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 commands/noamseg/interview-coach-skill/helpgit clone --depth 1 https://github.com/noamseg/interview-coach-skillWrote 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/commands/noamseg/interview-coach-skill/help)<a href="https://agentmods.dev/commands/noamseg/interview-coach-skill/help"><img src="https://agentmods.dev/badge/commands/noamseg/interview-coach-skill/help.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 | $0.00000 | $0.03033 |
| Opus 5 | $0.00000 | $0.01517 |
| Sonnet 5 | $0.00000 | $0.00607 |
| Haiku 4.5 | $0.00000 | $0.00303 |
Grade A, and why
help 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 4d 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 — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.
help — Command Reference Workflow
Logic
When the user types help, generate a context-aware command guide — not just a static list.
- Read
coaching_state.mdto understand where the candidate is in their coaching journey. - Show the full command guide (see Output Schema below) with sub-commands and key features for each command.
- Highlight the 2-3 most relevant commands right now based on coaching state:
- If no coaching state exists: highlight
kickoff - If storybank is empty: highlight
stories - If storybank has 5+ stories but no narrative identity analysis: highlight
stories(mention option 7) - If an interview is scheduled within 48 hours: highlight
hypeandprep - If transcripts exist but haven't been analyzed: highlight
analyze - If 3+ scored sessions exist: highlight
progress - If an offer was received: highlight
negotiate - If drill progression shows the candidate hasn't completed Stage 1: highlight
practice ladder - If LinkedIn Analysis doesn't exist and storybank has 3+ stories: highlight
linkedin - If LinkedIn Analysis exists and overall is "Weak" or "Needs Work": highlight
linkedin(mention pending fixes) - If Resume Optimization doesn't exist and kickoff has been run: highlight
resume - If Resume Optimization exists and overall is "Weak" or "Needs Work": highlight
resume(mention pending fixes) - If Positioning Statement doesn't exist and storybank has 3+ stories: highlight
pitch - If Positioning Statement exists and consistency status shows gaps: highlight
pitch(mention updating) - If Outreach Strategy doesn't exist and kickoff has been run and LinkedIn Analysis is not "Weak": highlight
outreach - If candidate mentions recruiter message, cold outreach, networking, or informational interview: highlight
outreach - If the candidate mentions recruiter feedback or an outcome in conversation but hasn't used
feedback: highlightfeedback - If a JD was mentioned or pasted but no JD Analysis exists and prep hasn't been run: highlight
decode - If the candidate mentions comparing job postings or deciding which roles to apply to: highlight
decode(batch triage) - If Interview Loops show a presentation round format (from prep or Format Discovery): highlight
present - If the candidate mentions a presentation, portfolio review, or case presentation: highlight
present - If Comp Strategy doesn't exist and the candidate mentions a recruiter screen or salary question: highlight
salary - If the candidate mentions salary expectations, compensation questions, or "what should I say about pay": highlight
salary
- If no coaching state exists: highlight
- Diagnostic Router — If the candidate describes a problem instead of asking for a command, route them to the right place:
- "I'm not getting callbacks" →
resume(ATS issues) ordecode(targeting wrong roles) - "I keep failing first rounds" →
analyze(if transcripts exist) orpractice ladder(if no data) - "I freeze in interviews" →
practice ladder(build reps) +hype(pre-interview boost) - "I don't know what to say about salary" →
salary - "I have an offer but it feels low" →
negotiate - "I don't know where to start" →
kickoff - "I'm not hearing back from networking" →
outreach+linkedin(profile quality gate) - "I keep getting to final rounds but not getting offers" →
progress(pattern analysis) +concerns(what's tripping you up) - "I have a presentation round" →
presentDon't just list the command — explain WHY that command addresses their specific problem.
- "I'm not getting callbacks" →
- Show current coaching state summary (if it exists): track, seniority band, drill stage, number of stories, number of real interviews, and active company loops.
- End with a prompt: "What would you like to work on?"
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.
- 4d ago First seen · 148 lines · 0 tokens per session scan A 630397a7afcb
help is a command published in the GitHub repository noamseg/interview-coach-skill (2,092 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,033 tokens. 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.
Other commands, from other repositories
retex
Retex - Capture lesson learned dans memory après fix, rollback, erreur.
review
View your learning progress — quiz scores, weak areas, and what to study next.
start-1-7
Start Lesson 1.7 - Project Memory.
edit-textbook-chapter
Edit a textbook-style chapter, following evidence-based writing instructions.
memory
Manage curated project memory — capture, list, show, and forget durable decisions, lessons, and conventions.
explain
Explain code, concepts, or system behavior with adjustable depth levels.