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 anysiteio/agent-skills --skill anysite-people-sourcinggit clone --depth 1 https://github.com/anysiteio/agent-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/anysiteio/agent-skills/anysite-people-sourcing)<a href="https://agentmods.dev/skills/anysiteio/agent-skills/anysite-people-sourcing"><img src="https://agentmods.dev/badge/skills/anysiteio/agent-skills/anysite-people-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/anysiteio/agent-skills/anysite-people-sourcing"><img src="https://agentmods.dev/badge/skills/anysiteio/agent-skills/anysite-people-sourcing.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 | $0.00150 | $0.03797 |
| Opus 5 | $0.00075 | $0.01899 |
| Sonnet 5 | $0.00030 | $0.00759 |
| Haiku 4.5 | $0.00015 | $0.00380 |
Grade A, and why
anysite-people-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 — 224 lines — stays where its author put it; the contents beside it link to each section on GitHub.
People Sourcing
linkedin/search/sql/users (endpoint search_sql_users) searches a very large
profile database with filters no live LinkedIn search has: derived seniority and
function, career-shape maths (tenure, promotions, months in role), past-employer
alumni, company domains and deterministic bucketing. It is the bulk people
workhorse; live search_users stays the tool for one-off lookups and namesake
disambiguation.
Verified live: filters compose correctly (seniority_min=head + function=sales +
US + 51–500 headcount + new-in-role returned exactly that, role histories fresh
to the current quarter; alumni via past_company_id returns people whose role at
that company has an end date, never current staff).
Two semantics that change how you work
- An over-
countresult is an unbiased SAMPLE, and repeating the request returns the SAME people (verified: two identical calls → identical 5 aliases; and raisingcountonly appends — the list is prefix-stable, not reshuffled). Calling again is not pagination. - Buckets are disjoint and stable (verified:
bucket_total:2, index 0 vs 1 → zero overlap across 40). Walk them for volume:bucket_total:N, bucket_index:0..N-1, also the built-in territory splitter. Ceiling:bucket_totalmax is 100, so the reachable population is ~100×1000 = 100k; sizebucket_totalso each bucket is < 1000, otherwise a bucket is itself a sample and you silently lose the tail.
What filters but does NOT come back (read before you "validate")
The derived fields you filter on are not in the response: no seniority,
function, profile_score, months_in_role, promotion_count, industry,
employee_count (verified on a live record). Consequences:
- "Validate against intent" = read
experience[]by hand: take roles withend_date == null(the current ones) and check.position/.company.name. You cannot re-sort or re-segment the result by seniority/function viaquery_cache— those columns aren't there. - The only size field carried per role is
experience[].company.employee_range, and that string is unreliable (see Company filters). There is no trustworthy company-size value in a people result to write to a CRM.
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 · 224 lines · 150 tokens per session scan A 7122dc74578e
anysite-people-sourcing is a skill published in the GitHub repository anysiteio/agent-skills (19 stars, last pushed 28d ago), licensed MIT. It adds 150 tokens to every session and 3,797 once invoked, about $0.0007 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…