Market ResearchSAFE

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

The instruction file, verbatim from the audited commit — this is the text the model reads, and the surface the audit's instruction layer examines. Quoted here so you can judge it without cloning anything.

---
name: market-research
description: Conduct market research, competitive analysis, investor due diligence, and industry intelligence with source attribution and decision-oriented summaries. Use when the user wants market sizing, competitor comparisons, fund research, technology scans, or research that informs business decisions.
origin: ECC
---

# Market Research

Produce research that supports decisions, not research theater.

## When to Activate

- researching a market, category, company, investor, or technology trend
- building TAM/SAM/SOM estimates
- comparing competitors or adjacent products
- preparing investor dossiers before outreach
- pressure-testing a thesis before building, funding, or entering a market

## Research Standards

1. Every important claim needs a source.
2. Prefer recent data and call out stale data.
3. Include contrarian evidence and downside cases.
4. Translate findings into a decision, not just a summary.
5. Separate fact, inference, and recommendation clearly.

## Common Research Modes

### Investor / Fund Diligence
Collect:
- fund size, stage, and typical check size
- relevant portfolio companies
- public thesis and recent activity
- reasons the fund is or is not a fit
- any obvious red flags or mismatches

### Competitive Analysis
Collect:
- product reality, not marketing copy
- funding and investor history if public
- traction metrics if public
- distribution and pricing clues
- strengths, weaknesses, and positioning gaps

### Market Sizing
Use:
- top-down estimates from reports or public datasets
- bottom-up sanity checks from realistic customer acquisition assumptions
- explicit assumptions for every leap in logic

### Technology / Vendor Research
Collect:
- how it works
- trade-offs and adoption signals
- integration complexity
- lock-in, security, compliance, and operational risk

## Output Format

Default structure:
1. executive summary
2. key findings
3. implications
4. risks and caveats
5. recommendation
6. sources

## Quality Gate

Before delivering:
- all numbers are sourced or labeled as estimates
- old data is flagged
- the recommendation follows from the evidence
- risks and counterarguments are included
- the output makes a decision easier

SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.

What the source does

Filesystem

none-observed

Network

none-observed

Shell

none-observed

Dependencies

pinned

Secrets in source

none-found

Findings (0)

No findings outside the package's declared scope.

Gates applied: no_behavioural_pass.