Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/MelonS/MelonS-Agentsnpx agentmods add skills/melons/melons-agents/job-huntWrote 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/melons/melons-agents/job-hunt)<a href="https://agentmods.dev/skills/melons/melons-agents/job-hunt"><img src="https://agentmods.dev/badge/skills/melons/melons-agents/job-hunt.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00000 | $0.02710 |
| Opus 5 | $0.00000 | $0.01355 |
| Sonnet 5 | $0.00000 | $0.00542 |
| Haiku 4.5 | $0.00000 | $0.00271 |
Grade A, and why
job-hunt scanned grade A with 1 finding 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 8d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
compatibility: Requires `bash`, `curl`, `jq`, optional `pup` or `python3` for HTML parsing depending on source. Per-source authentication varies — see `sources/<name>.sh` headers. macOS or Linux. Live scraping not yet im How it starts
The opening of the file, as written. The whole thing — 203 lines — stays where its author put it; the contents beside it link to each section on GitHub.
job-hunt
Daily / on-demand digest of new job postings matched against an operator-defined filter (직군 + 지역 + 키워드), with apply-assist links per posting.
Status (2026-05-20)
End-to-end pipeline functional in mock-fallback mode, with the
v2 short-keyword UX (--seed "Problem Solver" → automatic role
family expansion via config/role-synonyms.yaml) wired in. Live
HTTP integration is gated on operator validation per source.
| Component | Status |
|---|---|
Orchestrator (scripts/run.sh) |
✅ wired; filter + dedupe + diff + render + --fit-score integration |
Markdown digest renderer (scripts/digest.sh) |
✅ working; fit-score line per posting |
Apply-assist link derivation (scripts/apply-assist.sh) |
✅ working |
config/role-synonyms.yaml |
✅ Phase 2.1 — 5 families, 50+ synonyms (problem-solver, ai-engineer-ml, agent-engineer, ai-product-manager, backend-engineer) |
config/operator-profile.example.md |
✅ Phase 2.2 — generic template (operator copies → operator-profile.md, gitignored) |
sources/_mock.sh |
✅ deterministic 11-posting fixture incl. Problem Solver family |
sources/global-ats.sh |
⭐ live-ready — Greenhouse + Ashby + Lever public boards, no auth; 2026-05-21 e2e test pulled 5,019 raw / 171 Problem-Solver-matched postings; flip JH_GLOBAL_ATS_LIVE=1 |
sources/global-remoteok.sh |
⭐ live-ready — remoteok.com/api, no auth; 99 raw postings on test fetch; flip JH_GLOBAL_REMOTEOK_LIVE=1 |
sources/global-remotive.sh |
⭐ live-ready — remotive.com/api/remote-jobs, no auth; 19 raw postings; flip JH_GLOBAL_REMOTIVE_LIVE=1 |
sources/global-hn-whoshiring.sh |
⭐ live-ready — HN monthly "Who is hiring?" thread via hn.algolia.com; 334 postings on May 2026 thread; flip JH_GLOBAL_HN_LIVE=1 |
sources/kr-worknet.sh |
⭐ live-ready — 워크넷 (정부 공공고용서비스); SSR HTML parser, 10-20 postings/page; flip JH_WORKNET_LIVE=1 |
sources/kr-wanted.sh |
⚠️ mock-fallback default + 1 Problem Solver entry; live HTTP flip via JH_WANTED_LIVE=1 + WANTED_API_KEY (operator-validated) |
sources/kr-saramin.sh |
⚠️ mock-fallback default + 1 문제 해결사 entry; live OpenAPI flip via JH_SARAMIN_LIVE=1 + SARAMIN_KEY (free signup at oapi.saramin.co.kr) |
sources/kr-jobkorea.sh |
⛔ permanent mock-only — robots.txt forbids /Search/?stext= (only SSR path); 2017 잡코리아 vs 사람인 precedent applies. See docs/research/job-sources-survey-2026-05-21.md. |
sources/kr-programmers.sh |
⛔ deprecated stub — Programmers 채용 service permanently closed 2025-05-19, domain NXDOMAIN |
scripts/fit-score.sh |
⚠️ Phase 2.3 — scaffold mode default; per-posting Claude call gated on JH_FIT_SCORE_LIVE=1 |
scripts/cover-letter-draft.sh |
⚠️ Phase 2.5 — scaffold mode default; gated on JH_COVER_LETTER_LIVE=1 |
scripts/company-research.sh |
⚠️ Phase 2.5 — scaffold mode default; gated on JH_COMPANY_RESEARCH_LIVE=1 |
scripts/interview-prep.sh |
⚠️ Phase 2.5 — scaffold mode default; gated on JH_INTERVIEW_PREP_LIVE=1 |
scripts/derive-profile.sh |
⚠️ Phase 2.4 — scaffold mode default; reads repo and drafts operator-profile.md; gated on JH_DERIVE_PROFILE_LIVE=1 |
tests/smoke.sh + edge-cases.sh + schema-validation.sh |
✅ 68/68 PASS (32 + 26 + 10) |
What ships with it
33 files 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.
- config/activation.tsv 1.9 KB
- config/ats-boards.example.yaml 2.8 KB
- config/filters.example.yaml 2.9 KB
- config/operator-profile.example.md 6.4 KB
- config/role-synonyms.yaml 5.5 KB
- data/company-tiers.yaml 2.1 KB
- scripts/apply-assist.sh 2.2 KB runs code
- scripts/company-research.sh 5.4 KB runs code
- scripts/cover-letter-draft.sh 5.5 KB runs code
- scripts/derive-profile.sh 6.3 KB runs code
- scripts/digest.sh 4.7 KB runs code
- scripts/fit-score.sh 9.2 KB runs code
- scripts/interview-prep.sh 6.6 KB runs code
- scripts/run.sh 23 KB runs code
- scripts/status.sh 3.5 KB runs code
- sources/_mock.sh 4.8 KB runs code
- sources/global-ats.sh 8.3 KB runs code
- sources/global-hn-whoshiring.sh 6.3 KB runs code
- sources/global-remoteok.sh 3.0 KB runs code
- sources/global-remotive.sh 3.1 KB runs code
- sources/kr-jobkorea.sh 2.6 KB runs code
- sources/kr-programmers.sh 1.8 KB runs code
- sources/kr-rallit.sh 4.2 KB runs code
- sources/kr-saramin.sh 6.1 KB runs code
- sources/kr-theteams.sh 7.6 KB runs code
- sources/kr-wanted.sh 5.7 KB runs code
- sources/kr-worknet.sh 6.1 KB runs code
- sources/README.md 4.1 KB
- sources/source-plugin.schema.json 3.6 KB
- tests/edge-cases.sh 8.4 KB runs code
- tests/run-all.sh 1.4 KB runs code
- tests/schema-validation.sh 2.7 KB runs code
- tests/smoke.sh 5.9 KB runs code
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.
- 8d ago First seen · 203 lines · 0 tokens per session scan A 34f002b13e7d
job-hunt is a skill published in the GitHub repository MelonS/MelonS-Agents (16 stars, last pushed 17d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,710 tokens. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
hive.slack-notifications-setup
Set up a Slack notification channel (Sentinel) for a colony by driving the browser — reuse or create the "Hive Sentinel" Slack app from a JSON manifest, install it, capture the bot + app tokens, create/select the channel via the Slack API, and turn Sentinel on so the colony can ping the user on Slack and accept…
browser-edge-cases
SOP for debugging browser automation failures on complex websites. Use when browser tools fail on specific sites like LinkedIn, Twitter/X, SPAs, or sites with Shadow DOM.
hive.pdf
Read, write, merge, split, rotate, watermark, encrypt, and OCR PDF files using Python (pypdf, pdfplumber, reportlab, pypdfium2) and command-line tools (poppler-utils, qpdf). Use when the user asks to extract text/tables/images from a PDF, create or modify a PDF, combine or split PDFs, OCR a scanned PDF…
article-writer
Multi-style article creation skill. Supports 5 writing styles (deep analysis, practical guide, story-driven, opinion, news brief), including complete workflow: material collection → outline → content → formatting. Activated when users mention "write article", "write post", "create", or "draft".
skin-creator
Create and apply a two-asset LobsterAI visual skin from the user's style description. Use only when the AI Skin Designer kit supplies the structured skinpack workflow marker; do not use for ordinary theme or image requests.
content-planner
WeChat Official Account topic planning and content calendar management. Based on WeChat article search and trending analysis, generates differentiated topic recommendations and outputs structured content calendars. Activated when users mention "topic", "planning", "content calendar", "trending", or "what to write next…