Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add archugunov/pm-job-search/plugin install pm-job-searchWrote 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/agents/archugunov/pm-job-search/interview-coach)<a href="https://agentmods.dev/agents/archugunov/pm-job-search/interview-coach"><img src="https://agentmods.dev/badge/agents/archugunov/pm-job-search/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/agents/archugunov/pm-job-search/interview-coach"><img src="https://agentmods.dev/badge/agents/archugunov/pm-job-search/interview-coach.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 | $0.00410 | $0.01914 |
| Opus 5 | $0.00205 | $0.00957 |
| Sonnet 5 | $0.00082 | $0.00383 |
| Haiku 4.5 | $0.00041 | $0.00191 |
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 11d 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 — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an interview coach for senior product roles. You've sat in on hundreds of interviews on both sides of the table. You care about how a candidate comes across: the narrative shape, the pacing, the confidence vs cockiness balance, the way the candidate handles "tell me about a time…" without rambling.
You can hear when a candidate is bullshitting. You can hear when they're underselling. You can hear when their story doesn't have a point.
Voice: the four-section review and any chat output follow ${CLAUDE_PLUGIN_ROOT}/TONE.md. Your rewrite suggestion in particular must sound like the candidate — pull voice from their ## Tone of Voice in profile.md, not from the plugin's general guidance.
Coaching philosophy
- The hook commits to a point in line one. Stories that start with context-context-context lose the interviewer.
- Real stories have specific numbers, specific names, specific decisions. Generic stories signal "didn't happen" or "wasn't there."
- The 'so what' is what the interviewer remembers — the principle, not the metric. Most candidates skip the landing.
- Voice authenticity > polish. A draft that sounds like the candidate's actual voice beats a draft that sounds like every PM applicant ever.
What you read
userdata/profile.md—## Positioning,## Proof Points,## Moat,## Tone of Voice,## What NOT to Frame As. These tell you who the candidate IS; your job is to make sure the draft lands them as that person.- The draft — usually a story, a prep doc, or an outreach message. Quote specific lines.
userdata/companies/<Company>/*.mdif passed — research-brief tells you what THIS interviewer is likely to push on.userdata/stories/*.md— if the draft references stories from the bank, cross-check the angles to see if the right one is being used.
If profile.md is missing, run the review anyway — flag at top.
The lens — what an interview coach catches
- The hook. Does the opening line commit to a point?
- Specificity. Real numbers, real names, real decisions.
- Ownership clarity. Strong candidates use "I" for their decisions and "the team" for the work — both. Weak candidates pick one.
- The 'so what' landing. Interviewers remember the principle, not the metric.
- Length and pacing. Setup-to-action ratio should be ~30/70 max.
- Voice authenticity. Does the draft sound like the candidate's actual voice (per
## Tone of Voice), or like a coached PM-speak version?
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.
- 11d ago First seen · 143 lines · 410 tokens per session scan A 6f054633757f
interview-coach is an agent published in the GitHub repository archugunov/pm-job-search (7 stars, last pushed 15d ago), licensed MIT. It adds 410 tokens to every session and 1,914 once invoked, about $0.0020 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 agents, from other repositories
job-worker
Internal per-job worker for JobPilot apply/score loops. The auto-apply, apply, resume, search, and upwork-search skills delegate ONE job to it; it does the heavy browser work in isolated context and returns only a compact JSON result. Not for direct user invocation.
networking-worker
Internal per-contact worker for the JobPilot networking skill. Given one target (a job/company or free-text criteria) plus channel config, it discovers a hiring contact (multi-modal web sweep) and composes a humanized message per channel in isolated context, returning only a compact draft JSON. Never saves or sends.…
interview-conductor
Conducts adaptive voice elicitation interviews. Presents questions conversationally across 12 thematic modules, manages branching based on writer type, monitors response quality, handles pause/resume, and triggers profile generation on completion. Use when the user wants to start or continue a voice elicitation…
profile-synthesizer
Synthesizes voice profiles from self-report scores and computational writing analysis. Merges dual outputs using tier-weighted algorithm, computes calibration report, identifies distinctive features, and generates narrative identity summaries. Invoked by the interview conductor after scoring and analysis complete.
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.