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.
git clone --depth 1 https://github.com/2612evgenii-hue/business-idea-evaluatorWrote 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/agents/2612evgenii-hue/business-idea-evaluator/biz-eval-17-sensitivity)<a href="https://agentmods.dev/agents/2612evgenii-hue/business-idea-evaluator/biz-eval-17-sensitivity"><img src="https://agentmods.dev/badge/agents/2612evgenii-hue/business-idea-evaluator/biz-eval-17-sensitivity/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/agents/2612evgenii-hue/business-idea-evaluator/biz-eval-17-sensitivity"><img src="https://agentmods.dev/badge/agents/2612evgenii-hue/business-idea-evaluator/biz-eval-17-sensitivity.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 | $0.00027 | $0.00250 |
| Opus 5 | $0.00014 | $0.00125 |
| Sonnet 5 | $0.00005 | $0.00050 |
| Haiku 4.5 | $0.00003 | $0.00025 |
Grade A, and why
biz-eval-17-sensitivity 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.
This is a copy
89% identical to biz-eval-13-evidence-stats — 14 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
You are a sensitivity analyst. Input: Expert Evidence Package.
Find top 5 parameters where ±30% change flips viability.
fragility_index 0-10, critical_assumptions[], zero_out_risks[].
Output JSON agent_id "17".
Math-layer contract (agents 13–18)
You receive the FULL Expert Evidence Package and work INDEPENDENTLY of the other math agents (own context, no shared scratchpad). Compute — do not restate prose. Weight by the experts' sources, evidence_level and confidence. Output numeric parameters with ranges (min/base/max where applicable). Lower your numbers when the evidence base is weak. Explicitly flag the single assumption that most moves the result.
Critical
- Return ONLY valid JSON (no markdown fences, no commentary).
- Follow schema in .agents/skills/business-idea-evaluator/references/expert-evidence-package.md
- Be objective. No flattery. Tag evidence status on claims.
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 · 23 lines · 27 tokens per session scan A a4acd8f82c7e
biz-eval-17-sensitivity is an agent published in the GitHub repository 2612evgenii-hue/business-idea-evaluator (2 stars, last pushed 2mo ago), licensed MIT. It adds 27 tokens to every session and 250 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 89% identical to biz-eval-13-evidence-stats, differing in 14 lines, and is treated as a copy.
Other agents, from other repositories
boss-scrum-master
A technical Scrum Master agent that turns a product story into small, assignable development tasks. Scrum is a software-planning method, and a story is a short description of a user need.
boss-architect
A software architecture reviewer and designer that researches technology choices before creating a full-stack plan. Full-stack means covering the user interface, server, database, and deployment environment.
boss-ui-designer
A UI/UX design agent that turns product requirements into detailed interface rules and a machine-readable design file. UI/UX covers how an interface looks, behaves, and can be used.
boss-backend
A backend development agent for building server-side APIs, database operations, business rules, security checks, and tests. It follows a layered structure where controllers receive requests, services apply rules, and repositories access data.
boss-frontend
A frontend development specialist agent that builds user-interface components and frontend features according to existing design specifications.
boss-tech-lead
A technical lead agent that reviews architecture and implementation plans for feasibility, maintainability, completeness, performance, security, and cost.