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 03-firecrawl-researchgit 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/03-firecrawl-research)<a href="https://agentmods.dev/skills/zevenue/headless-gtm/03-firecrawl-research"><img src="https://agentmods.dev/badge/skills/zevenue/headless-gtm/03-firecrawl-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/zevenue/headless-gtm/03-firecrawl-research"><img src="https://agentmods.dev/badge/skills/zevenue/headless-gtm/03-firecrawl-research.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 Tool Misuse · line 225 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
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 | $0.00086 | $0.02323 |
| Opus 5 | $0.00043 | $0.01162 |
| Sonnet 5 | $0.00017 | $0.00465 |
| Haiku 4.5 | $0.00009 | $0.00232 |
Grade A, and why
03-firecrawl-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 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 — 233 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Firecrawl Research
Given a company domain, scrape its website and return clean markdown organized by page type. Downstream skills (signal-builder, email-writer) consume this output. This skill fetches only - scoring and interpretation belong to signal-builder.
Quick start
The user provides domain(s) and optionally a mode. Default to standard.
| Mode | Credits | Pages |
|---|---|---|
| standard | 5-8 | Homepage, About, Careers, Blog, Pricing, Customers, Integrations, Product |
| deep | 5-11 | Standard + Changelog, Leadership |
| minimal | 3 | Homepage, About only |
| extract | token-billed (varies) | Structured JSON via LLM extraction |
If the user doesn't specify a mode, use standard. Confirm mode before running only when the choice is ambiguous or the batch is large (>50 domains).
Running the scraper
# Single domain
python3 scripts/firecrawl_scrape.py --domain "acme.com" --mode standard
# Batch (one domain per line in file)
python3 scripts/firecrawl_scrape.py --batch domains.txt --mode standard
# Resume interrupted batch
python3 scripts/firecrawl_scrape.py --resume runs/<run-folder-name>
All paths are relative to the skill folder (03-firecrawl-research/).
The script creates a timestamped run folder under runs/ with a tracker.json
for progress and per-domain JSON scan files under runs/<name>/scans/.
After a scrape completes, read the tracker and show the user a summary (completed/failed count, total credits).
Writing to Google Sheet
Use scripts/sheets_writer.py - the Google Sheets MCP fails on large content.
python3 scripts/sheets_writer.py \
--run-dir runs/<run-folder> \
--spreadsheet-id <SHEET_ID>
Options: --summary (char counts instead of full content), --tab-name "name".
Output columns
| Column | Content |
|---|---|
| Domain | acme.com |
| Status | success / partial / blocked |
| Mode | standard / deep / minimal / extract |
| Date | 2026-06-18 |
| URLs Found | 47 |
| Pages Scraped | 6 |
| Credits Used | 7 |
| Homepage…Product | Page content (or empty if not found) |
What ships with it
6 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 · 233 lines · 86 tokens per session scan A e47c9e44bd8e
03-firecrawl-research is a skill published in the GitHub repository Zevenue/headless-gtm (27 stars, last pushed 1mo ago), licensed MIT. It adds 86 tokens to every session and 2,323 once invoked, about $0.0004 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.…