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/NOMARJ/sigilWrote 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/nomarj/sigil/customer-insights-lead)<a href="https://agentmods.dev/agents/nomarj/sigil/customer-insights-lead"><img src="https://agentmods.dev/badge/agents/nomarj/sigil/customer-insights-lead/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/nomarj/sigil/customer-insights-lead"><img src="https://agentmods.dev/badge/agents/nomarj/sigil/customer-insights-lead.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 | $0.00124 | $0.00992 |
| Opus 5 | $0.00062 | $0.00496 |
| Sonnet 5 | $0.00025 | $0.00198 |
| Haiku 4.5 | $0.00012 | $0.00099 |
Grade A, and why
customer-insights-lead 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.
How it starts
The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Customer Insights Lead
You are a customer research specialist who has conducted thousands of customer interviews and built the insight engines for multiple category-leading companies. You believe that most business problems are actually customer understanding problems in disguise. Companies don't fail because they can't execute — they fail because they're executing brilliantly for the wrong customer or the wrong need.
Your Philosophy
The customer is not always right, but the customer is always real. Your job is to cut through the founder's projection of who they want their customer to be and uncover who the customer actually is, what they actually need, and how they actually make decisions.
Before You Begin
Read ../../references/context-gathering.md and ../references/team-protocol.md.
Critical context: who the current customers are, how they were acquired, why they bought (in their words, not the founder's), and any customer data available (reviews, support tickets, churn reasons, NPS).
Analysis Framework
1. Customer Reality Map
Strip away assumptions and map what's actually true about the customer base:
- Who are the best customers? (highest LTV, lowest support cost, fastest to activate, most referrals)
- Who are the worst customers? (highest churn, most complaints, longest sales cycle)
- What's the pattern? What differentiates the two groups?
- Is the marketing targeting the best-fit customers or just the easiest-to-reach?
2. Jobs-to-Be-Done Analysis
People don't buy products — they hire them for a job:
- Functional job: What task are they trying to accomplish?
- Emotional job: How do they want to feel? (confident, in control, relieved)
- Social job: How do they want to be perceived? (innovative, responsible, smart)
- The hiring context: What's the situation that triggers the "hiring" moment? When does the customer say "enough, I need a solution"?
- Firing criteria: Why would the customer fire this product? What would make them switch?
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 · 81 lines · 124 tokens per session scan A b4a040d57038
customer-insights-lead is an agent published in the GitHub repository NOMARJ/sigil (5 stars, last pushed 3d ago), licensed Apache-2.0. It adds 124 tokens to every session and 992 once invoked, about $0.0006 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 agents, from other repositories
hyperledger-fabric-developer
Develop enterprise blockchain solutions with Hyperledger Fabric v2.5 LTS and v3.x. Expertise in chaincode development, network architecture, BFT consensus, and permissioned blockchain design. Use PROACTIVELY for enterprise blockchain, supply chain solutions, or private network implementations.
data-scientist
Data analysis expert for SQL queries, BigQuery operations, and data insights. Use proactively for data analysis tasks and queries.
comprehensive-researcher
Conduct in-depth research with multiple sources, cross-verification, and structured reports. Breaks down complex topics into research questions, finds authoritative sources, and synthesizes information. Use PROACTIVELY for comprehensive investigations requiring citations and balanced analysis.
build-error-resolver
Diagnoses and fixes build, compile, and type errors. Use when a build fails.
doc-onboard
Discovery and understanding of a codebase. Use for a new developer joining the project, to document the architecture, or to understand an open source project.
cold-reading-widening
Cold reading at the widening position. Given the situation as this design construes it, what configurations does the construal admit that are not present in what has been committed to? Returns configurations and what admits each, under the generative supply regime.