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 Zevenue/headless-gtm --skill 01-icp-qualifygit clone --depth 1 https://github.com/Zevenue/headless-gtmWrote 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/zevenue/headless-gtm/01-icp-qualify)<a href="https://agentmods.dev/skills/zevenue/headless-gtm/01-icp-qualify"><img src="https://agentmods.dev/badge/skills/zevenue/headless-gtm/01-icp-qualify/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/zevenue/headless-gtm/01-icp-qualify"><img src="https://agentmods.dev/badge/skills/zevenue/headless-gtm/01-icp-qualify.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Anti-Refusal · line 189 Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.Fix: Remove instructions that suppress warnings, disclaimers, or ethical commentary. Let the agent surface safety-relevant caveats to the user.
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 | $0.00176 | $0.02271 |
| Opus 5 | $0.00088 | $0.01136 |
| Sonnet 5 | $0.00035 | $0.00454 |
| Haiku 4.5 | $0.00018 | $0.00227 |
Grade A, and why
01-icp-qualify 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 11d 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 — 192 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ICP Qualify - the gate
Discovery filters match labels (industry codes, size bands, locations as a database recorded them). This skill judges fit: would this specific company plausibly buy from this specific client? The two questions diverge constantly - acquisitions, competitors, stale headcounts, and shell listings all pass label filters and then waste enrichment spend downstream. The gate exists so every credit spent after discovery goes to a company that could actually buy.
The skill is general-purpose by construction: nothing client-specific is hardcoded. It first understands the client, then compiles a client-specific qualification brief, gets it approved, and only then judges prospects.
Phase 1 - understand the client
Detect the operating mode; never ask for what is already available.
- Package mode - running inside the chain: inherit the client profile (what they sell, ICP bounds, exclusions) from the chain's client-profile artifact or the router's plan. Ask nothing.
- Standalone mode - invoked directly: the user names the client company and provides whatever they have - ICP description, firmographic bounds, competitor names, exclusion list. Proceed with whatever exists. Missing information never blocks a run.
Research fallback (bounded). If the client's business or ICP is still unclear, read the client's own website - homepage, about, product pages, at most ~5 pages - and draft the missing understanding. Cache everything learned into the client profile so research runs once per client, not once per run.
Phase 2 - compile the qualification brief
From the client understanding, write the criteria that will judge every prospect. The brief has two mandatory checks, one universal check, and client-specific dynamic checks:
- Business nature (primary). What does the prospect actually do, judged from its description - and does that match who the client sells to? This is also where competitors are caught: a prospect in the client's own product category is never a lead.
- Firmographics. Headcount band, geography, industry bounds from the ICP. Cheap, rule-based - and applied with the wide-tolerance rule below, because discovery data is often stale.
- Independence and liveness (universal). Is this still an operating, independent business? Acquired, merged, dormant, or shell companies are not buyers regardless of fit. This check is client-independent and always on.
- Dynamic checks (client-specific). Derive 1–3 checks from this client's reality that the generic checks can't know - e.g. for a QA-automation client: "does the prospect ship software?"; for a payroll client: "does the prospect have employees in the covered countries?". These are generated fresh per client, from the profile and research.
What ships with it
3 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.
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.
- 11d ago First seen · 192 lines · 176 tokens per session scan A 5c6149de137a
01-icp-qualify is a skill published in the GitHub repository Zevenue/headless-gtm (27 stars, last pushed 1mo ago), licensed MIT. It adds 176 tokens to every session and 2,271 once invoked, about $0.0009 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 skills, from other repositories
gtm-machine
Validate startup ideas with evidence and test them with real outbound — the full loop from raw idea to booked calls. Use this skill whenever an idea-stage founder wants to validate a startup or product idea, assess AI-platform kill-risk, check if a market is worth entering, build an ICP or personas, source leads from…
deepline-ads-audiences
Use this skill when building, enriching, auditing, or uploading B2B paid ads audiences to Google Customer Match, Meta/Facebook Custom Audiences, or LinkedIn Matched Audiences. Triggers on phrases like '/deepline-ads-audience', '/deepline-ads-audiences', 'upload this audience', 'create custom audiences', 'personal…
deepline-gtm
GTM prospecting, enrichment, outreach, and Deepline Play work/audits. Providers…
deepline-pre-research
Use when the user wants a last30days-style pre-research pass in Deepline: discover the critical public, private, CRM, workflow, social, and web data sources for a research/enrichment job; compare provider coverage; estimate Deepline credit cost; recommend the source plan before building or running the workflow; or…
deepline-analytics
Use this skill when answering business analytics, RevOps, GTM metric, pipeline, revenue, funnel, customer, or warehouse questions with Deepline. Triggers on phrases like 'query Snowflake', 'analyze pipeline', 'total ACV', 'break down by quarter', 'use the semantic layer', 'run a semantic query', or any use of…
niche-signal-discovery
Discover niche first-party signals that differentiate Closed Won vs Closed Lost accounts for ICP analysis. Use when the user provides won/lost customer domain lists and wants differential signals (website content, job listings, tech stack, maturity markers) to build account scoring models and prospecting criteria.…