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 jasonjgarcia24/ai-assisted-job-search --skill job-application-helpergit clone --depth 1 https://github.com/jasonjgarcia24/ai-assisted-job-searchWrote 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/jasonjgarcia24/ai-assisted-job-search/job-application-helper)<a href="https://agentmods.dev/skills/jasonjgarcia24/ai-assisted-job-search/job-application-helper"><img src="https://agentmods.dev/badge/skills/jasonjgarcia24/ai-assisted-job-search/job-application-helper/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/jasonjgarcia24/ai-assisted-job-search/job-application-helper"><img src="https://agentmods.dev/badge/skills/jasonjgarcia24/ai-assisted-job-search/job-application-helper.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 | $0.00153 | $0.03367 |
| Opus 5.5 | $0.00061 | $0.01347 |
| Sonnet 5.5 | $0.00031 | $0.00673 |
| Haiku 4.5 | $0.00015 | $0.00337 |
Grade A, and why
job-application-helper 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 2mo 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 — 278 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Job Application Tailoring
Source Documents
- Baseline Resume:
assets/Jason_J_Garcia-RESUME.docx(MUST be edited via XML, never recreated) - LinkedIn Profile: https://www.linkedin.com/in/24-jason-j-garcia/ (for additional experience details)
- Cover Letter Template:
assets/Jason_J_Garcia-COVERLETTER.md(for formatting structure) - Target Companies List:
references/list_of_target_companies.md
Core Principles
LinkedIn Parsing System (LPS) Optimization
Modern employers use LPS to screen resumes before human review. Your materials must:
- Include targeted keywords from the job description (especially in the first third of the resume)
- Use industry-standard terminology and role-specific language
- Avoid verbose descriptions that dilute keyword density
- Structure content for both machine parsing and human readability
- Quantify achievements with specific metrics
- Align experience descriptions with job requirements using parallel language
Critical: If a resume lacks proper formatting, targeted keywords, or alignment with job-specific requirements, it will be rejected before reaching human eyes. Issues like verbose descriptions, weak KSA (Knowledge, Skills, Abilities) responses, or outdated templates render applications invisible.
Applicant Tracking System (ATS) Optimization
ATS software parses and stores resume data before human review. Ensure materials are ATS-compatible:
- File format: Always submit
.docxfor initial applications — PDFs may not parse correctly in all ATS platforms - Standard section headers: Use recognizable headers (e.g., "Experience", "Education", "Technical Skills") so ATS can map content to the correct fields
- Parseable structure: Avoid tables, text boxes, multi-column layouts, and content in headers/footers — ATS systems often skip or misparse these elements
- Simple formatting: Use standard fonts (Calibri, Arial, Times New Roman) and avoid graphics, icons, or decorative elements that interfere with text extraction
- Contact info placement: Place name, email, phone, and LinkedIn URL in the main document body (not in a header/footer) so ATS can extract them into candidate fields
What ships with it
17 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.
- assets/Jason_J_Garcia-COVERLETTER.md 2.1 KB
- assets/Jason_J_Garcia-RESUME.docx 13 KB
- assets/LinkedIn_Best_Profile_Guide.pdf 52 KB
- references/company_research.md 1.9 KB
- references/interview_preparation.md 2.4 KB
- references/linkedin_profile_optimization.md 12 KB
- references/list_of_key_accomplishments.md 2.2 KB
- references/list_of_target_companies.md 308 B
- references/networking_support.md 2.7 KB
- references/qa_and_delivery.md 2.3 KB
- references/skill_gap_analysis.md 2.3 KB
- references/user_profile.md 1.2 KB
- references/xml_editing_guide.md 9.3 KB
- scripts/cleanup_unpacked.sh 1.3 KB runs code
- scripts/create_tailored_resume.sh 3.2 KB runs code
- scripts/prepare_resume.sh 2.7 KB runs code
- scripts/verify_page_count.sh 1.5 KB runs code
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.
- 2mo ago First seen · 278 lines · 153 tokens per session scan A 6a57ba390ae3
job-application-helper is a skill published in the GitHub repository jasonjgarcia24/ai-assisted-job-search (11 stars, last pushed 8mo ago), licensed MIT. It adds 153 tokens to every session and 3,367 once invoked, about $0.0006 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.
job-application-helper compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| job-application-helperjasonjgarcia24/ai-assisted-job-search | Skill | 11 | 8mo ago | MIT | A | 153 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 134k | today | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | today | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | today | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 314k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |