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 benskamps/career-compass-mcp --skill todaygit clone --depth 1 https://github.com/benskamps/career-compass-mcpWrote 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/benskamps/career-compass-mcp/today)<a href="https://agentmods.dev/skills/benskamps/career-compass-mcp/today"><img src="https://agentmods.dev/badge/skills/benskamps/career-compass-mcp/today/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/benskamps/career-compass-mcp/today"><img src="https://agentmods.dev/badge/skills/benskamps/career-compass-mcp/today.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 | $0.00029 | $0.00625 |
| Opus 5.5 | $0.00012 | $0.00250 |
| Sonnet 5.5 | $0.00006 | $0.00125 |
| Haiku 4.5 | $0.00003 | $0.00063 |
Grade A, and why
today 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 2d 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.
What it actually says
The user wants today's job-search digest: the one thing to do first, then the rest.
- If the Career Compass tools are available, call
pipeline_viewwithaction: "next_actions". It returns a ranked digest: a "Start here" move, the rest of today's list, and what is coming up. Lead with the Start here move in a sentence or two and offer to do its first step right now (draft the check-in, build the interview prep, review the offer). Then the other items, one line each with its action. Keep the whole reply short enough to read over coffee, and don't pad it with generic job-search advice. - Never change a status, date or note on your own. Where the digest suggests one (mark a
silent application ghosted, record where an offer stands, set a follow-up date), offer
the exact
pipeline_updateand make it only after the user says yes. - If nothing is due, say so in one line, name the "📅 Next up" date when the digest has one, and suggest one forward move such as tracking a new role. Don't invent work.
- If the result ends with "↩️ Since you were last here", open with what is new since their last visit in one line, then the digest as usual.
- If the pipeline is empty, say so in one line and ask for one thing: "Tell me one role
you've applied to or are considering (company and title) and I'll start tracking it."
That is the whole reply. When they answer, show the
pipeline_addcalls as one batch, make them after one yes, then give the first digest (pipeline_viewnext_actions) in the same reply. Since these were their first applications, end with the career-compass skill's one-time morning briefing offer. - If the search has ended in an accepted offer, offer the career-compass skill's landing mode (this week's wins) instead of tracking new roles.
- If the tools are not available (usually claude.ai chat), don't explain setup. If they pasted a Career Compass card or a list of applications, rank it as the career-compass skill's chat method says. If not, ask for one thing: "Paste your Career Compass card, or list your applications (company, role, date applied, last contact), and I'll tell you what to do first." At the end, offer the card if they don't have one yet.
$ARGUMENTS
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.
- 2d ago Changed · +3 lines b094b29ca0e4
- 3d ago Changed · +1 lines 755c524a6432
- 4d ago Changed · +7 lines d52805620281
- 5d ago Changed · +10 lines a6ac07ae2743
- 8d ago First seen · 19 lines · 29 tokens per session scan A e727d03fa683
today is a skill published in the GitHub repository benskamps/career-compass-mcp (6 stars, last pushed today), licensed MIT. It adds 29 tokens to every session and 625 once invoked, about $0.0001 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 2026-10-03.
Other skills, from other repositories
kochab
Kochab, a personalized resume-based job-search assistant that runs a recurring scan and everything downstream of it. Use when the user wants to start or run a job search, shares a resume, or says "set up my job scan," "find roles that fit my resume," or "what should I apply to." Also use to tailor a resume, draft a…
interviewing
Use when the user gets an interview invitation, moves into an interview process, wants to track interview stages, capture post-interview notes, draft follow-up messages, or update an application to interviewing.
get-started
Use when the user is new to Job Hunt Skills and wants to see what it does or set up their workspace — including "I'm new to Job Hunt Skills", "help me get started", "set me up", "first time using this", "here's my resume, tailor it for this job", "can you look at my resume", pasting a resume and a job posting…
yc-job-tracker
Track and filter YC startup job listings for AI/ML engineering roles. Builds a daily-refreshed local database of relevant jobs with scoring and alerts for new postings.
Job Description Analyzer
Analyze job postings, calculate match scores, identify gaps, and create application strategy.
opportunity-brief
Research a company and a specific role, then produce an honest brief on whether it is worth pursuing. Use this whenever the user mentions a recruiter reaching out, a job posting they found, a company someone told them about, or a role they are weighing. Triggers on "a recruiter contacted me," "should I apply to,"…