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 fmind/dot --skill upgrade-toolsgit clone --depth 1 https://github.com/fmind/dotWrote 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/fmind/dot/upgrade-tools)<a href="https://agentmods.dev/skills/fmind/dot/upgrade-tools"><img src="https://agentmods.dev/badge/skills/fmind/dot/upgrade-tools/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/fmind/dot/upgrade-tools"><img src="https://agentmods.dev/badge/skills/fmind/dot/upgrade-tools.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 | $0.00021 | $0.01123 |
| Opus 5.5 | $0.00008 | $0.00449 |
| Sonnet 5.5 | $0.00004 | $0.00225 |
| Haiku 4.5 | $0.00002 | $0.00112 |
Grade A, and why
upgrade-tools 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 today.
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 — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Upgrade Tools
Upgrade one repository's tools and dependencies to their latest stable releases, validating each ecosystem. The playbook owns the ecosystem commands; mise owns exact pins.
Workflow
- Scope to the requested repository: upgrade only the repository the user named, by default the current one. Each repository owns its pins: never bump another because
fmind/dotor a sibling changed. A multi-repository upgrade needs the user's explicit list; upgrade each on its own merits with its own candidate, gate, and report, canonicalizing paths and linked worktrees so none is upgraded twice. - Separate audit from upgrade: a disk-space or version-reuse check compares current declarations, locks, backends and installed versions without resolving new releases or installing tools. Include restored project directories with mise/runtime files even when
.gitis missing; report recovery gaps and validation limits. Record floating selectors, duplicate installations and justified compatibility exceptions separately. - Start from a green baseline:
mise run checkandmise run testmust be green in a repository before its first bump so regressions are attributable. Preserve dirty work through git-worktree; report pre-existing failures separately. - mise first: in
fmind/dotrunmise run upgrade; elsewhere resolve the latest stable releases of the project's own tools and pin them exactly per the tool version rules, keeping incompatible pins with evidence. - Python dependencies next: they decide whether the new toolchain builds and tests the project; follow the playbook for
pyproject.tomlanduv.lock, then validate. - Infrastructure and images after that (OpenTofu providers, container base images), which consume the language artifacts.
- CI and formatter config last (GitHub Actions, dprint), the outermost layer and the least likely to cascade.
- Stop the failing repository's upgrade and diagnose before advancing its next ecosystem. Keep its original working pins if the upgrade cannot be qualified.
- Verify the final candidate: run the repository gate; test hook wiring when it changed.
lefthook run pre-commit --all-filescan format and restage unrelated work, so exercise it only in an isolated candidate when the original tree is dirty. - Commit per ecosystem when requested: use
chore(deps): upgrade <ecosystem> to latestwith its lockfile (mise run upgradespans several ecosystems at once, so split its commits by lockfile), per conventional-commit. - Report and preview cleanup: list the adopted versions, retained exceptions, and gate results, then preview cleanup as in the playbook; deleting installations needs separate authorization.
What ships with it
1 file 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.
- today Changed 987333ba85eb
- 12d ago Changed · +1 tokens per session 7a4421ba956f
- 14d ago Changed · +4 tokens per session a51c119179d7
- 15d ago Changed · -1 lines 4c0786366627
- 17d ago Changed 8f4ab7f5caba
- 26d ago Changed 4a12954a681d
- 29d ago Changed e6f43cbb8201
- 1mo ago Changed · +1 lines · -23 tokens per session f7f99dc13815
- 1mo ago Changed · +3 lines · +3 tokens per session 38f853cff1d2
- 1mo ago First seen · 42 lines · 36 tokens per session scan A 3d8e273cab83
upgrade-tools is a skill published in the GitHub repository fmind/dot (12 stars, last pushed today), licensed MIT. It adds 21 tokens to every session and 1,123 once invoked, about $0.0001 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 2026-09-03.
Other skills, from other repositories
dotfiles-bootstrap
Bootstrap a workstation with the dotfiles framework. Takes a GitHub user / owner+repo / explicit clone URL and runs dot init (which shells out to chezmoi) with the right safety prompts. Honors the active agent profile (ask / plan / apply / audit) so it defaults to dry-run in safer modes and full apply in apply.
vibe
Delegate a coding task to a cheap AI model (Mistral Vibe by default, but any provider Vibe knows about — DeepSeek, Gemini Flash, etc.) and supervise the result via git diff. Claude orchestrates, the cheap model codes. Claude consumes 500-1500 tokens per delegation regardless of how many file reads the delegate does…
go-stack
Build Go projects, libraries, CLIs, TUIs, web apps, or ADK agents with the standard package layout and pinned tooling.
python-stack
Build typed Python projects with uv, Ruff, ty, pytest, Litestar, and Typer. Use for packages, CLIs, web apps, tests, typing, or API verification.
hugo
Canonical Hugo static-site stack with the Hextra docs theme — Hugo Modules, mise tasks, dprint, lefthook, and GitHub Pages deploy. Use for documentation sites, project docs, and static websites.
k8s-local
Create and manage local Kubernetes clusters (k3d or kind) and deploy to them with kubectl, helm, helmfile, and skaffold. Use for local k8s cluster setup, dev loops, and debugging.