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 muggl3mind/career-manager --skill job-searchgit clone --depth 1 https://github.com/muggl3mind/career-managerWrote 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/muggl3mind/career-manager/job-search)<a href="https://agentmods.dev/skills/muggl3mind/career-manager/job-search"><img src="https://agentmods.dev/badge/skills/muggl3mind/career-manager/job-search/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/muggl3mind/career-manager/job-search"><img src="https://agentmods.dev/badge/skills/muggl3mind/career-manager/job-search.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 | $0.00051 | $0.04323 |
| Opus 5.5 | $0.00020 | $0.01729 |
| Sonnet 5.5 | $0.00010 | $0.00865 |
| Haiku 4.5 | $0.00005 | $0.00432 |
Grade A, and why
job-search 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 27d 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 — 230 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Job Search
Data hub and scripts for the job search pipeline. Three-phase workflow: Python exports, Claude agent research, Python merges.
Data Files (source of truth)
{baseDir}/data/target-companies.csv— Researched companies with scores (0-100) and company lifecycle{baseDir}/data/opportunities.csv— Actionable role-level opportunities generated from target companies{baseDir}/data/cv-index.json— Maps role types to resume versions- Note:
applications.csvis owned by siblingjob-trackerskill
Scripts
scripts/core/ (utilities)
| Script | Purpose |
|---|---|
scripts/core/todoist_client.py |
Todoist API client wrapper |
scripts/core/cv_index_resolver.py |
Portable CV index path resolution |
scripts/ops/ (pipeline operations)
| Script | Purpose |
|---|---|
scripts/ops/run_pipeline.py |
Orchestrator — runs full pipeline |
scripts/ops/discovery_pipeline.py |
JobSpy discovery, filter, eval export |
scripts/ops/evaluate_jobs.py |
Cache check + pending-eval export |
scripts/ops/apply_eval_results.py |
Merge eval-results.json into CSV |
scripts/ops/web_prospecting.py |
Company discovery — export context + merge |
scripts/ops/monitor_watchlist.py |
Re-check known companies for new roles |
scripts/ops/pipeline_health.py |
Pipeline quality checks |
scripts/ops/pipeline_followup_top3.py |
Follow-up shortlist generation |
Execution Playbook
Run all phases continuously. Do not pause between phases or ask the user to run commands.
Phase 1 — Python exports + discovery
uv run job-search/scripts/ops/run_pipeline.py phase1
uv run job-search/scripts/ops/run_pipeline.py phase1 --skip-jobspy # faster, skip job board scrape
When phase1 exits 0, immediately launch the Wave 1 agents (next section) in the same turn — no pause, no confirmation prompt.
Agent Work — parallel sub-agent dispatch
Wave 1: Use the Agent tool to launch sub-agents in parallel: one Eval agent, one Monitor agent, and one Prospecting agent per career path (one per prospecting-context-{path_key}.json file in the data directory). Make all Agent tool calls in a single response so they run concurrently.
What ships with it
35 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.
- data/.gitkeep 0 B
- data/search-config.json 1.2 KB
- data/search-config.json.example 10 KB
- scripts/core/company_dedup.py 4.6 KB runs code
- scripts/core/csv_io.py 2.4 KB runs code
- scripts/core/csv_schema.py 1.1 KB runs code
- scripts/core/cv_index_resolver.py 1.8 KB runs code
- scripts/core/flags.py 2.4 KB runs code
- scripts/core/merge_validation.py 12 KB runs code
- scripts/core/migrate_csv_columns.py 2.5 KB runs code
- scripts/core/opportunities.py 16 KB runs code
- scripts/core/path_normalizer.py 2.5 KB runs code
- scripts/core/scoring.py 5.5 KB runs code
- scripts/core/search_config_loader.py 2.4 KB runs code
- scripts/core/send_email.py 4.5 KB runs code
- scripts/core/target_companies_sync.py 5.6 KB runs code
- scripts/core/tavily_client.py 4.4 KB runs code
- scripts/core/test_company_dedup.py 8.8 KB runs code
- scripts/core/todoist_client.py 5.6 KB runs code
- scripts/ops/apply_eval_results.py 17 KB runs code
- scripts/ops/dashboard_views.py 8.7 KB runs code
- scripts/ops/discovery_pipeline.py 19 KB runs code
- scripts/ops/evaluate_jobs.py 8.6 KB runs code
- scripts/ops/fix_careers_urls.py 2.3 KB runs code
- scripts/ops/generate_dashboard.py 67 KB runs code
- scripts/ops/merge_research.py 12 KB runs code
- scripts/ops/migrate_lifecycle_columns.py 3.6 KB runs code
- scripts/ops/monitor_watchlist.py 32 KB runs code
- scripts/ops/pipeline_followup_top3.py 833 B runs code
- scripts/ops/pipeline_health.py 9.2 KB runs code
- scripts/ops/run_pipeline.py 19 KB runs code
- scripts/ops/test_discovery_scoring_gate.py 7.4 KB runs code
- scripts/ops/web_prospecting.py 44 KB runs code
- scripts/requirements.txt 113 B
- templates/follow-up-email.md 3.0 KB
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.
- 27d ago Changed · +2 lines 35f7d1b75e38
- 28d ago Changed · +5 lines f80fe8d8d0ef
- 1mo ago First seen · 223 lines · 51 tokens per session scan A 520eb5eca4d9
job-search is a skill published in the GitHub repository muggl3mind/career-manager (24 stars, last pushed 27d ago), licensed MIT. It adds 51 tokens to every session and 4,323 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
amlei-portfolio
A workflow for creating and checking a job portfolio: a collection of project case studies and evidence for employers. It selects real work, explains the person's contribution and decisions, and links claims to supporting material.
amlei-resume
A resume-writing and job-application workflow that helps create, revise, assess, and export a resume as an A4 PDF. It can also prepare a short greeting for job platforms such as Boss Zhipin.
job-matcher
A workflow that turns a résumé and job preferences into an interactive HTML report of matching jobs. A résumé is a document describing someone’s experience, skills, and education.
cv-resume-builder
Optimize resumes and CVs for impact, ATS compatibility, and audience targeting. Supports multiple formats (chronological, functional, hybrid), accomplishment framing (STAR/XYZ), and tailoring for specific roles. Triggers on resume review, CV update, job application prep, or career document requests.
job-navigation-skill
Research current job markets and hiring requirements, analyze recent job descriptions, compare them with a user's resume, projects, skills, and constraints, and turn the gaps into prioritized career actions. Use for students, job seekers, and career changers who need industry or role trends, cross-platform JD…
cv-creator
Professional CV and resume builder transforming career narratives into ATS-optimized, multi-format resumes. Integrates with career-biographer for data and competitive-cartographer for positioning. Generates PDF, DOCX, LaTeX, JSON Resume, HTML, and Markdown. Activate on 'resume', 'CV', 'ATS optimization', 'job…