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 swan-gtm/gtm-skills --skill lookalike-candidate-sourcinggit clone --depth 1 https://github.com/swan-gtm/gtm-skillsWrote 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/swan-gtm/gtm-skills/lookalike-candidate-sourcing)<a href="https://agentmods.dev/skills/swan-gtm/gtm-skills/lookalike-candidate-sourcing"><img src="https://agentmods.dev/badge/skills/swan-gtm/gtm-skills/lookalike-candidate-sourcing/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/swan-gtm/gtm-skills/lookalike-candidate-sourcing"><img src="https://agentmods.dev/badge/skills/swan-gtm/gtm-skills/lookalike-candidate-sourcing.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 | $0.00063 | $0.00763 |
| Opus 5 | $0.00032 | $0.00381 |
| Sonnet 5 | $0.00013 | $0.00153 |
| Haiku 4.5 | $0.00006 | $0.00076 |
Grade A, and why
lookalike-candidate-sourcing 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 — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Use this when one hire worked and you want more like them. It produces a ranked shortlist where every score decomposes into title, skills, seniority, and location, so a hiring manager can argue with it.
The play
-
Take one exemplar, not a job description. A JD describes what someone wrote down. A person who is actually good in the role describes what worked. Start from the exemplar's real current title, skills, and location.
-
Push filters into the search, not into post-processing. Role family, country, city, and current-role-only belong in the query. Filtering a large result set client-side wastes lookups and hides how narrow you actually were.
-
Start broad, then tighten once. Role family plus two skills plus a country is a good opening net. Stacking an exact title, an all-skills-match, and a city returns zero and looks like "nobody exists" when it is really a bad query.
-
Decide whether to enrich. Without enrichment you get a cheap keyword-ordered list. With it you get skills, education, and geography per candidate, at one extra lookup each. Enrich 20, not 200, until the shortlist direction is confirmed.
-
Score transparently out of 100:
- Title match, 40 — exact title 40, same role family at any seniority 25, different family 0.
- Skills overlap, 30 — shared skills over the exemplar's skill count, times 30, compared on normalized names.
- Seniority, 15 — same level 15, one level off 7, further 0. Infer from title prefix: Senior, Staff, Principal, Head of, VP.
- Location, 15 — same city 15, same metro 10, same country 5.
-
Drop the exemplar before ranking. Search returns them, they score 100, and it makes the list look broken.
-
Return a table, not JSON. Name, current title, company, location, score, and the one line explaining the score.
What good looks like
- The strongest sourcers treat a zero-result search as information about the query, not the market, and can say which filter they loosened and why.
- The mediocre version returns fifty unranked names and calls it a pipeline, leaving the hiring manager to do the actual sourcing work.
- A score is only useful if it decomposes. "77" means nothing; "77: exact title, 6 of 9 skills, one level junior, same metro" is a conversation.
- You know it is good when the hiring manager disagrees with a specific score for a specific reason. That means they can see the reasoning.
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 · 45 lines · 63 tokens per session scan A d388fc04bdee
lookalike-candidate-sourcing is a skill published in the GitHub repository swan-gtm/gtm-skills (150 stars, last pushed 2d ago), licensed MIT. It adds 63 tokens to every session and 763 once invoked, about $0.0003 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
recruit-outreach
Personalized Recruiting Outreach — LinkedIn InMail templates, cold email, second-touch follow-ups customized to the candidate's background.
recruit-outreach
Personalized Recruiting Outreach — LinkedIn InMail templates, cold email, second-touch follow-ups customized to the candidate's background.
ai-dev-jobs-mcp
Search 8,400+ AI and ML jobs across 489 companies, inspect listings and employers, match roles, and view salary and market stats via AI Dev Jobs MCP.
afrexai-lead-hunter
Enterprise-grade B2B lead generation, enrichment, scoring, and outreach sequencing for AI agents. Find ideal prospects, enrich with verified data, score against your ICP, and generate personalized outreach — all autonomously.
smart-sourcing
Selects optimal sources for tool calls, balancing accuracy with token cost. Use before research tasks or when deciding whether a claim needs verification.
first-customer-finder
Find and qualify evidence-backed potential first customers, early adopters, design partners, or beta users for a startup using recent public pain and buying signals. Use when Codex needs to analyze a product URL or idea, define an ideal customer profile, research public discussions and business pages, identify…