spellbook

Cross-runtime skills for Claude Code, Codex, and multi-agent workflows.

Runssource: GitHubhomepagePythonMITcommit 414b597ec113

Python, MIT licensed. The project labels itself: agent skills, ai agent skills, ai agents, ai coding assistant, automation, claude, claude code and claude code skills.

spellbook runs. An Argusic agent installed it in 35 minutes and hit 3 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.

109 installable skills validated with 0 errors, install.sh installs 110 skills to ~/.agents/skills for Codex, and the full 532-test suite passes.

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

At a glance

verdict
Runs
Argusic Score
60 / 100
cost of the verifying run
$0.24 (measured)
recorded runs
2
last tested
stars
300
forks
33
open issues
1
watchers
2
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 spellbook, 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.

  • install.sh had an inline Python parser that rejected upstream frontmatter format (compatibility string + metadata dict), plus banner count mismatch (112 vs 109)2 minutes
  • Missing PyYAML dependency: 7 tests failed to collect with ModuleNotFoundError for 'yaml'1 minute
  • Out-of-date generated registry files (skills.json, tags.json, skill-registry.md, skills.html) fail validation1 minute
Install time
35 minutes
Cold machine to finish
13 minutes
Errors hit and fixed
3 hit, 3 fixed with no human help
How the result was proved
python3 -m pytest tests/ -q returned '532 passed, 136 subtests passed in 12.80s' with 0 failures
Model tokens used
538,501
Exact commit tested
414b597ec113
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.

/bin/sh -lc 'cd /work/repo && python3 scripts/validate_skills.py --check 2>&1' in /work/repo
 succeeded in 549ms:
WARN: skills/threads/SKILL.md is 611 lines; consider progressive disclosure
Validated 109 installable skills: 0 errors, 1 warnings
 succeeded in 12834ms:
532 passed, 136 subtests passed in 12.86s
exec
/bin/sh -lc 'cd /work/repo && /tmp/spellbook_venv/bin/python -m pytest tests/ -q 2>&1 | tail -1' in…
 succeeded in 12783ms:
532 passed, 136 subtests passed in 12.80s
tokens used
538,501

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.
  • Recovered from all 3 errors 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.

What did not, or is not known

  • Took 35 minutes to install, slower than the median of the 127 comparable projects Argusic has measured.

Of the 128 agent-skills projects Argusic has installed and timed, spellbook was the 125th 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.

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 Runner2/3Runs100.000.24
Argusic Runner1/3Did not run20.000.19

Topics (from GitHub)

agent-skillsai-agent-skillsai-agentsai-coding-assistantautomationclaudeclaude-codeclaude-code-skillscode-reviewcodexcodex-skillscross-runtimedeveloper-toolsmulti-agentproductivityprompt-engineeringskill-librarysoftware-developmentspellbookworkflows

Embed the badge

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

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

Questions

Does spellbook run?
Yes. spellbook runs. Argusic installed and launched it on a clean machine in 35 minutes, hitting 3 errors on the way, and recorded the session.
How did Argusic test spellbook?
On a fresh, disposable machine, with every command recorded and the repository pinned at commit 414b597ec113. 2 attempts are recorded, and the full method is on the methodology page.
What did it cost to test spellbook?
The run that produced this verdict cost $0.24: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
How long does spellbook take to install?
35 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 spellbook need a GPU?
Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing spellbook?
3 things broke in the recorded run, and 3 were fixed without human help. Each one, and the time it cost, is listed on this page.
How does spellbook compare with the alternatives?
Of the 128 agent-skills projects Argusic has installed and timed, spellbook was the 125th fastest to reach a running state, and 96 of 128 reached one at all.
Where is the evidence for spellbook?
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