upgrade-tools

upgrade-tools is a skill for Claude Code, Codex from fmind/dot. It costs 36 tokens per session (778 once invoked), scanned A, original, MIT.

A workflow for updating pinned development tools and project dependencies one technology group at a time.

In plain words
What is it for?
Use it when upgrading language packages, toolchains, infrastructure providers, container images, CI workflows, or formatters.
Why use it?
It makes it easier to identify which update caused a failure and avoids debugging many changes at once.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/fmind/dot/upgrade-tools
Any agent
npx skills add fmind/dot --skill upgrade-tools
Clone the repo
git clone --depth 1 https://github.com/fmind/dot

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for upgrade-tools

README.md
[![agentmods](https://agentmods.dev/badge/skills/fmind/dot/upgrade-tools.svg)](https://agentmods.dev/skills/fmind/dot/upgrade-tools)
Your own site
<a href="https://agentmods.dev/skills/fmind/dot/upgrade-tools"><img src="https://agentmods.dev/badge/skills/fmind/dot/upgrade-tools.svg" alt="Measured on agentmods" height="20"></a>
Per session 36 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 778 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00036 $0.00778
Opus 5 $0.00018 $0.00389
Sonnet 5 $0.00007 $0.00156
Haiku 4.5 $0.00004 $0.00078

Measured yesterday against content hash a2b6900c4b5e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 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.

skills/upgrade-tools/SKILL.md · 40 lines

How it starts

The opening of the file, as written. The whole thing — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Upgrade Tools

Bump every pinned tool and dependency to its latest stable version, one ecosystem at a time, validating after each so a bad bump is caught immediately; the per-manifest commands live in the playbook and mise owns the tool pins.

Workflow

  1. Baseline: mise run check and mise run test must be green before the first bump so regressions are attributable.
  2. mise first: it provisions the toolchain every later step runs; bump and re-lock the pins per mise, then validate.
  3. Language dependencies next (Go, Python, Node, Rust) decide whether the new toolchain compiles the project; follow the playbook per manifest and validate after each.
  4. Infrastructure and images after that (OpenTofu providers, container base images), which consume the language artifacts.
  5. CI and formatter config last (GitHub Actions, dprint), the outermost layer and the least likely to cascade.
  6. Stop at the first failing ecosystem and fix it before continuing; bumping the rest on top of a broken one turns a short upgrade into an afternoon of bisecting.
  7. Run the hooks once at the end: lefthook run pre-commit --all-files and lefthook run pre-push --all-files.
  8. Commit per ecosystem: chore(deps): upgrade <ecosystem> to latest with its lockfile, per conventional-commit.

Gotchas

  • Latest stable only: no RCs, betas, or pre-releases; tools deliberately range-pinned pre-1.0 stay in their range.
  • Lockfiles are the record: commit mise.lock, go.sum, uv.lock, pnpm-lock.yaml, .terraform.lock.hcl; the manifest says "latest", the lockfile says which.
  • Majors are separate changes: go get -u and uv lock --upgrade stay within declared majors; a major bump gets its own reviewed change.
  • Held-back pins: a pin kept below latest carries a comment saying why (a parser ABI, a broken upstream asset); re-pin it deliberately instead of letting a bump carry it forward silently.

Read the full file on GitHub · 40 lines

Files

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.

Changes

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.

  1. yesterday First seen · 40 lines · 36 tokens per session scan A a2b6900c4b5e

Subscribe to this mod's changes

upgrade-tools is a skill published in the GitHub repository fmind/dot (4 stars, last pushed yesterday), licensed MIT. It adds 36 tokens to every session and 778 once invoked, about $0.0002 per session on Opus 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.