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 surfmind-space/awesome-surfmind --skill job-fit-reviewgit clone --depth 1 https://github.com/surfmind-space/awesome-surfmindWrote 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/surfmind-space/awesome-surfmind/job-fit-review)<a href="https://agentmods.dev/skills/surfmind-space/awesome-surfmind/job-fit-review"><img src="https://agentmods.dev/badge/skills/surfmind-space/awesome-surfmind/job-fit-review/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/surfmind-space/awesome-surfmind/job-fit-review"><img src="https://agentmods.dev/badge/skills/surfmind-space/awesome-surfmind/job-fit-review.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 | $0.00068 | $0.01023 |
| Opus 5 | $0.00034 | $0.00511 |
| Sonnet 5 | $0.00014 | $0.00205 |
| Haiku 4.5 | $0.00007 | $0.00102 |
Grade A, and why
job-fit-review 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.
How it starts
The opening of the file, as written. The whole thing — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Job Fit Review
Review the selected text, visible page, or pasted job description as a career decision aid. Work only from what the user gave you or what's visible on the page — don't invent experience, metrics, employers, credentials, work authorization, salary expectations, or availability, and don't submit applications, alter forms, or declare a posting fake; present evidence and let the user decide. Use web search or browser tools when current compensation, company news, layoffs, hiring freezes, or posting liveness matter. Adapted from santifer/career-ops oferta mode.
- Confirm the posting appears active before the full review. If the page says expired, closed, no longer accepting applications, redirects to a generic careers page, or lacks a real job description, stop and say the posting looks inactive.
- Classify the role by archetype when useful (platform, LLMOps, agentic automation, product, solutions architecture, forward-deployed, transformation, or another clear fit), then map the posting's requirements to the user's provided experience.
- Separate hard blockers from nice-to-have gaps. For each gap, suggest an honest mitigation: adjacent evidence, a portfolio proof point, a phrase for the application, or a question for the recruiter.
- Read the level and plan strategy. Compare the posting's target level against the user's natural level; position seniority honestly with real achievements, and if the company downlevels, advise accepting only when compensation is fair and negotiating a defined review window with clear promotion criteria. Never advise overstating a title or scope.
- Check legitimacy signals without making accusations, then settle on one tier — High confidence, Proceed with caution, or Suspicious. Weigh posting age, active apply controls, description specificity, inconsistent requirements, reposting clues, salary transparency, and recent hiring news. Account for fair context: government, academic, executive, and niche roles legitimately stay open for months; evergreen postings are pipelines, not ghosts; a recruiter-only posting has no public freshness signal. Never default to Suspicious without evidence.
- Suggest the top resume, LinkedIn, or application customizations, grounded in the job description and the user's actual background, then build a short interview prep plan: likely themes, STAR story prompts, risks to prepare for, and questions to ask back.
Return these sections when they fit: Role snapshot, Fit with your background, Gaps and mitigations, Level and strategy, Compensation and demand signals, Posting legitimacy (High confidence, Proceed with caution, or Suspicious), Customization plan, Interview prep, and Recommendation. End on exactly one recommendation — Apply now, Apply with caveats, Research first, or Skip — explained briefly. Preserve names, numbers, dates, titles, links, and technologies exactly; mark uncertain facts as uncertain and label search-derived claims with sources. If the user hasn't shared a resume or career profile, review the posting on its own and list the profile details needed for a stronger assessment.
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.
- 12d ago First seen · 43 lines · 68 tokens per session scan A d926cbfc62ee
job-fit-review is a skill published in the GitHub repository surfmind-space/awesome-surfmind (5 stars, last pushed 1mo ago), licensed MIT. It adds 68 tokens to every session and 1,023 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
cs-master
Expert computer scientist for algorithms, complexity analysis, and distributed systems.
uiux-master
UI/UX expert for design systems, accessibility, and avoiding generic AI-generated design patterns.
c-master
C programming expert for memory management, systems programming, and performance optimization.
data-science
ML engineering expert for feature engineering, model debugging, and production pipelines.
go-master
Go expert for goroutines, channels, microservices, and concurrent patterns.
network-devops
Network performance expert for latency optimization, packet analysis, and infrastructure tuning.