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 suxrobGM/jobpilot --skill solve-captchagit clone --depth 1 https://github.com/suxrobGM/jobpilotWrote 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/suxrobgm/jobpilot/solve-captcha)<a href="https://agentmods.dev/skills/suxrobgm/jobpilot/solve-captcha"><img src="https://agentmods.dev/badge/skills/suxrobgm/jobpilot/solve-captcha/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/suxrobgm/jobpilot/solve-captcha"><img src="https://agentmods.dev/badge/skills/suxrobgm/jobpilot/solve-captcha.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Data Exfiltration · line 51 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Excessive Agency · line 81 Skill allows unbounded resource consumption (API calls, storage, compute). Without rate limits or quotas, a compromised or misbehaving agent can cause denial-of-service or cost overruns.Fix: Set explicit rate limits, timeouts, and resource quotas for API calls, file operations, and compute. Implement circuit breakers for runaway loops.
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 | $0.00040 | $0.00976 |
| Opus 5.5 | $0.00016 | $0.00390 |
| Sonnet 5.5 | $0.00008 | $0.00195 |
| Haiku 4.5 | $0.00004 | $0.00098 |
Grade A, and why
solve-captcha 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 28d 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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Solve CAPTCHA
Clear a CAPTCHA on the current browser tab. Return solved or unsolved (the caller falls back). Authorized use only - the user's own applications. Call the API with jobpilot-api (../_shared/setup.md "Calling the API").
1. Dispatch + identify
If the argument is a URL → browser_navigate there first. browser_resize to a tall viewport (1280×1400) so the widget is fully on-screen, then browser_snapshot + browser_take_screenshot the captcha and classify:
- checkbox (reCAPTCHA "I'm not a robot" / hCaptcha / Turnstile) → §2. Always try this first - it escalates to the service only if it opens an image challenge.
- text (distorted characters + answer field) → §3.
- image-grid already open (no checkbox to click) → §4 directly.
- slider / unknown → unsolved.
2. Checkbox (free, first)
browser_click the control by ref, browser_wait_for, re-snapshot. Verified → solved. An image grid opened instead → escalate to §4. Never hand-click tiles - automated clicks get flagged and fail.
3. Text (free)
browser_take_screenshot, read the characters, browser_type the answer, submit. Verified → solved.
4. Image-grid → token service
Read the sitekey (browser_evaluate, read-only):
() => {
const el = document.querySelector(".g-recaptcha, [data-sitekey]");
let key = el?.getAttribute("data-sitekey");
if (!key) {
const f = [...document.querySelectorAll('iframe[src*="recaptcha"]')]
.map((f) => f.src)
.find((s) => /[?&]k=/.test(s));
key = f && new URL(f).searchParams.get("k");
}
return { sitekey: key, pageurl: location.href };
};
hCaptcha: iframe[src*="hcaptcha"] → type:"hcaptcha". Turnstile: .cf-turnstile[data-sitekey] → type:"turnstile".
Solve it server-side (the endpoint resolves the configured key + polls the provider; the skill never sees the key):
jobpilot-api POST /api/captcha/solve --data '{"type":"recaptcha","sitekey":"<sitekey>","pageurl":"<pageurl>"}'
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.
- 28d ago Changed · -2 lines 5318903fb8af
- 1mo ago First seen · 85 lines · 40 tokens per session scan A 46344688f701
solve-captcha is a skill published in the GitHub repository suxrobGM/jobpilot (102 stars, last pushed yesterday), licensed MIT. It adds 40 tokens to every session and 976 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 2026-08-30.
Other skills, from other repositories
ww-upload-cover-letter
Upload a PDF cover letter from the coverletter/ folder (typically coverletter/Company-coverletter.pdf produced by ww-write-cover-letter) into a required WaterlooWorks Cover Letter document slot during the Full-Cycle Service Submit Application workflow. Use when a WaterlooWorks application package requires Cover…
recheck-statuses
Use when the user wants to verify which Job Search HQ vacancies are still live vs closed / deleted. Triggers: /recheck-statuses, "check dead listings", "clean closed roles", "are these still open?", "refresh statuses". Walks data/vacancies.json, opens each URL (webfetch first, Chrome fallback for auth-gated), and…
ww-login
Restore a WaterlooWorks Chrome session when Codex is viewing or applying to WaterlooWorks jobs and lands on recoverable logged-out states such as notLoggedIn.htm, WaterlooWorks - Not Logged In, the WaterlooWorks home page, or waterloo.htm?action=login. Use before asking the user to log in; stop and ask only when…
test-site
Tests a deployed, activated Power Pages site at runtime using browser-based navigation, page crawling, and API request verification via Playwright. Use when the user wants to test, verify, or smoke-test their deployed site.
preview-screens
Use when the user wants to preview generated screens in a browser without starting Metro / a simulator — for example after /create-mobile-app finishes or after /edit-app regenerates a screen.
qa
Browser-based QA verification. Launches a real browser, navigates the app, clicks buttons, fills forms, and tests user flows. Works as a standalone skill or as a phase end condition in campaigns. Requires Playwright (optional dependency, graceful skip if not installed).