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/btmoriarty/kochab/roadmap-interviewnpx skills add btmoriarty/kochab --skill roadmap-interviewgit clone --depth 1 https://github.com/btmoriarty/kochabWrote 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/btmoriarty/kochab/roadmap-interview)<a href="https://agentmods.dev/skills/btmoriarty/kochab/roadmap-interview"><img src="https://agentmods.dev/badge/skills/btmoriarty/kochab/roadmap-interview.svg" alt="Measured on agentmods" 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 | $0.00105 | $0.01290 |
| Opus 5 | $0.00053 | $0.00645 |
| Sonnet 5 | $0.00021 | $0.00258 |
| Haiku 4.5 | $0.00011 | $0.00129 |
Grade A, and why
roadmap-interview 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 3d 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Roadmap Interview
A structured, non-leading interview that pulls real needs out of a user and turns them into roadmap input. The goal is not a wish list. It is to understand the person's actual job search well enough to know which features would matter and which would just look good.
Run it in fifteen to twenty minutes. Respect the person's time.
Interviewing principles (these matter more than the questions)
- Ask about the real and recent, not the hypothetical. "Walk me through the last job you applied to" beats "what features do you want." People describe their needs accurately when telling a true story and inaccurately when speculating.
- Do not lead, and do not pitch. Never describe a feature and ask if they would like it; almost everyone says yes. Ask what they did, where they got stuck, and what they wished had happened. Let the feature idea come from the friction.
- Separate the stated want from the underlying need. When they ask for a thing, ask why, twice. "I want it to auto-apply" often means "I am exhausted by the repetition," which points at a very different, and better, feature.
- Follow the energy. When someone gets animated or frustrated, stop and dig there. That is where the real signal is.
- One question at a time. Let them finish. Silence is fine.
- Capture their words. A vivid verbatim quote is worth more than your paraphrase.
- Welcome disagreement. If they think something you built is useless, that is the most valuable thing they can tell you. Do not defend it.
The interview
Move through these sections in order, but adapt. Skip what does not apply; dig where it does.
1. Grounding
- Where are you in your job search right now, and what does a normal week of it look like?
- What is the search for: a similar role, a change, a first job in a field, a move up?
2. The last real instance
- Walk me through the last role you applied to, start to finish. What did you do first?
- Where did it get tedious, confusing, or discouraging?
- What did you do by hand that you wished something would do for you? What did you skip because it was too much work?
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.
- 3d ago First seen · 79 lines · 105 tokens per session scan A a00358baf932
roadmap-interview is a skill published in the GitHub repository btmoriarty/kochab (1 stars, last pushed 1mo ago), licensed MIT. It adds 105 tokens to every session and 1,290 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
dashboard
Opens a local web dashboard that visualizes the job application pipeline, funnel stats, recent messages, and target company status. The agent opens it at the end of a round so the user can visually review the pipeline.
pilot
One autonomous Pilot cycle - fetch the agenda, execute the top item, journal, exit. Injected by the terminal host - not for manual invocation loops.
pipeline-triage
Decide WHICH role to spawn / pause / kill based on backlog state, not gut feel. Open this skill EVERY TIME you observe — vel team < 50% target, OR any role queue = 0, OR Scout sources exhausted, OR [SCALA UP] from Sentinella, OR PIPELINE VUOTA + UNDERSHOOT, OR MARGINE from bridge-pacing, OR cold start, OR whenever you…
add-asana
Add Asana project management MCP integration to Deus. Gives host-side Claude Code sessions read/write access to Asana tasks, projects, sections, and tags via @roychri/mcp-server-asana.
careerops
CareerOps agent skill — open-source career OS modes (scan, evaluate, rank, tailor, interview, followup, outcome, advise). Materials-first. Never invents experience. Never auto-applies.
docs
Public-facing skill docs. Full mode prompts live in .agents/skills/careerops/.