ecc-universal-bin needs npm cache, control-pane regex mismatch, npm-publish-surface pack-includes README.md, plugin-install expects missing ajv)
- Model tokens used
- 579,956
- Exact commit tested
- e482e579415f
- 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.
? readInstallState(plan.installStatePath)
: null;
- if (previousState && (
+ if (previousState && plan.adapter && (
previousState.target.id !== plan.adapter.id
|| comparablePath(previousState.target.root) !== comparablePath(plan.targetRoot)
|| comparablePath(previousState.target.installStatePath) !== comparablePath(plan.installStateP…
Final test count: 4876/4906 passed (30 pre-existing failures)
Install validation: npm install OK, all CI validators OK
Patch: Fixed 1 test failure in scripts/install-apply.test.js by guarding plan.adapter access
tokens used
579,956Replay 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 1 minute, faster than the median of the 116 comparable projects Argusic has measured.
- 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
- Hit 2 errors during setup, 1 of which were not solved.
Of the 117 ai-agents projects Argusic has installed and timed, ECC was the 19th fastest to reach a running state, and 87 of 117 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 1 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)
ai-agentsanthropicclaudeclaude-codedeveloper-toolsllmmcpproductivity
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/ecc)Questions
- Does ECC run?
- Yes. ECC runs. Argusic installed and launched it on a clean machine in 1 minutes, hitting 2 errors on the way, and recorded the session.
- How did Argusic test ECC?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit e482e579415f. 2 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test ECC?
- 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 ECC take to install?
- 1 minute in the run that decided this verdict, from a clean machine to a running state. That is one measured attempt, not an average.
- Does ECC need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing ECC?
- 2 things 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 ECC compare with the alternatives?
- Of the 117 ai-agents projects Argusic has installed and timed, ECC was the 19th fastest to reach a running state, and 87 of 117 reached one at all.
- Where is the evidence for ECC?
- 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.