ww-write-cover-letter

ww-write-cover-letter is a skill for Codex from jerryzhang1011/waterlooworks-application-plugins. It costs 219 tokens per session (2,254 once invoked), scanned A, original, MIT.

A skill that creates a tailored, one-page cover-letter PDF from a job description and one of the user's résumés. It saves the file in a coverletter folder using a specified Times-font layout.

In plain words
What is it for?
Use it to write job-specific cover letters, format the applicant's contact details and signature, and save the finished PDF with the company name.
Why use it?
It removes the work of adapting a résumé to a job and formatting the letter into a one-page PDF.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: mentions Codex.

Good fit Use it to write job-specific cover letters, format the applicant's contact details and signature, and save the finished PDF with the company name.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jerryzhang1011/waterlooworks-application-plugins/ww-write-cover-letter
Install

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.

Any agent
npx skills add jerryzhang1011/waterlooworks-application-plugins --skill ww-write-cover-letter
Clone the repo
git clone --depth 1 https://github.com/jerryzhang1011/waterlooworks-application-plugins

Made for: Codex.

Wrote 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.

agentmods badge for ww-write-cover-letter

README.md
[![agentmods](https://agentmods.dev/badge/skills/jerryzhang1011/waterlooworks-application-plugins/ww-write-cover-letter/github.svg)](https://agentmods.dev/skills/jerryzhang1011/waterlooworks-application-plugins/ww-write-cover-letter)
Your own site
<a href="https://agentmods.dev/skills/jerryzhang1011/waterlooworks-application-plugins/ww-write-cover-letter"><img src="https://agentmods.dev/badge/skills/jerryzhang1011/waterlooworks-application-plugins/ww-write-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.

agentmods 80×15 button for ww-write-cover-letter

Your own site · 80×15
<a href="https://agentmods.dev/skills/jerryzhang1011/waterlooworks-application-plugins/ww-write-cover-letter"><img src="https://agentmods.dev/badge/skills/jerryzhang1011/waterlooworks-application-plugins/ww-write-cover-letter.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 219 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,254 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00219 $0.02254
Opus 5 $0.00110 $0.01127
Sonnet 5 $0.00044 $0.00451
Haiku 4.5 $0.00022 $0.00225

Measured 12d ago against content hash 9194a10d3cd9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

ww-write-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 12d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/generate_cover_letter.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

plugins/waterlooworks-jobs-codex/skills/ww-write-cover-letter/SKILL.md · 158 lines

How it starts

The opening of the file, as written. The whole thing — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Generate Cover Letter

Overview

Produce a one-page, job-specific cover letter PDF that matches the user's reference style: the name centered and bold at the top, a contact row with the mailing address on the left and links (LinkedIn, email, etc.) on the right, then "Dear Hiring Manager," three-to-four tailored body paragraphs, "Sincerely," and the signature name.

The division of labor matters: you write the tailored prose, and a bundled script (scripts/generate_cover_letter.py, reportlab) owns the layout and the one-page guarantee. The script auto-fits the text by stepping down through compact typographic presets, and if the body is too long to fit on one page even at the smallest readable size it fails loudly instead of spilling onto a second page — so keep the writing tight and let the script handle the rest.

The output is written to the coverletter/ folder (created automatically) as <Company>-coverletter.pdf.

Inputs

Gather or infer these before generating:

  • Job description — accept any of: a WaterlooWorks job ID (e.g. 475135), a path to a JD file, JD text pasted into chat, or JD details already in your context (a calling skill or agent passed the posting facts, or you read the posting earlier this session — no local file needed). From it you need the company/organization name, the role title, the work term (e.g. "Fall 2026"), and the key responsibilities/skills to tailor toward.
  • Résumé — which of the user's résumés to draw evidence from (resume/ai.pdf, swe.pdf, frontend.pdf, backend.pdf). If the user names one, use it. If not, check ranks/shortlist.md in the repo — it maps job IDs to the recommended résumé. If still ambiguous, ask.
  • Header configcoverletter-config.json in the current folder (see Step 0).

Step 0 — Ensure the header config exists

Look for coverletter-config.json in the current working directory.

  • If it exists, use it as-is.
  • If it is missing, ask the user for their header details and write the file before continuing. Collect: full name; mailing address lines (or confirm none); and which contact items to show on the right (LinkedIn, GitHub, email, phone, website) with their URLs. Then write the config in this schema:

Read the full file on GitHub · 158 lines

Files

What ships with it

4 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.

Changes

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.

  1. 12d ago First seen · 158 lines · 219 tokens per session scan A 9194a10d3cd9

Subscribe to this mod's changes

ww-write-cover-letter is a skill published in the GitHub repository jerryzhang1011/waterlooworks-application-plugins (1 stars, last pushed 2mo ago), licensed MIT. It adds 219 tokens to every session and 2,254 once invoked, about $0.0011 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.