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 BastiDood/dependency-wrangler --skill bump-dependenciesgit clone --depth 1 https://github.com/BastiDood/dependency-wranglerWrote 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/bastidood/dependency-wrangler/bump-dependencies)<a href="https://agentmods.dev/skills/bastidood/dependency-wrangler/bump-dependencies"><img src="https://agentmods.dev/badge/skills/bastidood/dependency-wrangler/bump-dependencies/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/bastidood/dependency-wrangler/bump-dependencies"><img src="https://agentmods.dev/badge/skills/bastidood/dependency-wrangler/bump-dependencies.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 | $0.00023 | $0.00922 |
| Opus 5 | $0.00012 | $0.00461 |
| Sonnet 5 | $0.00005 | $0.00184 |
| Haiku 4.5 | $0.00002 | $0.00092 |
Grade A, and why
bump-dependencies 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 9d 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.
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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bump Dependencies
Research one package-manager ecosystem and produce a dependency-impact report. Do not modify dependency manifests, lockfiles, application code, commits, branches, or pull requests.
Interpret the user's prose as workflow parameters. With no filter: analyze every patch, minor, and major upgrade. A stated severity filter and a stated package allowlist form an intersection. Include all workspace members by default unless the user narrows the scope.
Procedure
Select One Ecosystem
Choose one cohesive package-manager ecosystem from the user's request and repository evidence. A monorepo that uses one manager for multiple packages is valid.
If multiple active managers exist and neither the request nor repository structure identifies one unambiguously, pause and ask the user to choose a manager or narrower working directory. Do not merge ecosystems.
Before discovery, state which manager and workspace scope will be parsed. For a monorepo, also state that a narrower package allowlist reduces changelog-research cost. Continue unless the manager is ambiguous.
Discover and Select Upgrades
Invoke Skill(find-outdated-dependencies) with the selected manager and workspace scope in prose. Treat its output contract as the sole schema for normalized dependency occurrences. The skill returns those records in context and writes no artifact.
If discovery returns no records, report that all dependencies are current and stop. Do not create or replace .dependabump/.
Apply the user's filters after discovery. Analyze all records when no filter exists. When both severities and package names are stated, select only records that match both. Disregard nonmatching records. If no records remain, report that no outdated dependencies match the requested scope and stop without creating or replacing .dependabump/.
Protect Existing Results
Inspect .dependabump/. If it contains any data, list the existing generated paths, pause, and ask whether the complete directory can be replaced. Make no changes until the user approves. Stop when the user declines.
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.
- 9d ago First seen · 79 lines · 23 tokens per session scan A 03e6a29cccd6
bump-dependencies is a skill published in the GitHub repository BastiDood/dependency-wrangler (11 stars, last pushed 28d ago), licensed Apache-2.0. It adds 23 tokens to every session and 922 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…