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 JayRHa/AgentSkills --skill dependency-upgradergit clone --depth 1 https://github.com/JayRHa/AgentSkillsWrote 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/jayrha/agentskills/dependency-upgrader)<a href="https://agentmods.dev/skills/jayrha/agentskills/dependency-upgrader"><img src="https://agentmods.dev/badge/skills/jayrha/agentskills/dependency-upgrader/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/jayrha/agentskills/dependency-upgrader"><img src="https://agentmods.dev/badge/skills/jayrha/agentskills/dependency-upgrader.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 | $0.00115 | $0.01936 |
| Opus 5.5 | $0.00046 | $0.00774 |
| Sonnet 5.5 | $0.00023 | $0.00387 |
| Haiku 4.5 | $0.00012 | $0.00194 |
Grade A, and why
dependency-upgrader 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 1mo 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 — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dependency Upgrader
Overview
This skill drives safe, auditable dependency upgrades across ecosystems (npm/yarn/pnpm, pip/poetry/uv, cargo, go modules, bundler, maven/gradle, composer). The core discipline: one upgrade per commit, tests green between each, and a known-good rollback point at all times. Never bulk-upgrade everything and hope.
Keywords: dependency upgrade, bump packages, outdated, semver, breaking change, changelog, migration guide, lockfile, CVE, security advisory, Dependabot, Renovate, rollback, npm audit, pip-audit.
Use this skill when the user wants to update libraries, patch a vulnerability, migrate a major version, or vet an automated bump PR.
Core Principles
- Isolate. One package (or one tightly-coupled group) per commit. A failed upgrade must be revertable without touching unrelated work.
- Read before you write. Always inspect the changelog / release notes / migration guide before bumping across a major version.
- Tiered risk. Patch < minor < major. Batch low-risk; isolate high-risk.
- Test gate. The test suite (or a defined verification command) must pass before each commit. No green, no commit.
- Always have a rollback. Know the exact git SHA and lockfile state to
return to. See
references/rollback.md.
Workflow
Follow these steps in order. Do not skip the inventory or the changelog read.
1. Establish a clean baseline
- Confirm the working tree is clean (
git status). If not, stop and ask the user how to proceed — never upgrade on top of uncommitted changes. - Record the current commit SHA as the rollback anchor.
- Run the test suite once to confirm it is green before you start. If tests are already failing, report that and stop — you cannot attribute later failures otherwise.
- Identify the ecosystem and the verification command. See
references/ecosystems.mdfor the canonical commands per package manager.
2. Inventory outdated dependencies
- Run the detector script:
python3 scripts/check_outdated.py --dir <repo>. It auto-detects the ecosystem and prints a risk-tiered table (patch / minor / major) plus any known advisories it can surface from the native auditor. - Or run the native tool directly (
npm outdated,pip list --outdated,cargo outdated,go list -m -u all) — seereferences/ecosystems.md. - Classify each candidate by semver jump and by whether it is a direct or transitive dependency.
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.
- 1mo ago First seen · 159 lines · 115 tokens per session scan A c66e101b2905
dependency-upgrader is a skill published in the GitHub repository JayRHa/AgentSkills (12 stars, last pushed 2mo ago), licensed MIT. It adds 115 tokens to every session and 1,936 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
cost-optimizer
Trigger when the user asks to audit Claude Code costs, reduce token spend, says "my Claude bill is too high", "optimize my CLAUDE.md", "why is this project burning tokens", or "/cost-optimizer". Scans a project for the common Claude Code cost leaks and returns a prioritized fix list.
excalidraw-architecture
Trigger when the user asks for an architecture diagram, says "draw the system", "update the architecture diagram", "give me an excalidraw of this codebase", or "/excalidraw-architecture". Generates or updates an Excalidraw JSON file at docs/architecture.excalidraw by reading the codebase's key entry points.
model-cost-compare
Trigger when the user asks which model to use, wants to compare model costs, says "what's cheapest for this task", "should I use Opus or Sonnet", "can a smaller model handle this", or "/model-cost-compare". Estimates token cost across Opus 4.6, Sonnet 4.6, GLM-5.1, Minimax M2.7, and local Gemma 4, then recommends the…
openclaw-debugger
Trigger when an OpenClaw agent is broken, silent, crashing, stuck, not responding, returning empty output, or the user says "my agent is down", "agent not working", "/openclaw-debugger". Walks through the standard OpenClaw 2026.4 diagnosis checklist and prints a report.
git-commit-writer
Trigger when the user asks to write a commit message, generate a commit from staged changes, review a diff before committing, or says "/commit". Reads git diff --staged and produces an opinionated, convention-matching commit message.
growth-ideas
Describe your product or project and get three actionable growth ideas tailored to your stage.