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/07-campaign-sheetWrote 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/07-campaign-sheet)<a href="https://agentmods.dev/skills/zevenue/headless-gtm/07-campaign-sheet"><img src="https://agentmods.dev/badge/skills/zevenue/headless-gtm/07-campaign-sheet/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/07-campaign-sheet"><img src="https://agentmods.dev/badge/skills/zevenue/headless-gtm/07-campaign-sheet.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 | $0.00152 | $0.01148 |
| Opus 5 | $0.00076 | $0.00574 |
| Sonnet 5 | $0.00030 | $0.00230 |
| Haiku 4.5 | $0.00015 | $0.00115 |
Grade A, and why
07-campaign-sheet 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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Campaign sheet (07)
The last step in the chain. Everything upstream produced records.jsonl; this
turns those records into what an owner actually uses - a ranked "who to contact
first and why" sheet, plus a CSV shaped for a one-click HubSpot import.
It adds no fields to the chain and nothing reads its output. The CSV is a
derived, human-facing export (headless-gtm-shared/CONVENTIONS.md) - the
canonical record stays records.jsonl, and re-running any upstream skill never
depends on this sheet.
What it reads
A terminal records.jsonl from any stage. The script tolerates every shape and
degrades instead of failing:
- Company name from
company(orname), site fromwebsite(orhttps://+domain), phone / city from wherever the discovery step put them. - Ranking from 05's
signals[]- the highest-score signal per record decides call order; itssignal_type,signal_sentence, andsource_urlbecome the "why now" line, and itsapproach(orfallback_approach) the recommended angle. Records with no signals stay in the sheet, ranked last. - Contacts from 06's
person_name/matched_title/email/verification_status. When 06 has not run, the contact columns are dropped entirely rather than shipped empty. - Rows with no website ride through on their listing fields - the sheet does not
drop them (a registry row with
domainempty is still a real target).
What it writes
runs/<run-id>/ (via common.runs_base(), step prefix 07):
campaign-sheet.md- owner-readable. Ranked cards for the top targets (company, city, why now with source, approach, contact or "not resolved"), then a compact table for the rest, then a "before you send" note.campaign-sheet.csv- HubSpot default contact-import headers:First Name, Last Name, Email, Company Name, Website URL, Phone Number, Lifecycle Stage, Notes. Every row is set to Lifecycle Stage = Lead;Notescarries the top signal and the recommended approach. First/Last/Email appear only when at least one record is resolved, and aListing URLcolumn appears only when at least one record carries one (directory-sourced runs) - so a phone-only registry row still exports a working link. The headers are HubSpot's defaults because it is the most common import target; every field is a plain column, so any other CRM (Salesforce, Pipedrive, Attio) takes the same file after a one-time header remap on import.
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.
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 · 95 lines · 152 tokens per session scan A 8fecdc480a00
07-campaign-sheet is a skill published in the GitHub repository Zevenue/headless-gtm (27 stars, last pushed 1mo ago), licensed MIT. It adds 152 tokens to every session and 1,148 once invoked, about $0.0008 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.…