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/palashjain95/jobhunternpx agentmods add skills/palashjain95/jobhunter/coffee-chatWrote 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/palashjain95/jobhunter/coffee-chat)<a href="https://agentmods.dev/skills/palashjain95/jobhunter/coffee-chat"><img src="https://agentmods.dev/badge/skills/palashjain95/jobhunter/coffee-chat/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/palashjain95/jobhunter/coffee-chat"><img src="https://agentmods.dev/badge/skills/palashjain95/jobhunter/coffee-chat.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 | $0.00084 | $0.01620 |
| Opus 5 | $0.00042 | $0.00810 |
| Sonnet 5 | $0.00017 | $0.00324 |
| Haiku 4.5 | $0.00008 | $0.00162 |
Grade A, and why
coffee-chat 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 10d 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 — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/coffee-chat
If you see unfamiliar
~~placeholders, see CONNECTORS.md.
Usage
/coffee-chat <person name at company>
/coffee-chat I'm meeting someone at Stripe tomorrow
/coffee-chat I just had a coffee chat with Sarah at Google
/coffee-chat elevator pitch
This is the most important skill in MBA recruiting. Networking drives more offers than applications.
How It Works
┌─────────────────────────────────────────────────────────┐
│ COFFEE CHAT │
├─────────────────────────────────────────────────────────┤
│ MODE 1: PREP (before the chat) │
│ - Research the person + company │
│ - Generate smart questions + talking points │
│ - Build elevator pitch (3 versions) │
│ + ~~calendar: auto-detect scheduled chat │
│ │
│ MODE 2: FOLLOW-UP (after the chat) │
│ - Ask about the conversation (one Q at a time) │
│ - Draft thank-you (email + LinkedIn versions) │
│ - Suggest pipeline update + next networking steps │
│ + ~~transcription: auto-pull chat transcript │
│ + ~~email: create draft for review │
└─────────────────────────────────────────────────────────┘
Inputs
- Who they're meeting (name, role, company — or just company)
- Context (coffee chat, info session, alumni call, recruiter meeting)
- Whether this is PREP (before) or FOLLOW-UP (after)
- knowledge/profile.md — candidate background
- knowledge/stories/ — for relevant anecdotes
- knowledge/frameworks/writing-framework.md — for follow-up tone
Mode 1: PREP (before the conversation)
1. Person Research (if name provided)
LinkedIn background, career path, current role. Anything they've written or spoken about. Mutual connections or shared experiences.
2. Company Context (quick, not full research)
What the company does, recent news (2-3 bullets). What the team/division does. Any open roles relevant to the candidate.
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.
- 10d ago First seen · 189 lines · 84 tokens per session scan A c189d62e5182
coffee-chat is a skill published in the GitHub repository palashjain95/jobhunter (2 stars, last pushed 5mo ago), licensed MIT. It adds 84 tokens to every session and 1,620 once invoked, about $0.0004 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
i-have-adhd
Shape output for a reader with ADHD: lead with the next action, number multi-step work, restate state across turns, suppress tangents, give specific time estimates, make wins visible. Invoke with /i-have-adhd; stays on until "stop adhd mode".
mix-compression
Reduce mix output noise (5-15% token savings) by installing rtk filters that compress mix test/credo/dialyzer/compile output before it reaches Claude. Use when long mix output floods context.
phx-mix-compression
Reduce mix output noise (5-15% token savings) by installing rtk filters that compress mix test/credo/dialyzer/compile output before it reaches Claude. Use when long mix output floods context.
quick
Implement small Phoenix changes without planning — add validations, update routes, fix components, create migrations. Use for single-file edits under 50 lines.
phx-freeze
Apply an advisory edit scope in this session. Use for read-only or directory-scoped work; no enforcement hook is installed.
service-desk
Runs the IT service desk — intake, triage, prioritization, escalation, knowledge, and the metrics that improve service rather than distort it. Use this to set up or fix a service desk, design ticket priority and escalation, reduce repeat contacts, structure a knowledge base, or work out why a desk hitting its targets…