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 tam159/next-role --skill interview-coachgit clone --depth 1 https://github.com/tam159/next-roleWrote 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/tam159/next-role/interview-coach)<a href="https://agentmods.dev/skills/tam159/next-role/interview-coach"><img src="https://agentmods.dev/badge/skills/tam159/next-role/interview-coach/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/tam159/next-role/interview-coach"><img src="https://agentmods.dev/badge/skills/tam159/next-role/interview-coach.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00058 | $0.00967 |
| Opus 5.5 | $0.00023 | $0.00387 |
| Sonnet 5.5 | $0.00012 | $0.00193 |
| Haiku 4.5 | $0.00006 | $0.00097 |
Grade A, and why
interview-coach 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 2mo 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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Interview Coach
Give the candidate everything they need to walk into the interview rounds prepared.
Inputs
The caller passes exact filesystem paths in the task description:
resume_path— the candidate's processed resumejd_path— the processed job descriptionintake_path— optional intake notes (especially: prep timeline, interview process)research_path— the hiring-recon reportoutput_path— where to write the prep doc
Read all four input files in full with read_file(path, limit=1000).
Determining the rounds
Check the intake for an interview process (e.g. "recruiter screen → hiring-manager → tech → onsite"). If present, prep every named round.
If no round info is given, default to a 3-round taxonomy:
- Recruiter screen (logistics, fit, salary expectations)
- Hiring-manager behavioral (leadership, problem-solving, motivation)
- Technical / role-specific (deep skills check)
If the prep timeline is short (< 3 days), prepend a ## Triage section recommending the 2 rounds to focus on.
Output structure
# Interview prep — <Role> at <Company>
_Captured <UTC date>_
## Self-introduction
**60-second elevator pitch** (~120 words):
> <first-person: role identity → 2 strongest accomplishments → why this company/role specifically, informed by the research's Company snapshot>
**30-second short version** (~60 words):
> <same arc, less detail — used when interviewer says "keep it brief">
_These two versions are reused across every round. Do not rewrite per round._
## Triage ← include only if prep timeline < 3 days
- Focus on: <Round X>, <Round Y>
- Reason: <one short line>
## Round-by-round prep
### Round 1 — <Name> (<format>)
**Likely question themes:**
- <Pick 2-3 from: Leadership / Problem-solving / Collaboration / Achievement / Failure & growth / Role-specific>
**STAR stories ready (3-5):**
1. **<Story title>** — maps to: <theme>
- **Full (~2 min):** S — ... | T — ... | A — ... | R — ...
- **Short (~60 sec):** <condensed>
2. ...
**Questions to ask back (2-3):**
- <question grounded in research's Hiring team / Reputation>
- ...
**Watch-outs:**
- <risk from research's Reputation & culture, and how to navigate>
### Round 2 — <Name> (<format>)
...
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.
- 2mo ago First seen · 93 lines · 58 tokens per session scan A c293e89ea726
interview-coach is a skill published in the GitHub repository tam159/next-role (65 stars, last pushed 2d ago), licensed MIT. It adds 58 tokens to every session and 967 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.
interview-coach compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| interview-coachtam159/next-role | Skill | 65 | 2d ago | MIT | A | 58 | Claude Code, Codex |
| openspec-onboardFission-AI/OpenSpec | Skill | 74k | yesterday | MIT | A | 43 | Claude Code |
| blog-postlangchain-ai/deepagents | Skill | 31k | yesterday | MIT | A | 58 | Claude Code, Codex |
| gsd-milestone-summaryopen-gsd/gsd-core | Skill | 11k | yesterday | MIT | A | 20 | Claude Code |
| gsd-helpopen-gsd/gsd-core | Skill | 11k | yesterday | MIT | A | 12 | Claude Code |
| principal-agentkangarooking/cangjie-skill | Skill | 12k | 1mo ago | MIT | A | 134 | Claude Code, Codex |
| book-to-skillvirgiliojr94/book-to-skill | Skill | 37k | 3d ago | MIT | C | 105 | Claude Code, Codex |