coco
Coco Super Intelligence: agent skills, slash commands and subagents for Claude Code, Cursor and Codex. One command installs them into the tool you already use.
Runssource: GitHubPythonApache-2.0commit 309d58d175bc
Python, Apache-2.0 licensed. The project labels itself: agent skills, agents md, ai, ai agents, claude code, codex, cursor and developer tools.
coco runs. An Argusic agent installed it in 1 minute and hit 1 error and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
Coco v1.10.0 installs cleanly: the npm CLI wrapper prints help, the generic adapter produces a complete 1648-line AGENTS.md with 191 listed skills and 342 generated SI commands, build-index generates all catalogs, and all 76 smoke tests pass.
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. 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.
- Missing Python module pyyaml1 minute
- Install time
- 1 minutes
- Cold machine to finish
- 6 minutes
- Errors hit and fixed
- 1 hit, 1 fixed with no human help
- How the result was proved
- npm test exited 0, python3 scripts/build-index.py regenerated all indexes, bash tests/smoke.sh 76/76 passed, python3 -m pytest on 8 test files all passed (38+5+13+183+6+... total 300+), real install --adapter generic produced 1648-line AGENTS.md with 191 skills, build-delivery-index.py ran on all 16 adapters
- Model tokens used
- 86,085
- Exact commit tested
- 309d58d175bc
- 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.
- `python3 -m pytest tests/test_learning_cli.py test_learning_detector.py test_learning_team_bridge… - `evals/paired.py --self-test` — 16/16 passed - `evals/skills/score.py --self-test` — PASS - `bash systems/m0/tests/m0-smoke.sh` — 27 passed, 0 failed - All `tests/check-*.sh` scripts that don't require `ssh-keygen` passed - `bash skills/arch-index/scripts/run_fixtures.sh` — all assertions passed - `bash skills/team-gate/scripts/run_fixtures.sh` — all gates passed - Real install (`--adapter generic`) into `/tmp/test-project` — generated 1648-line `AGENTS.md`, 19… - `git status` — clean tree, no modifications **Could not run (infrastructure gap):** - `tests/check-coco-gate.sh` requires `ssh-keygen`/`ssh-agent` (not available in container) - A few CI-only tests (`e2e-npx-install.sh`, `cursor-si-commands.sh`) require network access to npm…
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 1 minute, faster than the median of the 112 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 Apache-2.0, 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 113 agent-skills projects Argusic has installed and timed, coco was the 24th fastest to reach a running state, and 82 of 113 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)
agent-skillsagents-mdaiai-agentsclaude-codecodexcursordeveloper-toolsllm-toolsmcppm-toolsproduct-managementproductivityprompt-engineeringworkflow-automation
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/coco)Questions
- Does coco run?
- Yes. coco 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 coco?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 309d58d175bc. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test coco?
- The run that produced this verdict cost $0.12: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does coco 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 coco need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing coco?
- 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 coco compare with the alternatives?
- Of the 113 agent-skills projects Argusic has installed and timed, coco was the 24th fastest to reach a running state, and 82 of 113 reached one at all.
- Where is the evidence for coco?
- 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.