Borrowing it
Nothing to install: this file belongs to the-sid-dani/second-brain-os. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/the-sid-dani/second-brain-os/main/.agents/skills/entity-research/SKILL.mdgit clone --depth 1 https://github.com/the-sid-dani/second-brain-osWrote 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/the-sid-dani/second-brain-os/entity-research)<a href="https://agentmods.dev/skills/the-sid-dani/second-brain-os/entity-research"><img src="https://agentmods.dev/badge/skills/the-sid-dani/second-brain-os/entity-research/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/the-sid-dani/second-brain-os/entity-research"><img src="https://agentmods.dev/badge/skills/the-sid-dani/second-brain-os/entity-research.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 | $0.00100 | $0.00740 |
| Opus 5.5 | $0.00040 | $0.00296 |
| Sonnet 5.5 | $0.00020 | $0.00148 |
| Haiku 4.5 | $0.00010 | $0.00074 |
Grade A, and why
entity-research 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 7d 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
entity-research
Research one of two entity types—company or person—using public information. Return distilled findings with source URLs and explicit uncertainty.
Route first
- Known internal person or existing relationship context →
/contactfirst. Use this skill only for fresh public enrichment when requested. - Company → company branch below.
- Person → person branch below.
- Topic, market thesis, or content idea rather than a named entity →
/research.
If the entity type is ambiguous, infer it from the name and prompt; ask only when the research method or output would materially differ.
Shared search discipline
- Use only
web_search_advanced_exa; do not silently substitute another Exa endpoint. - Run broad searches in isolated Task agents and return compact findings to the main context. Generate two or three query variants when coverage matters, then merge and deduplicate.
- Match result volume to the request: honor an explicit number; otherwise use a small focused set for a profile and a broader set for discovery. Ask about volume only when it materially changes cost or scope.
- Treat public LinkedIn results as leads, not proof. Verify important claims against a company site, filing, personal site, conference bio, or reputable news source where possible.
- Never infer private contact details, protected attributes, or identity matches from weak signals. State ambiguity.
Company branch
Start with category: "company" for discovery and basic metadata. Use category: "news" for announcements and an unclassified/deep query for filings, product detail, or broader context.
Important filter limits:
- With
category: "company", omit domain and published/crawl date filters. includeTextandexcludeTextaccept at most one array item.
Return:
- Company snapshot: what it does, location, scale/funding/revenue only when sourced.
- Competitors or comparable companies, with the comparison basis.
- Material recent developments when requested, including publication dates.
- Sources with one-line relevance notes.
- Conflicts, gaps, and confidence.
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.
- 7d ago First seen · 66 lines · 100 tokens per session scan A b32f2a7bb323
entity-research is a skill published in the GitHub repository the-sid-dani/second-brain-os (3 stars, last pushed 7d ago), licensed MIT. It adds 100 tokens to every session and 740 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-10-17.
Other skills, from other repositories
apply
A browser-based job application workflow for submitting applications through services such as Ashby, Greenhouse, Lever, and Hacker News. It uses prepared candidate information, answers, job links, and cover letters.
rep-reply
Find live third-party GitHub issues and discussions on topics where you have real hands-on experience and artifacts, then reply with that experience to build reputation. Use when asked to answer people about your work, find threads matching your expertise, or reply with evidence from your own setup.
dr-fanout
Fan one deep-research prompt out to several external LLMs at once through a logged-in browser, then collect the reports, archive the originals and synthesize a consensus. Use at the final stage of a research protocol, instead of hand-pasting one prompt into N sites. Triggers: "/dr-fanout", "fan out the DR"…
cv-outreach
A daily workflow for carrying out scheduled outward-facing tasks, such as event registrations, messages to organisers, and public posts. It uses a browser identity carefully so actions are made from the intended account.
devrel-wave
A planned outreach process for contacting developer-relations and research staff at major AI laboratories through several available channels. Developer relations, often called DevRel, is the team that works with developers and outside communities.
peer-onboard
A procedure for bringing an outside lead or peer into a shared working setup, including their contact space, records, previous conversations, and ongoing session.