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 agentmods add skills/sma1lboy/coforce-apply/applynpx skills add Sma1lboy/coforce-apply --skill applygit clone --depth 1 https://github.com/Sma1lboy/coforce-applyWrote 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/sma1lboy/coforce-apply/apply)<a href="https://agentmods.dev/skills/sma1lboy/coforce-apply/apply"><img src="https://agentmods.dev/badge/skills/sma1lboy/coforce-apply/apply.svg" alt="Measured on agentmods" 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 | $0.00057 | $0.01987 |
| Opus 5 | $0.00028 | $0.00993 |
| Sonnet 5 | $0.00011 | $0.00397 |
| Haiku 4.5 | $0.00006 | $0.00199 |
Grade A, and why
apply 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 5d 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 — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Apply — Chrome-backed job application
Input: a job posting / application URL (from args). Expect a non-trivial form: multi-step wizard, custom widgets, an ATS (Workday, Greenhouse, Lever, Ashby…), or login walls.
Setup (first run, answers persist in ~/.coforce/config.json)
Before the first application, ask ONCE and merge these keys into the flat
~/.coforce/config.json (setup owns the rest of that file — never overwrite
it with just these):
{
"email": "[email protected]", // account email for ATS registrations
"autoRegister": true, // may I create ATS accounts for you?
"mailboxAccess": "browser | paste", // how to fetch verification codes
"resumePdf": "path/to/resume.pdf",
"headlessApply": false // explicit consent; setup manages this
}
Subsequent runs read this file and only ask about gaps.
This skill is the operator in the operator contract
(docs/OPERATOR.md in the CoForce repo): inputs are job + profile + resume +
intent, progress is reported as COFORCE_STATUS sentinels, and the iron laws
(never cross the confirmation gate, never fabricate screening answers,
instructions.md overrides everything) bind every run.
Preconditions
- Read
~/.coforce/instructions.md— standing user instructions (never-apply companies, preferences). It overrides everything below; a never-apply company means stop and tell the user, not apply anyway. - Read
~/.coforce/profile.json. Missing → run theprofileskill's init first; don't guess values. - Read
~/.coforce/config.json— canonical user intent plus runtime config (workAuthorization,needsSponsorship, work mode, locations, and the Setup answers above). Screening answers about visa/sponsorship come from here, never invented. Missing (and no legacyapply-config.json/preferences.jsonfor the loader to fold in) → run Setup above. Batch any remaining per-job questions up front; don't drip.
Flow
- Initialize Claude in Chrome from inside this skill (
--chromeor/chrome) and open the URL in visible Chrome. Do not substitute the in-app Browser, Computer Use, or a second Playwright runtime for this workflow. If Chrome is unavailable, stop and report the setup/connection blocker. - Navigate to the actual application form (click "Apply" through interstitials).
If the ATS demands an account (Workday, iCIMS, SuccessFactors…) and
autoRegisteris true, register one — see Account registration below. - Fill every field mappable from the profile: contact info, links, education,
experience. Upload the resume PDF where a file input exists.
Resume resolution: a campaign resume for this job wins; otherwise, if
the user didn't hand over a specific PDF, run the
tailorskill against this JD first and upload its~/.coforce/out/resume-<company>-<role>.pdf. The staticresumePdfin config.json is the last resort, not the default. - Free-text questions ("why us", cover letter): draft 2–4 sentences from the
profile tailored to the posting — factual, no invented experience. Check
~/.coforce/research/<company>.jsonfirst (company-research cache; schema in theinterviewskill, 30-day TTL) for a verified company angle to ground the "why us" in; a cache hit is a lead, so re-check any specific claim against its recorded source URL before it lands in an answer. Show drafts to the user before submitting if they're required fields. - Stop before the final submit and show a summary of what was entered. Submit only after the user confirms. Submission is irreversible.
- Report the outcome (confirmation page / email signal), record it in the
local tracker (
~/.coforce/applications.json, per thetrackerskill — add or update the entry with the final status), then serve/refresh the board per thetrackerskill and open it so the user sees the updated state without asking.
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.
- 5d ago First seen · 156 lines · 57 tokens per session scan A 837618142c63
apply is a skill published in the GitHub repository Sma1lboy/coforce-apply (5 stars, last pushed 6d ago), licensed MIT. It adds 57 tokens to every session and 1,987 once invoked, about $0.0003 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
v8-jit
V8 JIT optimization patterns for writing high-performance JavaScript in Next.js server internals. Use when writing or reviewing hot-path code in app-render, stream-utils, routing, caching, or any per-request code path. Covers hidden classes / shapes, monomorphic call sites, inline caches, megamorphic deopt, closure…
use-agent-browser-for-airi
Test AIRI display-model imports with agent-browser across stage-tamagotchi Electron, stage-web, and stage-pocket mobile web layouts. Use when uploading and verifying contributor-supplied Live2D ZIP, VRM, or MMD ZIP/PMX/PMD files through AIRI's model selector, including onboarding bypass, format-specific import…
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…
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
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.