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 huskar20/huskar20-plugins --skill reviewgit clone --depth 1 https://github.com/huskar20/huskar20-pluginsWrote 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/huskar20/huskar20-plugins/review)<a href="https://agentmods.dev/skills/huskar20/huskar20-plugins/review"><img src="https://agentmods.dev/badge/skills/huskar20/huskar20-plugins/review/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/huskar20/huskar20-plugins/review"><img src="https://agentmods.dev/badge/skills/huskar20/huskar20-plugins/review.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 | $0.00093 | $0.00919 |
| Opus 5 | $0.00046 | $0.00460 |
| Sonnet 5 | $0.00019 | $0.00184 |
| Haiku 4.5 | $0.00009 | $0.00092 |
Grade A, and why
review 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Resume Forge — Review
Audit a resume and report what actually fails. Read-only by default: report first, offer to fix second.
Step 1 — Get the resume
Accept a Google Doc link or Drive file, a local .docx / .pdf / .md /
.txt, or pasted text. Read the whole document before judging any part of it.
Ask for two things if not obvious, because several checks depend on them:
- Years of professional experience — sets the page budget and the section order
- Target role — sets whether the title line and skills are aimed correctly
If a target job description is available, say that tailor does the
posting-specific comparison, and keep this review about the document itself.
Step 2 — Run the checklist
Read references/checklist.md and work through all 39 items. Check every one;
do not sample. Each is written to be objectively testable against the text.
Some checks need a whole-document view rather than a line-by-line pass:
- Metric count — count bullets containing a figure across the entire resume. Fewer than four is a strong warning; zero is the most common failure there is. The opposite also matters: if nearly every bullet ends in a figure, flag it — that reads fabricated even when each number is true.
- Machine-written tells — these need the whole document too: dash density inside sentences, bullets all landing at the same length, repeated opening verbs across a role.
- Tense consistency — evaluate within each role, not globally. Present tense is correct for a current role and wrong for a past one.
- Page budget — estimate from content volume if the source is text rather than a rendered document, and say the estimate is an estimate.
- Section order — depends on the years-of-experience answer from Step 1.
- Header links — for a
.docxsource, runscripts/check_links.py <file>(standard library only, no install). It compares every hyperlink's display text with its real target, and lists URL-looking text that carries no hyperlink at all. A link whose text says one address while pointing at another cannot be seen on the rendered page, so never skip the script when the source is a.docx. Covers advisory items 35 and 36; for other source formats those two stay an eyeball check.
What ships with it
2 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.
- 8d ago First seen · 80 lines · 93 tokens per session scan A f891ca25c5e7
review is a skill published in the GitHub repository huskar20/huskar20-plugins (4 stars, last pushed yesterday), licensed MIT. It adds 93 tokens to every session and 919 once invoked, about $0.0005 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…
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…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…