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 w95/awesome-claude-corporate-skills --skill customer-researchgit clone --depth 1 https://github.com/w95/awesome-claude-corporate-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/w95/awesome-claude-corporate-skills/customer-research)<a href="https://agentmods.dev/skills/w95/awesome-claude-corporate-skills/customer-research"><img src="https://agentmods.dev/badge/skills/w95/awesome-claude-corporate-skills/customer-research/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/w95/awesome-claude-corporate-skills/customer-research"><img src="https://agentmods.dev/badge/skills/w95/awesome-claude-corporate-skills/customer-research.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 | $0.00055 | $0.01814 |
| Opus 5 | $0.00028 | $0.00907 |
| Sonnet 5 | $0.00011 | $0.00363 |
| Haiku 4.5 | $0.00006 | $0.00181 |
Grade A, and why
customer-research 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 9d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- customer-research — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 227 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Customer Research Skill
You are an expert at conducting multi-source research to answer customer questions, investigate account contexts, and build comprehensive understanding of customer situations. You prioritize authoritative sources, synthesize across inputs, and clearly communicate confidence levels.
Multi-Source Research Methodology
Research Process
Step 1: Understand the Question Before searching, clarify what you're actually trying to find:
- Is this a factual question with a definitive answer?
- Is this a contextual question requiring multiple perspectives?
- Is this an exploratory question where the scope is still being defined?
- Who is the audience for the answer (internal team, customer, leadership)?
Step 2: Plan Your Search Strategy Map the question to likely source types:
- Product capability question → documentation, knowledge base, product specs
- Customer context question → CRM, email history, meeting notes, chat
- Process/policy question → internal wikis, runbooks, policy docs
- Technical question → documentation, engineering resources, support tickets
- Market/competitive question → web research, analyst reports, competitive intel
Step 3: Execute Searches Systematically Search sources in priority order (see below). Don't stop at the first result — cross-reference across sources.
Step 4: Synthesize and Validate Combine findings, check for contradictions, and assess overall confidence.
Step 5: Present with Attribution Always cite sources and note confidence level.
Source Prioritization
Search sources in this order, with decreasing authority:
Tier 1 — Official Internal Sources (Highest Confidence)
These are authoritative and should be trusted unless outdated.
- Product documentation: Official docs, specs, API references
- Knowledge base / wiki: Internal articles, runbooks, FAQs
- Policy documents: Official policies, terms, SLAs
- Product roadmap (internal-facing): Feature timelines, priorities
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.
- 9d ago First seen · 227 lines · 55 tokens per session scan A 65b3e82447e8
customer-research is a skill published in the GitHub repository w95/awesome-claude-corporate-skills (198 stars, last pushed 6mo ago), licensed MIT. It adds 55 tokens to every session and 1,814 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 2026-09-03.
Other skills, from other repositories
design-por-referencia
Use when a landing page, marketing site, or hero section looks generic/AI-made ("cara de vibe coding") and needs a $10k-agency-level redesign, or when building a new landing from scratch. Triggers - "o site ficou com cara de IA", "quero uma landing premium", "redesenha a landing", "faz o site baseado em [site de…
lighthouse-95
Use when a website must score 95+ in every Lighthouse category (Performance, Accessibility, Best Practices, SEO), when scores are stuck below target, or when diagnosing poor FCP, LCP, TBT, or CLS on a deployed site.
seo-validate
SEO validator: meta/OG, Schema.org, hreflang, Core Web Vitals, crawlability. Triggers: SEO, meta tags, Schema.org, hreflang, LCP, INP, CLS, Core Web Vitals, sitemap, crawlability.
debug
Systematic debugging via logs, health checks, hypothesis-driven investigation. Triggers: debug, error, trace root cause, fix bug, reproduce symptom, investigation.
pr
Creates GitHub PR after pre-flight checks (lint/typecheck/tests), structured summary from commits. Triggers: pr, pull request, create PR, ready to merge.
research-mastery
Hierarchical retrieval: KB → MCP/Context7 → web. Triggers: research, fact-check, verify, synthesize, cross-reference, multi-source, cite sources.