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 nthnclrk/enablement-skills --skill talk-track-buildergit clone --depth 1 https://github.com/nthnclrk/enablement-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/nthnclrk/enablement-skills/talk-track-builder)<a href="https://agentmods.dev/skills/nthnclrk/enablement-skills/talk-track-builder"><img src="https://agentmods.dev/badge/skills/nthnclrk/enablement-skills/talk-track-builder/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/nthnclrk/enablement-skills/talk-track-builder"><img src="https://agentmods.dev/badge/skills/nthnclrk/enablement-skills/talk-track-builder.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 | $0.01017 |
| Opus 5 | $0.00042 | $0.00508 |
| Sonnet 5 | $0.00017 | $0.00203 |
| Haiku 4.5 | $0.00008 | $0.00102 |
Grade A, and why
talk-track-builder 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 11d 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Talk track builder
Write lines a seller can say out loud. If it reads like a script, rewrite it.
A talk track covers one conversation moment, one objective, and one next-step ask. If the user wants the meeting architecture (what to discover, what to demo, in what order), use discovery-and-demo-structure first.
Spoken line. "Before we look at the product, can we start with the handoff misses that brought you here? Where does ownership break today, and what happens downstream when it does?"
Script. "Thanks so much for taking the time today. I'm excited to share how our AI-powered platform delivers unmatched visibility across your operational handoffs."
If a good AE would wince saying it to a VP, it is not done.
Confirm Inputs First
Ask only for the inputs that change the lines:
- Who is speaking, and to whom
- The conversation moment and the one outcome it must produce
- How long they actually get to talk
- Approved proof and claim boundaries
If proof is missing, leave spoken proof slots marked needs source. Do not invent customers, numbers, pricing, or implementation promises.
Read The Right Reference
Read references/talk-track-framework.md for the spoken-line test, branch pattern, and worked excerpts. Skip it if the user already gave you a structure and only wants lines.
Default Workflow
- Name the job. One objective. One next-step ask with an owner and a time. Done when both fit in the close the seller will actually say.
- Pick the moment, not the whole call.
Discovery, demo, commercial, renewal, expansion, or a coaching inspect. One primary. If the discovery or demo architecture is not yet defined, route that design to
discovery-and-demo-structure. - Write the through-line. Opening frame, one context check, the few questions that change the next move, a value bridge, proof only if you have it, close. Cut any beat that does not serve the objective.
- Write the lines. One breath each. Buyer language, not product language. Role and stage should change the questions and the ask, not just the nouns.
- Hang proof on a moment. One sentence, under 20 seconds, with source and scope. Directional evidence stays directional. No source, no spoken claim.
- Branch the turns you can hear coming. For each: the trigger you listen for, a diagnostic question, then the response. Usual set: skepticism, "we already have a process," price, competitor. Skip branches this moment will not raise.
- Mark the landmines. What not to say. Where to stop and ask. Where to hand off to SE, legal, or deal desk.
- Read it aloud. Split anything you cannot say in one breath. Delete phrases a person would never say to another person. Flag high-stakes rollouts for rehearsal.
- Add manager checks only if someone asked to coach or inspect this track.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 11d ago First seen · 79 lines · 84 tokens per session scan A e1ca037528e5
talk-track-builder is a skill published in the GitHub repository nthnclrk/enablement-skills (13 stars, last pushed 21d ago), licensed MIT. It adds 84 tokens to every session and 1,017 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 2026-08-30.
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…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…