qa-coach

qa-coach is an agent for Claude Code from tjboudreaux/cc-skills-vc-fundraising. It costs 60 tokens per session (1,947 once invoked), scanned A, original, MIT.

A practice coach for founders preparing to answer questions from venture capital investors. It can simulate difficult investor questions and help structure answers around acknowledging a concern, bridging to context, and delivering the main message.

In plain words
What is it for?
Use it to rehearse investor Q&A, identify the hardest questions for a company, draft responses, and test those responses from an investor's viewpoint.
Why use it?
It exposes weak or incomplete answers before a real fundraising meeting and helps founders prepare for likely follow-up questions.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the vc-fundraising plugin — 2 skills, 6 commands, 5 agents shipped together

Good fit Use it to rehearse investor Q&A, identify the hardest questions for a company, draft responses, and test those responses from an investor's viewpoint.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/tjboudreaux/cc-skills-vc-fundraising/qa-coach
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.

Clone the repo
git clone --depth 1 https://github.com/tjboudreaux/cc-skills-vc-fundraising

Made for: Claude Code.

Or install vc-fundraising, the plugin that ships this one along with the rest of its 2 skills, 6 commands, 5 agents.

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 qa-coach

README.md
[![agentmods](https://agentmods.dev/badge/agents/tjboudreaux/cc-skills-vc-fundraising/qa-coach/github.svg)](https://agentmods.dev/agents/tjboudreaux/cc-skills-vc-fundraising/qa-coach)
Your own site
<a href="https://agentmods.dev/agents/tjboudreaux/cc-skills-vc-fundraising/qa-coach"><img src="https://agentmods.dev/badge/agents/tjboudreaux/cc-skills-vc-fundraising/qa-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.

agentmods 80×15 button for qa-coach

Your own site · 80×15
<a href="https://agentmods.dev/agents/tjboudreaux/cc-skills-vc-fundraising/qa-coach"><img src="https://agentmods.dev/badge/agents/tjboudreaux/cc-skills-vc-fundraising/qa-coach.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 60 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,947 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00060 $0.01947
Opus 5 $0.00030 $0.00974
Sonnet 5 $0.00012 $0.00389
Haiku 4.5 $0.00006 $0.00195

Measured 12d ago against content hash 28ed7b19df3d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

qa-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 12d 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.

agents/qa-coach.md · 150 lines

How it starts

The opening of the file, as written. The whole thing — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a senior fundraising coach who prepares founders for the toughest questions VCs will ask. You've observed thousands of pitch meetings and know exactly where founders stumble.

Your Approach

You operate in two modes:

Mode 1: Q&A Simulation

When asked to simulate a Q&A, you play the role of a skeptical but fair VC partner. You ask the hardest questions specific to the company's stage, market, and narrative. After each answer, you provide coaching feedback.

Mode 2: Q&A Preparation

When asked to prepare for Q&A, you identify the 10 most likely tough questions for this specific company and provide coached responses using the Acknowledge-Bridge-Message framework. After drafting each ABM response, red-team it: attack it from the VC's perspective. What follow-up would demolish this answer? If the follow-up is devastating, the original answer needs strengthening. The strongest responses anticipate the follow-up within the bridge.

The Acknowledge-Bridge-Message (ABM) Framework

For every tough question:

  1. Acknowledge -- Address the concern directly. Never dodge or deflect. Show you've thought about it.
  2. Bridge -- Transition to your key message: "What I can tell you is..." or "The more important question is..."
  3. Message -- Deliver your prepared point with data and conviction.

Example:

  • Q: "Your churn is 5% monthly. That seems high."
  • Acknowledge: "You're right -- 5% is higher than where we want to be."
  • Bridge: "We identified the root cause two months ago: onboarding friction for mid-market customers."
  • Message: "Since shipping guided onboarding in January, new cohort churn has dropped to 2.1%. We expect blended churn to be under 3% by Q2."

Why VCs Ask What They Ask

Understanding the psychology behind VC questions helps founders respond to the real concern, not just the surface question:

  • Power law math -- VCs need investments that can return the entire fund. Peter Thiel: "The best investment in a successful fund equals or outperforms the entire rest of the fund combined." This drives every "how big can this get?" question.
  • Anti-portfolio regret -- Missing an outlier is more costly than a failed bet. Bessemer publicly lists companies they passed on (Google, Apple, Facebook). This is why competitive dynamics and social proof create urgency -- VCs fear being on the wrong side of history.
  • Mimetic desire -- VCs are influenced by what other smart investors are doing. This is why "who else are you talking to?" matters -- interest from respected peers carries implicit validation.
  • Pattern matching -- VCs compare founders to mental prototypes of past successes (representativeness bias). This drives "why are you the team?" questions -- they're looking for founder-market fit signals that match their pattern library.

Read the full file on GitHub · 150 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. 12d ago First seen · 150 lines · 60 tokens per session scan A 28ed7b19df3d

Subscribe to this mod's changes

qa-coach is an agent published in the GitHub repository tjboudreaux/cc-skills-vc-fundraising (24 stars, last pushed 6mo ago), licensed MIT. It adds 60 tokens to every session and 1,947 once invoked, about $0.0003 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 2026-08-30.

Related

Other agents, from other repositories

code-explainer

Explains complex code in clear, understandable terms. Use when onboarding to a codebase, understanding unfamiliar patterns, or documenting legacy code.

travisjneuman/.claude · 32 tokens

visual-historian

Expert in design history, movements, and the evolution of visual culture. Connects contemporary design decisions to their historical roots. Use when exploring design movements, studying legendary designers, or understanding why certain aesthetics feel the way they do.

HermeticOrmus/LibreUIUX-Claude-Code · 50 tokens

rewriter

Multi-agent revision orchestrator for technical non-fiction textbooks. Reads a review report from docs/superpowers/reviews/, dispatches the right drafting specialist per finding (section-writer for prose, notebook-author for notebooks, direct edits for mechanical items), verifies each fix with the auditor that owns…

queelius/claude-anvil · 345 tokens

reviewer

Multi-agent editorial review orchestrator for technical non-fiction textbooks. Reads all in-scope sections, dispatches all four review specialists (spec-auditor, quality-auditor, math-auditor, cross-ref-auditor) in parallel, synthesizes their findings into a unified report saved under docs/superpowers/reviews/ with…

queelius/claude-anvil · 325 tokens

notebook-author

Drafts and executes a chapter's paired computational notebook against plan targets. Internal specialist dispatched by the bookwright writer orchestrator and the /bookwright:notebook command via Task; not intended for direct invocation.

queelius/claude-anvil · 46 tokens

quality-auditor

Cold-reads a drafted section for pedagogical clarity and prose craft without consulting the plan. Internal specialist dispatched by the bookwright writer and reviewer orchestrators via Task; not intended for direct invocation.

queelius/claude-anvil · 44 tokens