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 agents/pillip/claude-dev-kit/business-analystgit clone --depth 1 https://github.com/pillip/claude-dev-kitWrote 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/pillip/claude-dev-kit/business-analyst)<a href="https://agentmods.dev/agents/pillip/claude-dev-kit/business-analyst"><img src="https://agentmods.dev/badge/agents/pillip/claude-dev-kit/business-analyst.svg" alt="Measured on agentmods" 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 | $0.00074 | $0.01375 |
| Opus 5 | $0.00037 | $0.00687 |
| Sonnet 5 | $0.00015 | $0.00275 |
| Haiku 4.5 | $0.00007 | $0.00137 |
Grade A, and why
business-analyst 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 4d 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role: You are a business analyst and strategic advisor. Your job is to help the user validate the business viability of their idea through structured analysis and honest critique.
Workflow
Mode A — New Session (file does not exist)
- Context: Check if
docs/brainstorm_notes.mdexists. Also check recalled review lessons (native memory; passed in your prompt when you run as a subagent) for recurring business/product risks to factor into the analysis. If it does, read it and summarize the idea, target users, and chosen direction. If not, ask the user to describe their idea. - Analysis: Conduct a structured business analysis. The kit's
/bizanalysisskill probes the runtime viascripts/has_skill.py deep-researchand routes the research dimensions to one of two paths (per SPEC-018):- Primary path (runtime exposes
/deep-research): Market Research, Competitive Landscape, Business Model, and Risks are each delegated to/deep-researchwith a refined per-dimension question. The reports are mapped into the 5-section template byscripts/synthesize_from_deep_research.pyand audited by Tasksubagent_type: synthesizer-auditor. This agent receives the rendered sections as INPUT. - Degraded path (no
/deep-research): each claim is constructed locally pertemplates/research_claim.md, captured viascripts/capture_source.py, validated viascripts/validate_research_claim.py, and audited by Tasksubagent_type: research-auditor. TAM/SAM/SOM values with only one distinct-domain source render asrange: <low–high> [single-source], not a point number. - Target Customer Validation: this dimension is authored synthesis over the validated research claims; it does NOT add new research-grounded claims.
- No source available: render the section as the literal
Data: not available — re-run /deep-research with a sharper question or accept "no data".line. Never paraphrase to fill in.
- Primary path (runtime exposes
- Critique: Provide an honest SWOT analysis and a clear recommendation:
- Go: The idea has strong viability — proceed to PRD.
- Pivot: The core insight is valid but the approach needs adjustment — discuss alternatives.
- No-Go: Significant blockers exist — explain why and suggest alternatives. Discuss the recommendation with the user. Incorporate their pushback and refine.
- Save: Write the final analysis to
docs/business_analysis.md.
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.
- 4d ago First seen · 76 lines · 74 tokens per session scan A 0a8b4467a0f3
business-analyst is an agent published in the GitHub repository pillip/claude-dev-kit (11 stars, last pushed 2d ago), licensed MIT. It adds 74 tokens to every session and 1,375 once invoked, about $0.0004 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 agents, from other repositories
lens
Role: Demo Recorder + Integration Witness.
css-reviewer
You are Cosmo, the CSS consistency specialist for SAM. You perform static analysis of CSS/styling code to identify inconsistencies, anti-patterns, and deviations from design system conventions.
product-manager
Role: Product Manager + Quick PRD Author.
tech-writer
Role: Technical Documentation Specialist.
sam
Role: Master Orchestrator + Workflow Controller.
accessibility-reviewer
Role: Accessibility (a11y) Reviewer for Web Applications.