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 forjd/startup-ideation-skills --skill startup-interview-synthesisgit clone --depth 1 https://github.com/forjd/startup-ideation-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/forjd/startup-ideation-skills/startup-interview-synthesis)<a href="https://agentmods.dev/skills/forjd/startup-ideation-skills/startup-interview-synthesis"><img src="https://agentmods.dev/badge/skills/forjd/startup-ideation-skills/startup-interview-synthesis/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/forjd/startup-ideation-skills/startup-interview-synthesis"><img src="https://agentmods.dev/badge/skills/forjd/startup-ideation-skills/startup-interview-synthesis.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 | $0.00053 | $0.01434 |
| Opus 5 | $0.00026 | $0.00717 |
| Sonnet 5 | $0.00011 | $0.00287 |
| Haiku 4.5 | $0.00005 | $0.00143 |
Grade A, and why
startup-interview-synthesis 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.
How it starts
The opening of the file, as written. The whole thing — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Startup Interview Synthesis
When to use
Use after interviews, outreach replies, paid-audit conversations, smoke-test responses, or validation-test notes have been collected, and before deciding whether to scope a v1.
This skill turns messy qualitative evidence into a decision. It should not convert polite interest into validation.
Core rule
Separate observed behaviour from opinion, compliments, guesses, and founder interpretation. Treat contradictions as useful evidence, not noise to smooth away.
Inputs to request if missing
Ask only for the missing inputs needed to make the synthesis credible:
Problem statement:
Target user:
Validation goal:
Interview notes or outreach replies:
Test setup:
Success / kill criteria:
Evidence packet so far:
If the user has raw notes, synthesize from them. If they only have a summary, mark confidence lower and ask for exact quotes, commitments, and objections.
Workflow
- Normalize the notes by respondent, role, segment, source, and date if available.
- Extract evidence as short claims tied to exact quotes or observed behaviour.
- Classify each signal as
Strong,Mixed,Weak, orNoise. - Separate problem reality, buyer/budget, urgency, workaround, reachability, willingness-to-pay, why-now, and behavioural commitment.
- Look for contradictions between respondents, segments, and stated intent versus behaviour.
- Identify the strongest evidence for and against the idea.
- Decide whether the validation criteria were met, missed, or remain inconclusive.
- Update the evidence packet with a proceed, narrow, retest, park, or kill gate.
Evidence quality rubric
Strong signals:
- A respondent describes a recent real instance with cost, workaround, and consequences.
- The buyer or budget owner is identified and reachable.
- Someone agrees to a concrete next step: introduction, paid audit, pilot, LOI, trial, data share, or calendar follow-up.
- The same pain appears across several similar users without being prompted.
- A respondent already spends time, money, political capital, or risk budget on the workaround.
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 · 180 lines · 53 tokens per session scan A 3ab9b72ebe82
startup-interview-synthesis is a skill published in the GitHub repository forjd/startup-ideation-skills (2 stars, last pushed 2mo ago), licensed MIT. It adds 53 tokens to every session and 1,434 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 2026-08-31.
Other skills, from other repositories
hunt-auth-bypass
Hunting skill for auth bypass vulnerabilities. Built from 12 public bug bounty reports across SAML XSW / parser-differential (GitHub Enterprise CVE-2025-25291/25292), SAML signature stripping (Uber, Rocket.Chat, samlify CVE-2025-47949), SAML domain enforcement bypass via control characters (HackerOne 2024)…
m365-entra-attack
Microsoft 365 / Entra ID red-team attack chain — current 2026 reality. AADSTS code reference, user enumeration vectors (with hardening status), Smart Lockout math, Conditional Access bypass options, ROPC + SAML SSO browser flow, Burp/Playwright templates. Built from authorized red-team work where ROPC spray surfaced…
password-spray-methodology
End-to-end password spray playbook. User enumeration, lockout detection, password pattern generation, spray execution across all protocols, error code differentials, and engagement discipline. Unifies M365/Entra, Okta, Exchange, Kerberos, SharePoint, XMLRPC, OIDC, and AD SMB/WinRM spraying into one methodology.
subdomain-enumeration
Map subdomains via crt.sh and subfinder at recon kickoff.
cache-attack
Poison CDN cache or deceive when X-Cache header is detected.
recon-sector
Parameterized sector recon using sector database.