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/Miracle-Aligner/job-search-hqnpx agentmods add skills/miracle-aligner/job-search-hq/interview-prepWrote 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/miracle-aligner/job-search-hq/interview-prep)<a href="https://agentmods.dev/skills/miracle-aligner/job-search-hq/interview-prep"><img src="https://agentmods.dev/badge/skills/miracle-aligner/job-search-hq/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/miracle-aligner/job-search-hq/interview-prep"><img src="https://agentmods.dev/badge/skills/miracle-aligner/job-search-hq/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 | $0.00109 | $0.00777 |
| Opus 5 | $0.00055 | $0.00388 |
| Sonnet 5 | $0.00022 | $0.00155 |
| Haiku 4.5 | $0.00011 | $0.00078 |
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 9d 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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
interview-prep
Produce one self-contained brief that gives the candidate everything to walk in prepared.
Invoked standalone (/interview-prep <id> [eventId]) or from /update-status when an
interview is scheduled.
Inputs (read these first)
- The vacancy in
data/vacancies.json— role, JD recap (summary,plus,minus),score/ss,statusDetail, the targetevent(stage, time, via, interviewer if noted). profile/candidate.md+profile/profile.json— strengths, gaps, comp/level targets.- The CV digests (
/ingest-cv) — concrete projects, metrics, evidence to cite. - Live research —
WebSearch+WebFetchthe company: what they do, product, stage/funding, recent news (last ~6 months), tech signals, Glassdoor-style interview-format hints. Cite nothing you didn't actually find; mark unknowns as unknown.
The brief (markdown → events[].prep)
Tailor depth to the stage (HR screen = light; tech/final = deep). Cover:
- Company snapshot — what they do, product, stage/size, 2–3 recent developments.
- Role & JD recap — the 3–5 things this role actually needs; how the candidate maps.
- Stage & format — what this round is (recruiter / tech / system design / final), who's on it if known, likely structure and length.
- Likely questions — behavioral + technical, tailored to the JD stack and the candidate's gaps. Make them specific to this company/role, not generic.
- Strong talking points — mapped to concrete CV evidence (project, metric, outcome).
- Gap defense — for each real gap (from the profile), an honest, confident framing.
- Smart questions to ask them — sharp, role/company-specific.
- Comp & level context — the candidate's target band vs this role; a negotiation anchor.
- Logistics — date/time, via, meeting URL, what to have open.
Keep it tight and skimmable (headers + bullets). It's a cheat-sheet, not an essay.
Persist
Write the markdown to the target event's prep field in data/vacancies.json
(vacancies[i].events[j].prep). If no specific event, attach to the soonest upcoming
interview-kind event, or create a follow-up event to hold it and say so.
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.
- 9d ago First seen · 62 lines · 109 tokens per session scan A 6ac9e7960f8d
interview-prep is a skill published in the GitHub repository Miracle-Aligner/job-search-hq (1 stars, last pushed 3mo ago), licensed MIT. It adds 109 tokens to every session and 777 once invoked, about $0.0005 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
apply
Apply to a single job (URL or pasted page) with fit review, or score and apply the job links pasted into an apply campaign when no argument is given.
scan-inbox
Classify unscanned mailbox messages, fuzzy-match each to an existing application, and write the proposal back. The user approves in /inbox.
resume-campaign
Resume a paused JobPilot campaign by id. Re-flips the campaign to inprogress and replays the apply loop on any remaining approved jobs without re-asking for fit confirmation.
interview
Produce a tailored interview prep sheet (behavioral, technical, system design, company) from a job description and the user's resume.
s4h-mindset-reframe
Applies cognitive reframing as a rigorous methodology — CBT-adjacent but not therapy. Use when you're stuck in a negative thought loop, interpreting a situation in a consistently unhelpful way, catastrophizing, or noticing that your automatic interpretation of events generates disproportionate distress. Triggers…
bb-assistant
A Chinese-language assistant for CUHK-Shenzhen Blackboard, the university's online course system. It helps manage assignments, announcements, grades, course materials, and to-do items.