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 Mahashwetha/Job-search-email-system-claude --skill cover-lettergit clone --depth 1 https://github.com/Mahashwetha/Job-search-email-system-claudeWrote 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/mahashwetha/job-search-email-system-claude/cover-letter)<a href="https://agentmods.dev/skills/mahashwetha/job-search-email-system-claude/cover-letter"><img src="https://agentmods.dev/badge/skills/mahashwetha/job-search-email-system-claude/cover-letter/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/mahashwetha/job-search-email-system-claude/cover-letter"><img src="https://agentmods.dev/badge/skills/mahashwetha/job-search-email-system-claude/cover-letter.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 | $0.00051 | $0.00686 |
| Opus 5.5 | $0.00020 | $0.00274 |
| Sonnet 5.5 | $0.00010 | $0.00137 |
| Haiku 4.5 | $0.00005 | $0.00069 |
Grade A, and why
cover-letter 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 20d 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cover Letter Generator
Generate a tailored cover letter using cover_letter.py.
How to invoke
Slash command (preferred):
/cover-letter https://job-url
/cover-letter https://job-url Company Name
/cover-letter https://job-url Company Name "Role Title"
Or natural language: cover letter <url>, generate cover letter for Constructor
How to run
python cover_letter.py "https://job-url" "Company Name" "Role Title"
python cover_letter.py "https://job-url" "Company Name" # role extracted from JD
python cover_letter.py "https://job-url" "Company Name" "Role Title" --referral "Name, their role"
Use --referral whenever the user mentions a referral (someone at the company recommended her): the opening line then names the referrer.
What it does
- Fetches the job description from the URL (same scraper as resume_tailor.py)
- Calls Gemini to generate three tailored paragraphs:
- Opening paragraph — 2 sentences, never "I am writing to express my interest". Gemini picks the strongest type for the job: referral, specific achievement (only from the verified CANDIDATE ACHIEVEMENTS list in the prompt), company-specific observation, or direct capability. The code rejects banned phrases and false domain claims (NASDAQ = trade surveillance, not payments/banking) and falls back to a safe achievement-led opening; the console prints the opening type and any rejection reason.
- Matched skills paragraph — specific tech/tools from the JD that the candidate has
- Gap bridge paragraph — honest: states what she hasn't used, never claims she is "learning/deepening" a gap technology
- Assembles the full letter using a fixed template (opening, generated paras, fixed personal projects + close)
- Saves DOCX to
cover_letters/CoverLetter_{Company}.docx - Dumps the full text to console
Output location
cover_letters/CoverLetter_{Company}.docx (next to the resume output folder set in config.py)
Template structure (fixed)
- Header (Paris, France | phone | email)
- "Respected Hiring Manager,"
- Opening — Gemini-generated (achievement / company / capability / referral), validated in code
- Matched skills para — Gemini-generated
- Gap bridge para — Gemini-generated
- Personal projects para — hardcoded (job pipeline + Fit-Check)
- Close para — hardcoded (Paris, open to remote/hybrid, aligns with company goals)
- Sign-off
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.
- 20d ago Changed b2fd3995cb0d
- 1mo ago Changed · +4 lines cd9169e7b287
- 1mo ago First seen · 59 lines · 51 tokens per session scan A afe8a4db53b4
cover-letter is a skill published in the GitHub repository Mahashwetha/Job-search-email-system-claude (10 stars, last pushed today), licensed MIT. It adds 51 tokens to every session and 686 once invoked, about $0.0002 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.
Other skills, from other repositories
ats-latex-cv
Build ATS-optimised, human-sounding CVs in LaTeX (Overleaf-ready code). Trigger this skill whenever a user asks to create, rewrite, reconstruct, or improve a CV, resume, or job application document — including when they upload an existing CV, paste raw experience, or describe a target role. Also trigger when the user…
pydicom
Reads, inspects, writes, transforms, and preflights local DICOM datasets and pixel data. Applies to DICOM metadata, transfer syntaxes, compression plugins, frames, private elements, JSON, and bounded de-identification review.
treatment-plans
Formats and structurally validates local treatment-plan documentation after clinical decisions have already been supplied and verified by authorized licensed professionals. Use for source traceability, clinician-authored intervention records, goals and checkpoints, shared-decision records, reconciliation handoffs, and…
venue-templates
Prepares journal manuscripts, conference papers, research posters, and grant documents using venue-specific formatting guidance and bundled LaTeX scaffolds. Supports selecting an official template, checking current page or anonymity rules, adapting academic writing to a venue, or inspecting a submission PDF.
baoyu-youtube-transcript
A tool for downloading the written captions, subtitles, chapter information, speaker labels, and cover image from a YouTube video using its URL or ID.
sync-submission
Use when building, auditing or freezing a journal submission package from the canonical manuscript. Detects drift between the source and the per-journal submission copy, builds byte-preserving packages with manifests, and records current, stale or frozen status.