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 H2OArctic/claude-skill-deps-update --skill skillgit clone --depth 1 https://github.com/H2OArctic/claude-skill-deps-updateWrote 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/h2oarctic/claude-skill-deps-update/skill)<a href="https://agentmods.dev/skills/h2oarctic/claude-skill-deps-update/skill"><img src="https://agentmods.dev/badge/skills/h2oarctic/claude-skill-deps-update/skill/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/h2oarctic/claude-skill-deps-update/skill"><img src="https://agentmods.dev/badge/skills/h2oarctic/claude-skill-deps-update/skill.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 | $0.00072 | $0.06446 |
| Opus 5 | $0.00036 | $0.03223 |
| Sonnet 5 | $0.00014 | $0.01289 |
| Haiku 4.5 | $0.00007 | $0.00645 |
Grade B, and why
deps-update scanned grade B with 2 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 10d ago.
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.
Recursive force deletemediumDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
No `clean` script → equivalent: `rm -rf node_modules **/node_modules bun.lock && bun install`. Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
`postinstall`, a new `import` of `fs`/`child_process`/`os`, `engines` moving from `node >=12` to `>=18`, How it starts
The opening of the file, as written. The whole thing — 465 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dependency updates (Bun)
Runtime and package manager: Bun only. Never npm, npx, yarn, pnpm, or node.
Requires Bun >= 1.4 (bun audit fix, bun dedupe, bun pm diff, --minimum-release-age).
This skill does not chase latest. It splits updates by risk, rebuilds the lockfile, then settles
overrides on that final tree, and ends with typecheck and tests.
Talk to the user in the language they use.
Invariant
Nothing is written to disk before the plan is approved (phase 2). Phases 0–1 are read-only, and the
new tools keep it that way: bun pm diff only downloads and compares tarballs, while bun audit fix and
bun dedupe resolve and report as long as --dry-run is there. Without that flag both rewrite
bun.lock and node_modules (and audit fix rewrites package.json too), so in phases 0–1 they are
never run bare.
The overrides experiment in phase 5 temporarily strips the root overrides block and reinstalls. Keep the
original block verbatim: everything load-bearing goes back before the phase ends, so the stripped state is
a measurement, never a result.
Phase 0. Preflight
git status --porcelain # working tree must be clean
git branch --show-current
bun --version # must be >= 1.4
- Dirty tree → look at what is actually in the diff (
git diff --stat, then thepackage.jsondiff) before asking anything. It is often a previous run of this skill, or unrelated work in progress; the two need different handling. Show the user what you found, then ask whether to continue. A clean tree means rollback is one command (git checkout -- .), so no backups are needed. - Working on top of someone else's uncommitted work is allowed, but from that moment you must be able to say which changes are yours — phase 6 failures will otherwise get blamed on the update.
- Read the root
package.json: which scripts exist (typecheck, tests, lockfileclean, dead-code checks), whether there areworkspaces,catalog/catalogs,overrides/resolutions. Use the project's own script names later — do not assume them. - Read
bunfig.tomlif present.[install] minimumReleaseAgeis the project's supply-chain policy andlinker = "isolated"changes whatnode_moduleslooks like (not what the lockfile says). Both are reported by the scan; respect them instead of proposing your own. - No
workspaces→ the skill works the same, just one package.
What ships with it
6 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.
- 10d ago First seen · 465 lines · 72 tokens per session scan B bbbc0f9add0b
deps-update is a skill published in the GitHub repository H2OArctic/claude-skill-deps-update (2 stars, last pushed 19d ago), licensed MIT. It adds 72 tokens to every session and 6,446 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it B with 2 findings (recursive force delete, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
add-a-service
Scaffold a new service under services/ in the builders-stack monorepo. Use when something needs its own URL, port, or independent deploy. Covers the package, entrypoint, config, Tilt, deployment registry, and shared small-image build path.
design-a-schema
Model a new table (or reshape an existing one) in libs/db with Drizzle — normalize by default, add the right constraints, and index deliberately. Use when adding a table/column, deciding on keys and foreign keys, or when a query is slow because the schema or its indexes are wrong. Enforces the stack's "Drizzle is the…
optimize-a-query
Diagnose and fix a slow Postgres query in the builders-stack — read its EXPLAIN plan, find the missing index or the ORM N+1, and confirm the fix. Use when a page or endpoint is slow, a query times out, or pgstatstatements shows a hot query. Pairs with design-a-schema for the index itself.
wire-a-new-payment-provider
Add or swap a payment provider behind the @stack/payment adapter in the builders-stack monorepo. Use when integrating Stripe, Paddle, Lemon Squeezy, or any provider alongside or in place of the default Creem adapter. The whole point is that apps and the API never change — only the adapter implementation does. Covers…
add-a-lib
Scaffold a new shared library under libs/ in the builders-stack monorepo. Use when code is needed in two or more places (apps or services) and should become a single source of truth consumed by package name. Covers the package.json, tsconfig, the one-public-door src/index.ts barrel, and wiring it into a consumer…
create-a-worktree
Create, inspect, or retire an isolated Builders Stack agent runtime through Worktree Zero. Use whenever parallel work needs another checkout or an old worktree needs cleanup.