Getting it into your agent
There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.
Wrote 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/thtskaran/claude-skills/people-sourcer)<a href="https://agentmods.dev/skills/thtskaran/claude-skills/people-sourcer"><img src="https://agentmods.dev/badge/skills/thtskaran/claude-skills/people-sourcer/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/thtskaran/claude-skills/people-sourcer"><img src="https://agentmods.dev/badge/skills/thtskaran/claude-skills/people-sourcer.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 | $0.00227 | $0.04841 |
| Opus 5 | $0.00113 | $0.02420 |
| Sonnet 5 | $0.00045 | $0.00968 |
| Haiku 4.5 | $0.00023 | $0.00484 |
Grade A, and why
people-sourcer 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 — 327 lines — stays where its author put it; the contents beside it link to each section on GitHub.
People Sourcer
A real recruiter, BD person, or research lead doesn't open a CRM first. They start with a question: who specifically am I trying to reach, and why? Then they hunt — across whichever platform that tribe actually lives on — and they keep notes. This skill makes Claude work that way, end-to-end, into a spreadsheet the user can act on.
Core premise
Spam happens when you compile names without context. A list with 200 anonymous LinkedIn URLs is worse than 30 rows where each one has a real signal — this person posted last week about exactly your problem, here's how to enter their world.
So the rule is: never source from zero. Always source from signal. Find the place where the right people are already self-identifying, scrape that signal, then enrich and personalize. The personalization is what makes the difference between a useful list and noise.
When to use this skill vs. just Google
Use this skill when the deliverable is a list of named individuals with structured fields. Don't use it for:
- Aggregate research ("how big is the X market") — use web search.
- Finding a single specific named person — just web search + verify.
- Company lists without people attached — that's account research.
If in doubt: if the user wants rows in a spreadsheet with names and an outreach angle, this is the skill.
The workflow
Six phases. Each writes to a scratchpad so context survives long runs.
1. Intake → pin down WHO and WHY
2. Source strategy → pick platforms + queries
3. Discovery → iterative BrightData scraping
4. Enrichment → per-person profile + contact pull
5. Personalization → worldbuilder commentary per row
6. Output → multi-sheet xlsx
Skip phases that are already done. If the user hands you a list of profile URLs and just wants enrichment + commentary, jump to Phase 4.
Phase 0: Scratchpad first
Before scraping anything, create a scratchpad so you don't lose the thread mid-run.
mkdir -p /home/claude/sourcing-work/<project-slug>/raw
touch /home/claude/sourcing-work/<project-slug>/brief.md
touch /home/claude/sourcing-work/<project-slug>/candidates.jsonl
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 · 327 lines · 227 tokens per session scan A a7b5ac82a875
people-sourcer is a skill published in the GitHub repository thtskaran/claude-skills (18 stars, last pushed 3mo ago), licensed MIT. It adds 227 tokens to every session and 4,841 once invoked, about $0.0011 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
Excel工具
A guide for using Excel tools to read, write, and recalculate spreadsheet files. It includes a rule for treating the first row as data when a spreadsheet has no column headings.
xlsx
Create, edit, analyze, or convert Excel spreadsheets (.xlsx, .xlsm, .xltx) where the workbook file is the primary deliverable. Use for formulas, formatting, financial models, multi-sheet workbooks, and tabular cleanup exported to Excel. Also applies to .csv/.tsv when the user wants spreadsheet output. Do NOT use for…
google-sheets
Read and write Google Sheets spreadsheets - get content, update cells, append rows, fetch specific ranges, search for spreadsheets, and view metadata. Use when user asks to: read a spreadsheet, update cells, add data to Google Sheets, find a spreadsheet, check sheet contents, export spreadsheet data, or get cell…
ifc-to-excel
Convert IFC files (2x3, 4x1, 4x3) to Excel databases using IfcExporter CLI. Extract BIM data, properties, and geometry without proprietary software.
dgn-to-excel
Convert DGN files (v7-v8) to Excel databases. Extract elements, levels, and properties from infrastructure CAD files.
dwg-to-excel
Convert AutoCAD DWG files (1983-2026) to Excel databases using DwgExporter CLI. Extract layers, blocks, attributes, and geometry data without Autodesk licenses.