ww-upload-cover-letter

ww-upload-cover-letter is a skill for Codex from jerryzhang1011/waterlooworks-application-plugins. It costs 104 tokens per session (2,862 once invoked), scanned A, original, MIT.

A browser workflow for placing a cover-letter PDF from the `coverletter/` folder into the required Cover Letter slot of a WaterlooWorks job application. WaterlooWorks is the University of Waterloo’s online job-application system.

In plain words
What is it for?
Use it after creating a custom WaterlooWorks application package when a Cover Letter slot is required. It finds the company-matching PDF, uploads it, and leaves the application unsubmitted.
Why use it?
It removes the need to navigate the nested file-upload dialogs manually and helps put the matching letter in the right application package without submitting the application.

Skill for Codex

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

Good fit Use it after creating a custom WaterlooWorks application package when a Cover Letter slot is required. It finds the company-matching PDF, uploads it, and leaves the application unsubmitted.

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

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/jerryzhang1011/waterlooworks-application-plugins/ww-upload-cover-letter"><img src="https://agentmods.dev/badge/skills/jerryzhang1011/waterlooworks-application-plugins/ww-upload-cover-letter.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 104 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,862 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 $0.00104 $0.02862
Opus 5 $0.00052 $0.01431
Sonnet 5 $0.00021 $0.00572
Haiku 4.5 $0.00010 $0.00286

Measured 12d ago against content hash b0d2dcf8ba1b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

ww-upload-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.

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-upload-cover-letter/SKILL.md · 142 lines

How it starts

The opening of the file, as written. The whole thing — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Upload Cover Letter

Overview

Upload a cover-letter PDF into the current WaterlooWorks application package without submitting the application. This skill is intended to be called from a WaterlooWorks application flow after Create Custom Application Package is selected and a required *Cover Letter slot is visible.

The observed reliable workflow is: Upload New Cover Letter -> fill Name -> click the parent dialog upload button #btn_fileUploadDialog_docUpload -> in the nested file-upload panel click label[for="fileUpload_docUpload"] / Choose a file -> set the PDF through the Chrome file chooser -> wait for Current File: in the parent dialog -> click Upload A Document.

Inputs

Require or infer these before starting:

  • application_tab: a Chrome-controlled WaterlooWorks tab showing Submit Application -> Application Options.
  • coverletter_path: default to coverletter/<Company>-coverletter.pdf — this is where ww-write-cover-letter writes it. If several coverletter/*-coverletter.pdf files exist, prefer the one whose company matches the application; ask only if none match or the choice is ambiguous.
  • document_name: optional display name for the uploaded WaterlooWorks document. Prefer the organization name shown in the application header; otherwise use the base file name without .pdf.

Do not upload a non-PDF file. The recorded WaterlooWorks dialog accepted pdf and showed a 5.00 MB max file size, so verify the local file exists, is a .pdf, and is no larger than 5 MB before uploading.

Browser Setup

Use the @chrome plugin (plugin://chrome@openai-bundled) so the task runs against the user's logged-in Chrome session, which WaterlooWorks depends on. Uploads go through the Playwright filechooser API the @chrome plugin exposes.

  • Claim or continue the existing WaterlooWorks Submit Application tab; do not start a new unrelated application.
  • Do not inspect cookies, local storage, saved passwords, or browser profile internals.
  • Use the browser file-chooser flow as the upload method:

Read the full file on GitHub · 142 lines

Files

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.

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 · 142 lines · 104 tokens per session scan A b0d2dcf8ba1b

Subscribe to this mod's changes

ww-upload-cover-letter is a skill published in the GitHub repository jerryzhang1011/waterlooworks-application-plugins (1 stars, last pushed 2mo ago), licensed MIT. It adds 104 tokens to every session and 2,862 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.