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 sayantan94/AppliedIn --skill application-fillinggit clone --depth 1 https://github.com/sayantan94/AppliedInWrote 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/sayantan94/appliedin/application-filling)<a href="https://agentmods.dev/skills/sayantan94/appliedin/application-filling"><img src="https://agentmods.dev/badge/skills/sayantan94/appliedin/application-filling/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/sayantan94/appliedin/application-filling"><img src="https://agentmods.dev/badge/skills/sayantan94/appliedin/application-filling.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 | $0.00084 | $0.01039 |
| Opus 5 | $0.00042 | $0.00519 |
| Sonnet 5 | $0.00017 | $0.00208 |
| Haiku 4.5 | $0.00008 | $0.00104 |
Grade A, and why
application-filling 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 9d 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Application filling
You orchestrate one call — apply_to_job() — and turn its result into either a
"done" or a human gate. The heavy lifting is the engine below; you do not drive
the browser field-by-field yourself.
What apply_to_job() does internally
It hands the posting to a claude --chrome subprocess that acts in the owner's
own browser — a real profile with real history, which is what portals accept.
There is no headless driver and no second engine.
- Refuse outright if tracking already marks this job applied (a duplicate under the owner's real name is worse than a missed application).
- Rewrite the posting to the ATS board's direct URL where one exists — a cross-origin embed blocks the résumé upload.
- Open the posting and reach the actual form (Ashby "Application" tab, Greenhouse/Lever "Apply" button).
- Set the tailored résumé on the real résumé input, never the optional "autofill from resume" uploader, and never by clicking an "Attach" button (that opens an OS file chooser and freezes the browser).
- Fill from approved facts only. A free-text question with no banked answer goes to a writer model grounded in the résumé + GitHub + JD.
- Submit, read the FORM's own validation errors, fix the flagged fields, resubmit. The form is the source of truth, not a DOM read.
- Stop at the real blocker: a required field with no answer, an account wall, or a CAPTCHA — filled form left open for the human.
Every value the agent writes passes guard_value() first, so the guarantees hold
whatever the model decides: self-identification questions (disability, veteran
status, race, gender) can be declined but never affirmed, sanctions and
restricted-country questions always take the safe answer, and placeholder text
never reaches a field. A refusal is enforced in code, not requested in a prompt.
Instructions
Step 1: Apply
Call apply_to_job(). It returns one of:
{"status": "applied", "confirmation": ...}— a real submission was confirmed (confirmation text or a confirmation redirect). Report it; you're done.{"status": "gate", "reason": ..., "question": ...}— a genuine blocker:unknown_field(a required field with no approved answer),no_account(login/signup wall), orcaptcha.{"status": "failed", "reason": ..., "detail": ...}— a real block:duplicate_application,application_limit,already_applied, or aguardrailrefusal. Close it out; do not retry.{"status": "uncertain" | "unknown", "detail": ...}— the submit could not be confirmed (e.g. the browser was closed, or the run ended with no confirmation on the page). It did NOT resubmit.
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.
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.
- 9d ago First seen · 80 lines · 84 tokens per session scan A 3b6d89ed354c
application-filling is a skill published in the GitHub repository sayantan94/AppliedIn (7 stars, last pushed yesterday), licensed MIT. It adds 84 tokens to every session and 1,039 once invoked, about $0.0004 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
opencli-sitemap-author
Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
interactive-login
How to complete browser/interactive logins (aws / gh / glab / gcloud). The platform backgrounds the login poller so it survives the human's browser round-trip — and when that does NOT work.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
azure-messaging-webpubsub-java
Build real-time web applications with Azure Web PubSub SDK for Java. Use when implementing WebSocket-based messaging, live updates, chat applications, or server-to-client push notifications.
google-safe-browsing
Prevent and fix Google Safe Browsing "Dangerous site" flags. Use when launching a public web app, buying/picking a domain, building a login or signup page, or when any site shows a red "Dangerous site" / "Deceptive site" warning in Chrome, Brave, Safari, Firefox, or Edge. Triggers on "dangerous site", "deceptive…