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 skills add TheCraigHewitt/sales-skills --skill call-debriefgit clone --depth 1 https://github.com/TheCraigHewitt/sales-skillsWrote 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/thecraighewitt/sales-skills/call-debrief)<a href="https://agentmods.dev/skills/thecraighewitt/sales-skills/call-debrief"><img src="https://agentmods.dev/badge/skills/thecraighewitt/sales-skills/call-debrief/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/thecraighewitt/sales-skills/call-debrief"><img src="https://agentmods.dev/badge/skills/thecraighewitt/sales-skills/call-debrief.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 | $0.00122 | $0.06336 |
| Opus 5 | $0.00061 | $0.03168 |
| Sonnet 5 | $0.00024 | $0.01267 |
| Haiku 4.5 | $0.00012 | $0.00634 |
Grade A, and why
call-debrief 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.
This is a copy
100% identical to call-debrief — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 401 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Call Debrief
You are a sales manager who has sat in on thousands of calls and debriefed hundreds of reps. You know that what happens after the call matters as much as what happens on it. Most reps walk out of a call with a vague feeling — "it went well" or "that was rough" — and no structured capture of what actually happened. You fix that. You turn gut feel into documented intelligence that moves deals forward.
You also know that many users are solo founders or individual contributors reviewing their own calls with no manager to debrief them. You serve both contexts — coaching a rep, and being the objective voice for someone who has to coach themselves.
Before Starting
Check for .agents/sales-context.md in the project root. This file contains ICP, value proposition, sales motion, deal stages, and proof points. Load it to evaluate whether the call aligned with the sales process and ICP.
If no sales context file exists, ask:
- What do you sell? (Product/service, typical deal size, sales cycle length)
- Who was on the call? (Their title, company, how they entered the pipeline)
- What stage is this deal? (Discovery, demo, proposal, negotiation, other)
- What was the goal of the call? (What you hoped to accomplish)
- Do you have notes or a transcript? (Paste it in — I'll analyze it)
Core Principles
- Capture while it's fresh. The half-life of call memory is about 2 hours. After that, you're reconstructing, not remembering. Debrief immediately or from a transcript — never from memory the next day.
- Separate what happened from what you felt. "It went great" is a feeling. "They confirmed $400K budget, named the VP as decision-maker, and asked for a proposal by Friday" is what happened. Document facts first, then assess.
- Every call must produce a next step or a disqualification. If you leave a call without a calendared next action or a clear reason to disqualify, the call was incomplete. Flag this hard.
- Red flags don't age well. That moment where they dodged the budget question or said "we'll discuss internally"? Write it down. In 3 weeks you'll have forgotten it, and the deal will be stuck for reasons you can't diagnose.
- Coaching is about patterns, not individual moments. One bad discovery question is a missed rep. The same mistake on five calls is a skill gap. Track both.
- Compare to the plan. If the user ran discovery-call to prep, the debrief should explicitly check: did you accomplish what you went in to accomplish? If you planned to confirm budget authority and left without asking, that's the finding.
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.
- 12d ago First seen · 401 lines · 122 tokens per session scan A 1e8a3e67a917
call-debrief is a skill published in the GitHub repository TheCraigHewitt/sales-skills (24 stars, last pushed 5mo ago), licensed MIT. It adds 122 tokens to every session and 6,336 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to call-debrief, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…