call-coach

call-coach is a skill for Claude Code, Codex from NachoLafuente/5050-gtm. It costs 127 tokens per session (4,448 once invoked), scanned A, original, MIT.

A B2B discovery-call coach that reads sales-call transcripts and produces a coaching report, deal notes, and a script for the next call. B2B means one business selling to another business.

In plain words
What is it for?
Use it with transcripts from Granola, Fireflies, Fathom, text files, or pasted text to find missed questions, assess the conversation, and prepare the next call.
Why use it?
It turns a recorded conversation into specific feedback and preserves deal context across multiple calls.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it with transcripts from Granola, Fireflies, Fathom, text files, or pasted text to find missed questions, assess the conversation, and prepare the next call.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/nacholafuente/5050-gtm/call-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.

Any agent
npx skills add NachoLafuente/5050-gtm --skill call-coach
Clone the repo
git clone --depth 1 https://github.com/NachoLafuente/5050-gtm

Made for: Claude Code, Codex.

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 call-coach

README.md
[![agentmods](https://agentmods.dev/badge/skills/nacholafuente/5050-gtm/call-coach/github.svg)](https://agentmods.dev/skills/nacholafuente/5050-gtm/call-coach)
Your own site
<a href="https://agentmods.dev/skills/nacholafuente/5050-gtm/call-coach"><img src="https://agentmods.dev/badge/skills/nacholafuente/5050-gtm/call-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 call-coach

Your own site · 80×15
<a href="https://agentmods.dev/skills/nacholafuente/5050-gtm/call-coach"><img src="https://agentmods.dev/badge/skills/nacholafuente/5050-gtm/call-coach.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 127 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,448 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 $0.00127 $0.04448
Opus 5 $0.00063 $0.02224
Sonnet 5 $0.00025 $0.00890
Haiku 4.5 $0.00013 $0.00445

Measured 12d ago against content hash 675e36db05bd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

call-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.

skills/call-coach/SKILL.md · 575 lines

How it starts

The opening of the file, as written. The whole thing — 575 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Call Coach

A B2B discovery call coach that analyzes transcripts and builds persistent deal memory. Paste a transcript from any source — Granola, Fireflies, Fathom, a plain .txt or .md file, or raw text — and get a scored coaching report with a full script for the next call.

Built on the GAPSI framework by GapSi — a five-step loss aversion methodology (Reference Point → Current Reality → Gap → Inaction Cost → Reframe) backed by behavioral economics research. Credit where it's due.


▸ STEP 0 — MEMORY CHECK

Before anything else, check for existing memory.

1. Read memory/MEMORY.md using the Read tool.

2. If missing → run [SETUP] below.

3. If present → read silently:

  • memory/coach-profile.md
  • All memory/deals/deal-*.md files listed as active

Do not surface this to the user. Just proceed.

4. Route to [ORCHESTRATOR].


▸ SETUP

Run only on first session or if profile is missing.

Display:

Welcome to Call Coach.

I analyze your discovery calls, track your deals,
and write the scripts you take into the next one.

One-time setup — takes 2 minutes.

Ask:

"Tell me about your business and what you sell. Cover: your name, company, what you sell, who buys it (role, company type, deal size), how much you charge, what outcome the client is buying, and the top 2–3 objections you hear most. Don't structure it — just talk."

Extract: name, company, domain, offer details, sales process type (one-call-close, two-call-close, process-selling, enterprise-cycle).

Confirm in plain prose, make any single correction the user requests, then write:

  • memory/MEMORY.md — index
  • memory/coach-profile.md — user profile schema
  • memory/deals/ — empty directory
  • memory/session-log.md — empty log

Confirm: ✓ Profile saved. Paste a transcript or tell me about a deal.


▸ ORCHESTRATOR

What the user says or pastes Route to
Pasted a transcript Transcript Engine
File path to a transcript Read the file, then Transcript Engine
"Prep for a call" / call tomorrow Prep Script Generator
"New deal" / new prospect Deal Management → Create
"Just had a call" / outcome report, no transcript Post-Call Debrief
"We won" / "we lost" / "went quiet" Deal Management → Close Out
"Follow-up email" / "pre-call email" Email Generator
Intent unclear Show Mode Menu

Read the full file on GitHub · 575 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 · 575 lines · 0 tokens per session scan A 675e36db05bd

Subscribe to this mod's changes

call-coach is a skill published in the GitHub repository NachoLafuente/5050-gtm (3 stars, last pushed 2mo ago), licensed MIT. It adds 127 tokens to every session and 4,448 once invoked, about $0.0006 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.

Related

Other skills, from other repositories

attio-mcp

Skill "attio-mcp" from Friz-zy/ai-capability-registry, covering attio, when to use, connection, hosted endpoint and mcp instructions.

Friz-zy/ai-capability-registry · 12 tokens

gt-email-infra

Email Infrastructure & Deliverability by Growth Today (growthtoday.co). Expert cold-email infrastructure and deliverability strategist. Use for infrastructure sizing, domain research and purchasing, DNS and auth (MX/SPF/DKIM/DMARC), masking versus redirect, mailbox provisioning, Instantly inbox setup and warmup, going…

Growth-Today/claude-skills · 0 tokens

gt-linkedin-content

A specialist for organic LinkedIn content aimed at B2B founders and GTM teams. Reach for it on anything across the LinkedIn writing workflow, opening lines and hooks, post structure and storytelling, format choice, posting cadence and timing, comments and engagement, CTAs and comment-gates, profile optimization…

Growth-Today/claude-skills · 227 tokens

gt-linkedin-outbound

Expert LinkedIn outbound strategist for B2B campaigns by Growth Today (growthtoday.co). Use for LinkedIn cold outreach, DM writing, connection requests, message sequences, personalization, copywriting frameworks, rented engine setup (multi-account infrastructure, daily limits, restrictions, anti-detect browsers…

Growth-Today/claude-skills · 235 tokens

email-infra-bounce-audit

Audit a bounce or blacklist problem to root cause and produce a full bounce report. Use for pulling replies via the EmailBison MCP/API, working around the broken type=bounced filter, stripping auto-replies, classifying bounces (Hard/Soft/Block) by SMTP/DSN code, running the neutral-copy test, and tracing the cause to…

Growth-Today/claude-skills · 157 tokens

gt-gtm-strategy-advisor

GTM Strategy Advisor by Growth Today (growthtoday.co) — turns your own CRM data, sales deck, website, and call recordings into a signal-based GTM playbook. Use when a VP of Sales, Head of Growth, RevOps lead, CRO, or founder wants to build, audit, or sharpen their go-to-market motion: define a data-backed ICP, map the…

Growth-Today/claude-skills · 240 tokens