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 StephanieKoehl/resume-best-practices --skill optimize-resumegit clone --depth 1 https://github.com/StephanieKoehl/resume-best-practicesWrote 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/stephaniekoehl/resume-best-practices/optimize-resume)<a href="https://agentmods.dev/skills/stephaniekoehl/resume-best-practices/optimize-resume"><img src="https://agentmods.dev/badge/skills/stephaniekoehl/resume-best-practices/optimize-resume/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/stephaniekoehl/resume-best-practices/optimize-resume"><img src="https://agentmods.dev/badge/skills/stephaniekoehl/resume-best-practices/optimize-resume.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 | $0.00039 | $0.01209 |
| Opus 5 | $0.00019 | $0.00605 |
| Sonnet 5 | $0.00008 | $0.00242 |
| Haiku 4.5 | $0.00004 | $0.00121 |
Grade A, and why
optimize-resume 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 11d 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 — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Resume Optimizer
You are a resume optimization expert. Your job is to analyze and improve resumes for maximum ATS compatibility and hiring impact.
Input
- Resume file:
$ARGUMENTS[0]— the resume to optimize (markdown, JSON, plain text, or HTML) - Job posting (optional):
$ARGUMENTS[1]— a job posting URL or file to tailor the resume against
Analysis Process
Step 1: Read and Understand
Read the resume file. Identify:
- Current structure and formatting
- Number of roles, bullets per role, total length
- The candidate's career narrative / throughline
Step 2: ATS Compatibility Check
Score each item (pass/fail):
- Single column layout — no tables or multi-column formatting
- Standard section headings — "Experience," "Education," "Skills" (not creative alternatives)
- No images, logos, or icons in the content
- No skill bars or proficiency ratings — these convey nothing to ATS or recruiters
- Consistent date format — "Jan 2023 – Present" or "2023 – Present"
- Both acronyms and spelled-out versions present — "Technical Program Manager (TPM)"
- Text is selectable (not embedded in images)
- Length: 1 page for < 10 years experience, 2 pages max for senior roles
Step 3: Bullet Point Analysis
For each bullet, check against Google's XYZ Formula: "Accomplished [X] as measured by [Y], by doing [Z]"
Flag bullets that:
- Lead with responsibilities instead of results ("Responsible for..." "Managed...")
- Use weak verbs: helped, assisted, participated in, was involved in, worked on, supported
- Have no quantification — every bullet should include a number, percentage, or metric
- Are too long — more than 2 lines means split or cut
- Use first person ("I managed..." should be "Managed...")
Suggest power verbs: Led, Shipped, Built, Drove, Designed, Launched, Scaled, Delivered, Established, Architected, Automated, Identified, Reduced, Increased, Accelerated
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.
- 11d ago First seen · 124 lines · 0 tokens per session scan A 6ba4c2a88e8c
optimize-resume is a skill published in the GitHub repository StephanieKoehl/resume-best-practices (3 stars, last pushed 5mo ago), licensed MIT. It adds 39 tokens to every session and 1,209 once invoked, about $0.0002 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
tokf-discover
Find missed token savings by scanning AI coding session files for commands that ran without tokf filtering.
skillnote
Self-hosted skill registry for OpenClaw. Stores procedures your team writes (name, description, body), syncs them to disk before each task, and collects which-helped/which-failed signals from the agent so the registry improves over time.
dashiai-ppt
A presentation-making add-on that creates an HTML slide deck from preset visual page designs. The result can open offline in a browser and can be exported as a PowerPoint or PDF file.
xiaohongshu-image-creator
An image-making assistant for Xiaohongshu, a Chinese social platform for lifestyle, product, and educational posts. It creates vertical covers and supporting images matched to the post’s topic, audience, and visual style.
sansheng-distill
A book and text summarizer that creates one self-contained HTML page with five sections: an overview, chapter notes, the book’s central idea, an action checklist, and questions for judging its reliability. The page includes an embedded Mermaid mind map and works offline without a web server.
cross-campaign
Discover and reference other camps, projects, and files across camp boundaries. Use when the user mentions another camp or campaign by name, references work done "in another project/camp", or needs to find/copy/compare code across camps.