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 interview-prepgit 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/interview-prep)<a href="https://agentmods.dev/skills/muggl3mind/career-manager/interview-prep"><img src="https://agentmods.dev/badge/skills/muggl3mind/career-manager/interview-prep/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/interview-prep"><img src="https://agentmods.dev/badge/skills/muggl3mind/career-manager/interview-prep.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 | $0.00064 | $0.00887 |
| Opus 5.5 | $0.00026 | $0.00355 |
| Sonnet 5.5 | $0.00013 | $0.00177 |
| Haiku 4.5 | $0.00006 | $0.00089 |
Grade A, and why
interview-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 16d 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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Interview Prep
Workflow skill: work → independent review → revise once. Dispatches use the Agent tool like the repo's other skills. (This is the orchflows work/review pattern — when the orchflows plugin is installed, orch-work and orch-review may serve as the dispatch primitives; the plugin is not required.)
Input
A company name as tracked in the pipeline (e.g. "Allvue Systems"). If no company is given, ask for one — that is the only fatal gap.
Process
-
Gather context (pure Python, no LLM):
uv run interview-prep/scripts/build_prep_context.py "<company>"Read the JSON summary it prints and the context file it wrote (
interview-prep/preps/<slug>-context.md). Missing pieces (dossier, tracker row, opportunities, base CV) are NOT failures — the workflow degrades gracefully and the prep doc must surface every gap. -
Draft: launch ONE Agent-tool subagent as the maker, session-default model (human-facing writing per the root SKILL.md Model Policy). Give it the context file, the base CV path from the JSON summary (it must read the CV file itself), and the acceptance criteria below. Output:
interview-prep/preps/<slug>.md— same slug the context builder printed, without the-contextsuffix.Required sections:
- Company Brief — from the dossier; only facts present in the context file
- Role Summary — from tracker row + opportunities rows
- Likely Interview Themes — inferred from role + company signals, labeled as inference
- Your Stories — map experience from the base CV to the themes (STAR prompts)
- Questions to Ask Them — grounded in dossier signals (funding, news, culture)
- Gaps & Logistics — every MISSING context piece, and what to do about each (e.g. "no dossier — run /research first")
-
Review: launch ONE independent Agent-tool subagent as reviewer,
model: sonnet(structured checking, per Model Policy), with the prep doc, the context file, and the criteria above. Checks: no fabricated facts (every claim traceable to the context file or CV, or labeled as inference); every MISSING piece surfaced in Gaps & Logistics; all six sections present and substantive. The reviewer reports findings only — no edits.
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.
- 16d ago Changed · +1 lines fee61d47d058
- 17d ago First seen · 51 lines · 64 tokens per session scan A bd9063ef4d4f
interview-prep is a skill published in the GitHub repository muggl3mind/career-manager (24 stars, last pushed 16d ago), licensed MIT. It adds 64 tokens to every session and 887 once invoked, about $0.0003 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 2026-10-01.
Other skills, from other repositories
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…
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.
amlei-profile
A shared, long-term profile of a user that acts as the main source of factual information across sessions. Resumes, portfolios, interview preparation, and personal work samples can use this profile as their source.