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 TimboGP/timbogp-marketplace --skill customer-interviewgit clone --depth 1 https://github.com/TimboGP/timbogp-marketplaceWrote 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/timbogp/timbogp-marketplace/customer-interview)<a href="https://agentmods.dev/skills/timbogp/timbogp-marketplace/customer-interview"><img src="https://agentmods.dev/badge/skills/timbogp/timbogp-marketplace/customer-interview/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/timbogp/timbogp-marketplace/customer-interview"><img src="https://agentmods.dev/badge/skills/timbogp/timbogp-marketplace/customer-interview.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 | $0.00159 | $0.01361 |
| Opus 5 | $0.00079 | $0.00681 |
| Sonnet 5 | $0.00032 | $0.00272 |
| Haiku 4.5 | $0.00016 | $0.00136 |
Grade A, and why
customer-interview 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Customer interview
The heart of customer development: talk to real people to validate (or kill) your assumptions before building. This skill lets the user rehearse those conversations against a believable customer and get coached on technique — or just prep the scripts. You play the Customer role-play role (../../reference/roles.md) under the shared role-play protocol. Read references/interview-scripts.md for the three scripts before running.
When to use
The user wants to run, practice, or prep a customer interview. Three flavors map to the methodology's stages (../../reference/methodology.md):
| Flavor | Stage | Tests | Exit criteria |
|---|---|---|---|
| Problem | Understand Problem | Is this a must-have problem? For whom? Vs. what existing alternatives? | ≥10 interviews; can identify early-adopter demographics; have a must-have problem; can describe how customers solve it today |
| Solution | Define Solution | Does the smallest solution (a demo/mock-up) excite them? Will they pay? | Early adopters who'd rather buy than build; a price they accept; a defined Release 1.0 |
| MVP | Validate Qualitatively | Does the live MVP get noticed, activate, deliver the UVP, and convert to paid? | Warm prospects sign up and complete activation; usability hot spots found |
If the user hasn't picked a flavor, infer it from their stage in .lean/PROGRESS.md and propose one.
Two modes
- Prep mode — the user wants scripts, demographic-qualifying questions, or a critique of their own script. Provide them from
references/interview-scripts.md, tailored to their canvas. No role-play. - Role-play mode (default when they say "play a customer") — run the role-play protocol below.
Role-play protocol (Customer)
Follow the three-phase protocol in ../../reference/roles.md. Flavor-specific points:
Phase 0 — Set up (out of character)
- Confirm flavor (problem/solution/mvp), the format ("a ~20-minute problem interview; you interview me"), and that you'll stay in character until they say
debrief(or break with[square brackets]). - Build the persona from
.lean/canvas.md(Customer Segment + Early Adopter) — or invent a realistic one and confirm it: a name, situation, how they handle the problem today (their existing alternative), constraints, and an attitude (busy, skeptical, enthusiastic-but-flaky…). Note privately their hidden truths — e.g. they say a problem matters but haven't acted on it — for the debrief. - Announce entering character.
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 · 64 lines · 159 tokens per session scan A e27f6ec98635
customer-interview is a skill published in the GitHub repository TimboGP/timbogp-marketplace (3 stars, last pushed 2mo ago), licensed MIT. It adds 159 tokens to every session and 1,361 once invoked, about $0.0008 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.
Other skills, from other repositories
recursive-decomposition
Handle tasks that exceed the context window by decomposing them: size and filter the input, chunk it, run recursive sub-agents on independent parts, verify on small windows, and synthesise programmatically, following the Recursive Language Models (RLM) research by Zhang, Kraska and Khattab (2025). Use when a task…
test-driven-development
Strict red-green-refactor TDD workflow for implementing features, fixing bugs, or changing behavior in Rails applications. Enforces the discipline of writing a failing test before any production code. Use whenever you want to implement with TDD — whether a new feature, a bugfix, a refactor, or any behavior change.
git-commit
Turn the working changes into one or more atomic commits with well-written messages. Use whenever the user runs /git-commit or asks to commit their work, wrap up a feature, or "commit what I have.".
swarm
Run a multi-agent audit of a codebase by spawning specialized parallel subagents (security, performance, tests, architecture, dead-code), then synthesize their findings into a single prioritized action plan. Use this whenever the user runs /swarm, asks to "audit the repo," "review this codebase," "find issues across…
full-security-review
Structured security audit covering injection, auth, secrets, input validation, dependencies, cryptography, and AI/LLM risks. Produces severity-graded findings.
log-correlation
Correlates and troubleshoots logs across OS (Linux/macOS), AWS (CloudWatch, CloudTrail, ALB, Lambda), application (JSON, logfmt), and web servers (Nginx, Apache).