What is validate-lead?

A company-screening workflow that checks whether a business matches your ideal customer profile (ICP), meaning the type of company you want to sell to. It can review company information and, when supplied, a job listing or LinkedIn page.

Use it to assess one company, review several unreviewed companies from an outreach sheet, or record a learning that should improve future checks.

It reduces manual research and applies your chosen scoring rules and disqualifiers consistently. This helps separate promising leads from companies that do not fit.

validate-lead — Skill for Claude Code by himanshusaleria

Install

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.

Any agent

npx skills add himanshusaleria/gtm-engine --skill validate-lead

Clone the repo

git clone --depth 1 https://github.com/himanshusaleria/gtm-engine

Made for: Claude Code.

Or install gtm-engine, the plugin that ships this one along with the rest of its 8 skills.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/himanshusaleria/gtm-engine/validate-lead.svg)](https://agentmods.dev/skills/himanshusaleria/gtm-engine/validate-lead)

Your own site

<a href="https://agentmods.dev/skills/himanshusaleria/gtm-engine/validate-lead"><img src="https://agentmods.dev/badge/skills/himanshusaleria/gtm-engine/validate-lead.svg" alt="Measured on agentmods" height="20"></a>

Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,097 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00000	$0.01097
Opus 5	$0.00000	$0.00549
Sonnet 5	$0.00000	$0.00219
Haiku 4.5	$0.00000	$0.00110

Measured 8d ago against content hash 8949a27bfdd1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

validate-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 8d 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.

skills/validate-lead/SKILL.md · 142 lines

How it starts

The opening of the file, as written. The whole thing — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/validate-lead — ICP Lead Validation

Validate whether a company is an ICP fit based on research and your ICP scoring criteria.

Usage

/validate-lead {company} [job_url] — Validate a single company
/validate-lead --batch — Validate unreviewed companies from your outreach sheet
/validate-lead --improve "learning" — Add a learning to improve future validations

Prerequisites

config/config.yaml with ICP section filled (scoring criteria, no-go rules, tiers)
Recommended: my-context/icp-definition.md filled (via /setup --icp)

Default Mode Flow

Step 1: Load Context (parallel reads)

Read these files in parallel:

~/.claude/skills/validate-lead/learnings.md
my-context/icp-definition.md (if exists)
config/config.yaml -> icp section

Step 2: Research the Company (parallel where possible)

If job URL provided: WebFetch the listing -> extract role title, tech stack, requirements, company description
WebSearch "{company} what they do product" -> understand what they build
WebSearch "{company} employees team size" -> estimate headcount
If LinkedIn URL provided: WebFetch it

Step 3: Apply No-Go Rules (check FIRST before scoring)

Read config.icp.no_go_rules. Auto-reject if ANY rule matches.

If No-Go triggered -> output verdict immediately with reason. Skip scoring.

Step 4: Score on ICP Scale

Use config.icp.scoring_criteria for criteria. Each criterion scored 0 or 1. Sum scores and apply tier thresholds from config.icp.tiers:

Score >= config.icp.tiers.core = Core ICP
Score >= config.icp.tiers.broader = Broader ICP
Below broader threshold = Not ICP

Step 5: Output

Present results in this format:

## {Company Name} — Lead Validation

### Verdict
| Field | Value |
|-------|-------|
| ICP Fit? | Yes / No |
| Action | Go ahead / No go |
| Summary | {one-line summary} |

### Research Summary
- **What they do:** ...
- **Headcount:** ...
- **Geography:** ...
- **Product type:** ...
- **Job listing signals:** ... (if applicable)

### ICP Scorecard ({X}/{max})
| # | Criterion | Score | Reasoning |
|---|-----------|-------|-----------|
| 1 | {criteria from config} | 0/1 | ... |
| 2 | ... | 0/1 | ... |

### Caveats
- ...

Read the full file on GitHub · 142 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

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.

8d ago First seen · 142 lines · 0 tokens per session scan A 8949a27bfdd1

Subscribe to this mod's changes

validate-lead is a skill published in the GitHub repository himanshusaleria/gtm-engine (18 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,097 tokens. 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.

Claude Code Marketing and SEO Research ai-agents anthropic b2b-sales claude claude-skills

review-work

Post-implementation gate review: run manual QA on the real surface yourself, then launch ONE gate reviewer (never a panel) to audit goal, constraints, code quality, security, missed context, and QA evidence. Use before a PR handoff or when the user explicitly asks to review completed work.

code-yeongyu/oh-my-openagent · 63 tokens

validate-lead