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 kirich1409/krozov-ai-tools --skill dependency-changesgit clone --depth 1 https://github.com/kirich1409/krozov-ai-toolsWrote 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/kirich1409/krozov-ai-tools/dependency-changes)<a href="https://agentmods.dev/skills/kirich1409/krozov-ai-tools/dependency-changes"><img src="https://agentmods.dev/badge/skills/kirich1409/krozov-ai-tools/dependency-changes/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/kirich1409/krozov-ai-tools/dependency-changes"><img src="https://agentmods.dev/badge/skills/kirich1409/krozov-ai-tools/dependency-changes.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00118 | $0.00613 |
| Opus 5 | $0.00059 | $0.00307 |
| Sonnet 5 | $0.00024 | $0.00123 |
| Haiku 4.5 | $0.00012 | $0.00061 |
Grade A, and why
dependency-changes 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 8d 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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dependency Changes
Show what changed between two versions of a Maven artifact by fetching release notes and changelog data.
Preferred — MCP
-
Parse
groupId,artifactId,fromVersion,toVersionfrom the user or conversation (e.g. a prior check-deps table). IffromVersionis missing, ask or use the current version from context. IffromVersionequalstoVersion, say there is nothing to show. -
Call
get_dependency_changeswith:groupId,artifactIdfromVersion(exclusive)toVersion(inclusive)- optional
projectPath
Provider order: AndroidX developer docs (for
androidx.*), AGP release notes (forcom.android.tools.build), then GitHub releases.GITHUB_TOKENis used server-side for the GitHub path when present — never pass the token in headers yourself. -
Present the tool result: versions in range, release notes / bodies, links. If notes are sparse, still show the version list plus docs / GitHub / Maven Central URLs from the response. Collapse the middle when many versions are returned.
Context: used after check-deps
When the user asks "show me what changed for X" after an update table, pull coordinates and current → latest versions from that table without re-asking.
Error handling
- No docs page / no GitHub repo / no notes — say so and provide the Maven Central (or Google Maven) artifact URL.
- Rate limited — note the limit; retry via
get_dependency_changes(server-side token) rather than attaching a token to a client request. - Artifact not found — suggest checking spelling; do not invent changelog text.
Fallback (MCP unavailable only)
If the tool cannot be called: fetch the POM for SCM, public maven-metadata.xml for the
version list, then unauthenticated GitHub /releases (and optionally raw CHANGELOG.md).
Do not add Authorization / GITHUB_TOKEN on the client. State that project-private
repos are skipped. If rate-limited, say so and stop.
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.
- 8d ago First seen · 51 lines · 118 tokens per session scan A 1f5beaca576b
dependency-changes is a skill published in the GitHub repository kirich1409/krozov-ai-tools (22 stars, last pushed 3d ago), licensed MIT. It adds 118 tokens to every session and 613 once invoked, about $0.0006 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 2026-09-01.
Other skills, from other repositories
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
story-readiness
Validate that a story file is implementation-ready. Checks for embedded GDD requirements, ADR references, engine notes, clear acceptance criteria, and no open design questions. Produces READY / NEEDS WORK / BLOCKED verdict with specific gaps. Use when user says 'is this story ready', 'can I start on this story', 'is…
autotask-creator
Rules for automation CRUD from the group-chat commander. The commander does not call mutation tools and does not edit cloud/autotasks files directly. It emits one or more top-level ... containers in its final text; the bus parses and applies them after the turn.
projects
List all managed projects with status, branch, open PRs, and open issue counts — portfolio-level view.