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 agentmods add commands/madslorentzen/ai-job-search/expandgit clone --depth 1 https://github.com/MadsLorentzen/ai-job-searchWhat 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 | $0.00000 | $0.01919 |
| Opus 5 | $0.00000 | $0.00959 |
| Sonnet 5 | $0.00000 | $0.00384 |
| Haiku 4.5 | $0.00000 | $0.00192 |
Grade A, and why
expand 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.
How it starts
The opening of the file, as written. The whole thing — 217 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/expand - Competency Expansion from Documents and Online Presence
You are enriching the candidate profile by discovering competencies hidden in documents and public online presence. This command is additive only — it never modifies existing profile content, only extends it.
Follow these steps exactly in order. Do not skip steps.
Step 0: Read Existing Profile Files
Read these two files in parallel before doing anything else. You must know what is already there so you do not propose duplicates.
.claude/skills/job-application-assistant/01-candidate-profile.md.claude/skills/job-application-assistant/02-behavioral-profile.md
Hold this content in context throughout the command. Do not re-read these files later.
Step 1: Discovery — Scan All Sources
Scan every available source for "experience items" — anything that implies skill, knowledge, or competency. Process sources in this order.
1a. documents/cv/
Read all files in documents/cv/. Extract:
- Every course or module listed (including university coursework and online courses)
- Every certification mentioned, with issuer and date
- Every job responsibility bullet point (tools, methods, outcomes)
- Every independent project or side project
- Every volunteer or extracurricular role
1b. documents/linkedin/
Read all files in documents/linkedin/. Extract:
- Courses and certifications in the "Licenses & Certifications" section
- Skills and endorsements list
- Volunteer experiences
- Projects section
- Any platform-specific items not already found in the CV
1c. documents/diplomas/
Read all files in documents/diplomas/. Extract:
- All course/module names listed on transcripts
- Thesis title and subject area
- Any specialisation or track name
1d. documents/references/
Read all files in documents/references/. Extract:
- Competency language used by the referee (what skills or qualities they mention)
- Any specific projects, tools, or methods named
1e. GitHub Profile
Look up the GitHub username from 01-candidate-profile.md. If a GitHub URL or username is present:
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 First seen · 217 lines · 0 tokens per session scan A 5e5dccdda221
expand is a command published in the GitHub repository MadsLorentzen/ai-job-search (39,400 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,919 tokens. 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 commands, from other repositories
resume
Generate a tailored resume and cover letter from a job description, score both, create DOCX files, and update the tracker.
resume-team
Run the role-separated, fail-closed Resume Team workflow against a job description.
writing-coach
Human-voice writing coach — rewrite resumes and cover letters with brevity, burstiness, plain language, and authentic impact. Blocks AI-sounding prose.
cover-letter
Create a one-page cover letter for a job description and generate the final DOCX.
find-jobs
Search live job boards for roles that match the master resume, then rank them by fit.
job-fit
Run the deterministic, digest-bound candidate-fit gate before any resume tailoring.