Borrowing it
Nothing to install: this file belongs to Othmane-Khadri/gtm-engineer-playbook. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Othmane-Khadri/gtm-engineer-playbook/main/.claude/skills/gtm-playbook/icp-architect/SKILL.mdgit clone --depth 1 https://github.com/Othmane-Khadri/gtm-engineer-playbookWrote 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/othmane-khadri/gtm-engineer-playbook/icp-architect)<a href="https://agentmods.dev/skills/othmane-khadri/gtm-engineer-playbook/icp-architect"><img src="https://agentmods.dev/badge/skills/othmane-khadri/gtm-engineer-playbook/icp-architect/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/othmane-khadri/gtm-engineer-playbook/icp-architect"><img src="https://agentmods.dev/badge/skills/othmane-khadri/gtm-engineer-playbook/icp-architect.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 | $0.00062 | $0.03065 |
| Opus 5 | $0.00031 | $0.01533 |
| Sonnet 5 | $0.00012 | $0.00613 |
| Haiku 4.5 | $0.00006 | $0.00307 |
Grade A, and why
icp-architect 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 — 284 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ICP Architect
Build a comprehensive Ideal Customer Profile through an interactive discovery process. This skill asks questions, pressure-tests assumptions, and produces a reference-ready docs/icp.md that other skills in the playbook can consume.
Activation
When the user triggers this skill, follow the steps below in order. Do NOT skip the discovery interview. Do NOT produce output before gathering all answers.
Step 0 — Check for Existing ICP
Use Read to check if docs/icp.md already exists in the current working directory.
- If it exists: Read the file, present a summary to the user, and ask: "You already have an ICP on file. Do you want to (A) refine it, (B) start fresh, or (C) add a new segment?"
- If refine: Load the existing content as context. During the discovery interview, pre-fill answers from the existing file and only ask about gaps or changes.
- If start fresh: Proceed with the full interview from scratch. The old file will be overwritten at the end.
- If add segment: Skip to Step 2 (ICP Segmentation) and ask only the questions needed to define the new segment and its personas. Append to the existing file.
- If it does not exist: Proceed to Step 1.
Step 1 — Discovery Interview (Interactive)
Present these questions to the user all at once in a numbered list. Tell the user they can answer inline (numbered) or paste a block of text and you will extract the answers.
Ask exactly these questions:
I need to understand your business before building your ICP. Answer these 10 questions — be as specific as possible. One-word answers are fine where they fit; paragraphs are fine where they don't.
1. What does your product do? (one sentence)
2. Who is your current best customer? Why are they your best?
3. What's your ACV or typical deal size range?
4. How long is your typical sales cycle? (days/weeks/months)
5. Who signs the check? (job title, not a person's name)
6. What's the trigger event that makes someone start looking for your solution?
7. What were they doing before your product? (the "old way" — spreadsheets, manual process, a competitor, nothing?)
8. What happens if they do nothing? (cost of inaction — lost revenue, compliance risk, wasted time?)
9. What's your unfair advantage vs. the next best alternative?
10. (Optional) Paste 3-5 LinkedIn profile URLs of your best customers. I'll extract patterns from their titles, industries, and company sizes.
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 · 284 lines · 62 tokens per session scan A 994ea882ca09
icp-architect is a skill published in the GitHub repository Othmane-Khadri/gtm-engineer-playbook (56 stars, last pushed 5mo ago), licensed MIT. It adds 62 tokens to every session and 3,065 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.
Other skills, from other repositories
go-to-market-playbook
A reusable Go-to-Market strategy template for both B2B and B2C launches. Covers positioning, messaging, ICP definition, channel selection, and competitive analysis frameworks. By @WeiYipei.
adoption-leaderboard
Scores a rep's or a team's recent sales calls against a fixed set of five winning-behavior checklists (rapport, upsell signals, renewal risk, customer experience, value realization), then ranks reps lowest-adoption-first so the highest-leverage coaching targets lead. Use when running a team calibration, prepping 1:1…
challenger
Audits a B2B sales call transcript against the Challenger Sale framework (teach, tailor, take control, plus the commercial-teaching pitch arc), or sweeps a CRM export for deals with no teaching insight logged. Use when a rep leans on discovery-question skill but rarely brings a point of view, when prepping a rep for a…
champion-tracker
Tracks champion strength across a deal's call(s) — builds an action ledger, one row per named contact per cited quote, tagging each as either an act of internal selling (looping in a stakeholder, pushing back for the rep in a room the rep wasn't in) or mere positive sentiment (encouraging words, no action), then reads…
executive-briefing
Writes the short brief a rep sends upward out of one deal — to their own exec or the buyer's exec sponsor — covering deal snapshot, status, what's at risk, and the ask, each claim cited to a quote or a CSV column/cell. Use when someone who will never read the transcript needs to act on one deal, not a call-by-call…
faint
Audits a B2B sales call transcript against the FAINT qualification framework (Funds, Authority, Interest, Need, Timing), or sweeps a CRM export for deals missing FAINT fields. Use when a prospect hasn't articulated a clear need yet but shows financial capacity and curiosity, or when deciding whether a demand-driven…