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 skills/alwaysmap/jobs4me/prepnpx skills add alwaysmap/jobs4me --skill prepgit clone --depth 1 https://github.com/alwaysmap/jobs4meWhat 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 | $0.00080 | $0.01899 |
| Opus 5 | $0.00040 | $0.00949 |
| Sonnet 5 | $0.00016 | $0.00380 |
| Haiku 4.5 | $0.00008 | $0.00190 |
Grade A, and why
prep 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 — 176 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Interview Prep Generator
Create research documents that help the user walk into an interview with company context and pre-mapped case studies.
When to Trigger
- User explicitly asks for interview prep
- User moves a role to
interviewingstage - User says they have a phone screen or interview coming up
Workflow
-
Read
profile.yamlandtracker.yaml -
Find the application matching the company name:
node ${CLAUDE_PLUGIN_ROOT}/scripts/tracker.js find --company "Company Name"If multiple roles are returned for the same company, list them with role titles and stages and ask which one:
I found two roles at Google:
- Staff Engineer (maybe)
- Engineering Manager (interviewing)
Which one are you prepping for?
-
Get file paths for the chosen application:
node ${CLAUDE_PLUGIN_ROOT}/scripts/tracker.js paths --id <id>This returns
company_dir,role_dir, and current file locations. -
If a JD exists (check
has_jdfrom paths output), read it. If not, ask the user for the job posting URL and fetch it. -
Read the user's evidence: fetch resume URL if provided, read portfolio URLs, read additional context.
-
Generate the two documents below.
-
Save files to the company structure:
- Company Overview →
{company_dir}/overview.md(shared across roles at this company) - Interview Prep →
{role_dir}/prep.md(role-specific) Create directories withmkdir -pif they don't exist.
- Company Overview →
-
Update the application's stage to
interviewingintracker.yamlif it isn't already. -
Show the user what was created. After saving, present the documents inline:
Company Overview —
{company_dir}/overview.md{Show a 3-4 line summary of what the overview covers}Interview Prep —
{role_dir}/prep.md{Show a 3-4 line summary: number of topics covered, key areas, questions to ask}Read the full docs in
{company_dir}/or click the links on your board.
What ships with it
1 file 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.
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 · 176 lines · 80 tokens per session scan A c2f2a557e42f
prep is a skill published in the GitHub repository alwaysmap/jobs4me (2 stars, last pushed 1mo ago), licensed MIT. It adds 80 tokens to every session and 1,899 once invoked, about $0.0004 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
interview
Produce a tailored interview prep sheet (behavioral, technical, system design, company) from a job description and the user's resume.
skill-plan
把一个目标岗位变成"以你的起点 + 每周时间,几个月内能学到能投简历"的可执行学习计划。.
skill-status
这个 skill 的目标是让用户每次回来都不用重新解释上下文。你必须读取 .skill-state.json,根据 active.progress、active.learningplan、active.prediction 和 retrolog 判断用户今天该做什么。.
skill-init
把用户从"我想找个 AI 时代的高薪工作"带到"有了一份清晰能力画像、可以开始找岗位",全程 ≤ 5 分钟。.
interview-analysis
This skill should be used when the user asks to "/interview-analysis", "analyze my interview", "debrief my interview", "what did I miss in the interview", "review my interview transcript", or pastes a transcript / notes from a just-finished interview. Reads the transcript (pasted, from --from-file, or auto-pulled from…
case-practice
This skill should be used when the user asks for "/case-practice", "/pm-job-search:case-practice", "drill me on product cases", "practice PM case interviews", "MC case drill", or "test my case-interview recognition". Runs drill 1 of the case-practice methodology — a multiple-choice (MC) rapid-recognition drill that…