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-theirstack-jobsWrote 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-theirstack-jobs)<a href="https://agentmods.dev/skills/zevenue/headless-gtm/04-theirstack-jobs"><img src="https://agentmods.dev/badge/skills/zevenue/headless-gtm/04-theirstack-jobs/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-theirstack-jobs"><img src="https://agentmods.dev/badge/skills/zevenue/headless-gtm/04-theirstack-jobs.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00203 | $0.02557 |
| Opus 5 | $0.00102 | $0.01278 |
| Sonnet 5 | $0.00041 | $0.00511 |
| Haiku 4.5 | $0.00020 | $0.00256 |
Grade A, and why
04-theirstack-jobs scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
recipe, curl examples, verified credit mechanics How it starts
The opening of the file, as written. The whole thing — 200 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TheirStack Jobs - open-req hiring signals (04)
Open job postings are the "what they're about to do" signal: a company hiring its first SDRs is building outbound, a VP Sales req is a strategy shift, three engineering reqs after a raise is product investment. This skill pulls those postings per company and emits chain records ready for judgment. Its sibling 04-crustdata-signals covers what already happened (funding, joins, headcount); this one covers what's open right now.
Two modes
| Mode | Input | Use when |
|---|---|---|
| check | Domains (--domains or an upstream --records records.jsonl) |
You have a list and want hiring evidence per company - the standard step-04 position in the chain |
| discover | Filters only (title/seniority/tech + geo/size/funding) | The ICP is the req itself: "companies hiring SDRs in the US right now". This is the direct entry for hiring-defined ICPs - no firmographic superset needed first |
Prerequisites
THEIRSTACK_API_KEYin env or.env- get one at app.theirstack.com/settings/api- No Python packages required (stdlib only;
python-dotenvis optional - the script falls back to reading.envitself)
Credit rules
Credits are money. The script's whole flow is built around four facts verified live against the balance ledger (2026-07-24):
| Operation | Cost |
|---|---|
Count without company filters (blur_company_data + include_total_results + limit 1) |
0 credits - exact totals of matching jobs AND companies, free. Discover mode sizing is genuinely free |
Count WITH company_domain_or |
Blur silently disables on company-identifier filters (HTTP 200, unblurred, billed per returned job). At limit 1 that is ~1 credit per count - and 0 when the domain has no matches. There is no zero-credit domain-scoped count |
| Job fetch | 1 credit per job returned, exactly |
| Re-fetching a job you already pulled | Charged again - TheirStack has no charge dedup |
Because re-pulls cost full price, every fetched domain is cached as
domains/<domain>.json keyed by a query hash. Re-running the same query
reuses the cache for 0 credits (any prior run folder counts, not just the
current one). --no-cache forces a refetch.
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.
- 12d ago First seen · 200 lines · 203 tokens per session scan A a4fdceca602b
04-theirstack-jobs is a skill published in the GitHub repository Zevenue/headless-gtm (28 stars, last pushed 1mo ago), licensed MIT. It adds 203 tokens to every session and 2,557 once invoked, about $0.0010 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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.…