research

research is a command for coding agents from noamseg/interview-coach-skill. It costs 0 tokens per session (2,049 once invoked), scanned A, original, MIT.

A lightweight company research workflow for people deciding whether to apply, building a target list, or learning about a company before networking.

In plain words
What is it for?
Researching public company information, comparing it with a candidate profile, and producing a research brief.
Why use it?
It helps you assess a company and your fit before spending time on full interview preparation.

Command

About the project

Interview Coach is a Claude Code-based coaching system for the full job-search process, including job-description analysis, application materials, interview practice, answer evaluation, and offer negotiation. It is intended for job seekers who want tailored feedback and structured preparation based on their own experience and interview transcripts. Its catalogue entry consists of commands, a setting, and a skill that provide the coaching workflows.

noamseg/interview-coach-skill · 2,112 stars · on GitHub

Install

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.

agentmods
npx agentmods add commands/noamseg/interview-coach-skill/research
Clone the repo
git clone --depth 1 https://github.com/noamseg/interview-coach-skill

Wrote 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.

agentmods badge for research

README.md
[![agentmods](https://agentmods.dev/badge/commands/noamseg/interview-coach-skill/research.svg)](https://agentmods.dev/commands/noamseg/interview-coach-skill/research)
Your own site
<a href="https://agentmods.dev/commands/noamseg/interview-coach-skill/research"><img src="https://agentmods.dev/badge/commands/noamseg/interview-coach-skill/research.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,049 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.02049
Opus 5 $0.00000 $0.01025
Sonnet 5 $0.00000 $0.00410
Haiku 4.5 $0.00000 $0.00205

Measured 6d ago against content hash 91561ce1ab24, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

research 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 6d 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.

references/commands/research.md · 144 lines

How it starts

The opening of the file, as written. The whole thing — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.

research — Company Research Workflow

A lightweight alternative to prep for when the candidate wants to understand a company before committing to a full prep cycle. Use when they're evaluating whether to apply, building a target list, or doing early-stage reconnaissance.

When to Use Research vs. Prep

Situation Use
Evaluating whether to apply research
Building a target company list research (run multiple)
Have an interview scheduled prep
Want to understand company culture before networking research
Need predicted questions and story mapping prep

Sequence

  1. Ask for company name and the candidate's target role type (if not already in coaching state).
  2. Research publicly available information. Follow the same Company Knowledge Sourcing tiers from prep — Tier 1 (verified), Tier 2 (general knowledge), Tier 3 (unknown/say so).
  3. Assess fit against the candidate's profile (from coaching_state.md if available, or from what they've told you).
  4. Output the research brief.

Research Depth Levels

Level When to Use What to Do Time Investment
Quick Scan Building a target list, evaluating 5+ companies at once Company website + careers page + recent news. Enough for a basic fit assessment. 5-10 min
Standard Evaluating whether to apply. Default for research. Full protocol: website, careers, news, Glassdoor, LinkedIn, blog. Produces a complete research brief. 15-20 min
Deep Dive High-priority target, interview scheduled, want maximum intelligence Standard + employee posts/talks, product reviews, competitor analysis, leadership team profiles. 30+ min

Default to Standard. Suggest Deep Dive when:

  • The candidate has an interview scheduled at this company
  • The candidate explicitly asks for comprehensive intelligence
  • The company is in the candidate's top 3 targets

Structured Search Protocol

Search for information in this order. Each step builds on the previous ones:

Read the full file on GitHub · 144 lines

Changes

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.

  1. 6d ago First seen · 144 lines · 0 tokens per session scan A 91561ce1ab24

Subscribe to this mod's changes

research is a command published in the GitHub repository noamseg/interview-coach-skill (2,112 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,049 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.