Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/Zevenue/headless-gtmnpx agentmods add skills/zevenue/headless-gtm/04-crustdata-signalsWrote 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/04-crustdata-signals)<a href="https://agentmods.dev/skills/zevenue/headless-gtm/04-crustdata-signals"><img src="https://agentmods.dev/badge/skills/zevenue/headless-gtm/04-crustdata-signals/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/04-crustdata-signals"><img src="https://agentmods.dev/badge/skills/zevenue/headless-gtm/04-crustdata-signals.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
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 →
- medium Rogue Agent · line 17 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00130 | $0.02022 |
| Opus 5 | $0.00065 | $0.01011 |
| Sonnet 5 | $0.00026 | $0.00404 |
| Haiku 4.5 | $0.00013 | $0.00202 |
Grade A, and why
04-crustdata-signals 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 12d 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 — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CrustData Signals
Enrich company domains with structured signal data (funding, growth, departments, recent hires) and write results to Google Sheets across 5 tabs.
Inputs
- Domains - a Google Sheet link/ID with a domain column, or a raw list
- Hire window (optional) - 90, 180, or 365 days back for recent hires (default: 180)
- Output destination - same sheet (new tabs), different sheet ID, or create new
If the user provides a sheet link, extract the spreadsheet ID and ask which tab and column contain the domains.
Prerequisites
CRUSTDATA_API_KEYenv var - get your API key from the CrustData dashboard- Python packages:
pip install -r ../headless-gtm-shared/requirements.txt(Sheets export uses the optionalgspread/google-authextras) - Google Sheets OAuth2 token at
~/.google/token.json
Credit rules
Each API call costs real credits. Treat them like money.
| API | Cost | Rate limit |
|---|---|---|
/company/enrich |
2 credits/company | 15 RPM |
/person/search |
0.03 credits/result | 30 RPM |
Cost per domain scales with how many hires come back, so it is not a flat rate:
2 (enrich) + 0.03 x (hires returned). Budget by the ICP's hiring velocity, not a
single number:
| ICP hiring profile | Hires/company | Cost/domain |
|---|---|---|
| Low-hiring | ~10 | ~2.3 |
| Typical | ~20 | ~2.6 |
| High-growth / high-hiring | ~65 | ~4.0 |
The flat "~2.6" only holds for a typical ~20-hire pull; high-growth ICPs run closer to ~4 credits/domain. Estimate with the actual hire window and expected velocity.
JSON files are the source of truth. Every API call saves a per-domain JSON
to runs/{run-id}/. Before calling the API for any domain, check whether a
JSON already exists in any prior run folder (older runs may sit in the legacy
outputs/ dir - check both). If it does, reuse it - do not spend credits
again. The sheets writer can combine multiple run folders.
What ships with it
5 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.
- 12d ago First seen · 181 lines · 130 tokens per session scan A d10db6a1abb8
04-crustdata-signals is a skill published in the GitHub repository Zevenue/headless-gtm (27 stars, last pushed 1mo ago), licensed MIT. It adds 130 tokens to every session and 2,022 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 2026-08-30.
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.…