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 agentmods add skills/adelie-squad/solosquad/interview-scriptnpx skills add Adelie-Squad/solosquad --skill interview-scriptgit clone --depth 1 https://github.com/Adelie-Squad/solosquadWhat 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 | $0.00038 | $0.00772 |
| Opus 5 | $0.00019 | $0.00386 |
| Sonnet 5 | $0.00008 | $0.00154 |
| Haiku 4.5 | $0.00004 | $0.00077 |
Grade A, and why
interview-script 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 2d 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.
What it actually says
Interview Script Author Skill
PM 또는 chief 가 호출. 사용자(founder)가 직접 실제 고객과 인터뷰 진행할 때 사용할 script 생성. PM 이 직접 인터뷰하지 않는다.
입력
- target segment 정의
- 검증하려는 hypothesis (XYZ format)
- 기존 customer 가설 (
<org>/domain/customers.md)
Mom Test 원칙 (Rob Fitzpatrick)
- 사람들의 의견 묻지 마라. 그들의 삶을 물어라.
- 미래 가설 묻지 마라. 과거 행동을 물어라.
- 칭찬 받지 마라. 사실을 받아라.
→ "X 기능 좋아하실까요?" ❌ → "마지막으로 [pain] 을 겪었을 때 어떻게 해결하셨나요?" ✅
산출
# Interview Script — {{topic}}
## 목적
{{검증할 hypothesis 1줄}}
## 인터뷰 대상
- Segment: ...
- Recruit criteria: ...
- 최소 N=5
## 진행 (25-30분)
### Warm-up (3분)
- 자기소개
- 최근 어떻게 지내셨는지 (light)
### 과거 행동 탐색 (15분)
1. 가장 최근 [domain] 관련 작업이 언제였나요? 어떤 상황이었나요?
2. 그 작업에서 가장 답답했던 순간은?
3. 그 순간을 어떻게 처리하셨나요? 어떤 도구/방법을 썼나요?
4. (위 도구/방법에 만족 못 한 경우) 다른 시도 해보셨나요?
5. 이 작업에 보통 시간/돈을 얼마 쓰시나요?
### Constraint 탐색 (7분)
- 만약 [hypothetical solution] 이 있다면, 지금 쓰시는 [current solution] 을 *대체* 하시겠어요? 무엇이 *전환* 결정 요인일까요?
- (전환 안 한다면) 어떤 조건이면 전환하시겠어요?
### Wrap-up (3분)
- 우리가 안 물어본 질문 중 이 주제에 중요한 게 있나요?
- 비슷한 고민하시는 분 소개 가능하실까요?
## Scoring Rubric
각 응답을 다음 기준으로 채점:
- Demand evidence: 0-3 (0=interest, 3=actual demand with payment/workaround)
- Specificity: 0-3 (0=vague, 3=specific instance with date+context)
- Switching cost signal: 0-3
HARD GATE
- [ ] 모든 질문이 Mom Test 통과 (no leading, no hypothetical)
- [ ] 과거 행동 질문 ≥ 5
- [ ] scoring rubric 첨부
- [ ] minimum sample N=5 명시
Reference
- Mom Test by Rob Fitzpatrick
- phuryn/pm-skills/pm-product-discovery/interview-script
- v1.1 PRD §9.1 (discovery)
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.
- 2d ago First seen · 94 lines · 38 tokens per session scan A 0ea670ec6cf5
interview-script is a skill published in the GitHub repository Adelie-Squad/solosquad (19 stars, last pushed 12d ago), licensed MIT. It adds 38 tokens to every session and 772 once invoked, about $0.0002 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
context-manager
Context management skill providing discovery, fetching, harvesting, extraction, compression, organization, cleanup, and guided workflows for project context.
tao-list-capabilities
Answer what the TAO Skill Bank plugin can do by generating the response from packaged application, data, model, AutoML, and platform manifests. Use when the user asks "what can TAO Skill Bank do", "list TAO models", "which TAO workflows are available", or "what supports AutoML".
canvas-health
Lint canvas files for staleness, missing fields, inconsistent evidence types, and orphaned references. Run periodically or before major transitions.
find-skills
Discovers, searches, and installs skills from multiple AI agent skill marketplaces (400K+ skills) using the SkillKit CLI. Supports browsing official partner collections (Anthropic, Vercel, Supabase, Stripe, and more) and community repositories, searching by domain or technology, and installing specific skills from…
framework-health
Evaluate Mycelium's own process effectiveness. Measures cycle velocity, discard trends, confidence calibration, gate effectiveness, regression rate. Run quarterly or every 20 cycles.
janitor-discover
Find new skills on GitHub or check a specific skill before installing. Use when the user wants to search for skills, evaluate a skill URL, check overlap and security risk before installing, or compare a local skill against alternatives. Trigger with '/janitor-discover'.