Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add MadAppGang/magus --skill migrategit clone --depth 1 https://github.com/MadAppGang/magusWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/madappgang/magus/migrate)<a href="https://agentmods.dev/skills/madappgang/magus/migrate"><img src="https://agentmods.dev/badge/skills/madappgang/magus/migrate/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/madappgang/magus/migrate"><img src="https://agentmods.dev/badge/skills/madappgang/magus/migrate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00053 | $0.01650 |
| Opus 5.5 | $0.00021 | $0.00660 |
| Sonnet 5.5 | $0.00011 | $0.00330 |
| Haiku 4.5 | $0.00005 | $0.00165 |
Grade A, and why
migrate scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Migrate a Bench or Experiment to the installed madbench
Target: $ARGUMENTS
With no path, ask for one. A directory means every madbench.yaml, *.madbench.yaml and
*.experiment.yaml in it, one file at a time.
Step 0 — the Glossary and versions, before anything else
- Read
../madbench-evals/glossary.md, relative to this skill's directory. Write only its words for madbench concepts; translate the user's words, never echo them. - Run
madbench skills --checkand quote its output (Step 0 of../madbench/SKILL.mdsays how to read it). You migrate to the installed binary, andchanges.mdmust cover it: an unpinned set older than the binary is updated first (madbench skills), with the user's yes.
Step 1 — the two versions
- Installed:
madbench version, quoted. - Written for: the version the user says the file was written for. With no answer, take v0.41.0 provisionally: Step 3 can still find that the file is older.
This skill knows v0.41.0 and every release after it, and nothing earlier. A file written for
a madbench older than v0.41.0 is outside what it knows: say so, and rewrite the file against
../madbench-evals/schema.md as new authoring, showing the user every change. This is the
rewrite path. Do not reconstruct an older format from memory, and do not report such a
file upstream: an older format is not a madbench gap.
Step 2 — apply changes.md
Read changes.md beside this file. A ## vX.Y.Z section is what release X.Y.Z changed, so a
file written for v0.41.0 takes the ## v0.42.0 section. Take every section newer than the
file's version and not newer than the installed one, oldest first. Apply each old → new line in
those sections exactly as written, and nothing else. A section with no lines changed nothing
that a file spells.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- yesterday Changed · +1 lines dee9fca94b6d
- 3d ago Changed · +3 lines 4df25a5ec089
- 10d ago First seen · 122 lines · 53 tokens per session scan A fd8363e6b6a8
migrate is a skill published in the GitHub repository MadAppGang/magus (13 stars, last pushed today), licensed MIT. It adds 53 tokens to every session and 1,650 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-07.
Other skills, from other repositories
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
eval-dataset-design
A guide to creating reliable test sets for AI agents. Each evaluation task includes the request, the simulated user's behaviour, a reset starting state, and a success check that can be independently verified.
tika-eval-compare
Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.