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 tailorgit 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/tailor)<a href="https://agentmods.dev/skills/huskar20/huskar20-plugins/tailor"><img src="https://agentmods.dev/badge/skills/huskar20/huskar20-plugins/tailor.svg" alt="Measured on agentmods" 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 | $0.00105 | $0.01339 |
| Opus 5 | $0.00053 | $0.00669 |
| Sonnet 5 | $0.00021 | $0.00268 |
| Haiku 4.5 | $0.00011 | $0.00134 |
Grade A, and why
tailor 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 6d 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 — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Resume Forge — Tailor
Produce a copy of the resume aimed at one posting. The master is never edited in place — tailoring always yields a new document, because the user will apply to other roles.
Roughly fifteen minutes of tailoring per application is the highest-return time in a job search. It is also where fabrication is most tempting: the posting names something the user lacks, and adding it is one keystroke away. Do not.
Step 1 — Check prerequisites
Confirm the Google Drive connector is present before collecting inputs — the tailored copy has to land somewhere. List the available tools rather than assuming; stop and say what is missing if it is absent.
Chrome is optional here but needed to edit an existing Doc or export a PDF.
Step 2 — Collect both inputs
- The resume — Google Doc link, local file, or pasted text.
- The job posting — pasted text, a URL to fetch, or a file. Get the actual text; a job title alone is not enough to tailor against.
Capture the company name and exact job title as written — both go into the new file name and the title line.
Step 3 — Analyze coverage
Read references/keyword-coverage.md and follow it. It defines the four
requirement buckets, the four coverage states, and the report format.
The high-value finding is wording mismatch: the user has the experience but describes it differently from the posting. Adopting the posting's exact phrasing for experience they genuinely have is legitimate and effective. Inventing experience is not.
Step 4 — Apply the changes that need no new claims
In order of impact:
- Target title line — rewrite it to echo the posting's own job title. Highest-leverage single line on the page.
- Summary — rewrite one or two sentences to speak to what this posting actually asks for. Keep it 2–4 sentences and keep every fact true.
- Core Competencies — move the most relevant category to the top, and the most relevant items to the front within each category. Do not add items.
- Bullet order inside each role — move the bullet closest to this posting to the top of its role. Do not reorder the roles themselves; reverse chronological is not negotiable.
- Vocabulary alignment — swap the user's phrasing for the posting's where they describe the same real work.
What ships with it
1 file 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.
- 6d ago First seen · 122 lines · 105 tokens per session scan A a09d1723d0e8
tailor is a skill published in the GitHub repository huskar20/huskar20-plugins (4 stars, last pushed 23d ago), licensed MIT. It adds 105 tokens to every session and 1,339 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…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
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…