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 spiralcrew-ou/profilespider-agent-skills --skill person-researchgit clone --depth 1 https://github.com/spiralcrew-ou/profilespider-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/spiralcrew-ou/profilespider-agent-skills/person-research)<a href="https://agentmods.dev/skills/spiralcrew-ou/profilespider-agent-skills/person-research"><img src="https://agentmods.dev/badge/skills/spiralcrew-ou/profilespider-agent-skills/person-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/spiralcrew-ou/profilespider-agent-skills/person-research"><img src="https://agentmods.dev/badge/skills/spiralcrew-ou/profilespider-agent-skills/person-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 | $0.00042 | $0.00440 |
| Opus 5.5 | $0.00017 | $0.00176 |
| Sonnet 5.5 | $0.00008 | $0.00088 |
| Haiku 4.5 | $0.00004 | $0.00044 |
Grade A, and why
person-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 2mo 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.
What it actually says
Person Research
Purpose
Create structured professional research summaries from public profile information, safely.
When to use this skill
- Preparing for a sales or recruiting conversation
- Summarizing a sourced profile list consistently
- Identifying relevant experience for a role or account
- Flagging what is unknown about a contact
When not to use this skill
- You only have a name with no professional context
- You need personal, private, or sensitive attributes (never infer these)
- You want verified contact details rather than a summary
Required inputs
- Public professional profile information
Optional inputs
- The role or account context
- Specific expertise you care about
Rules
- Use only supplied public, professional information.
- Do not infer health, religion, ethnicity, sexual orientation, political affiliation, or other sensitive personal attributes.
- Do not speculate about personality, intent, or private life.
- Separate stated facts from inferences.
- List unknowns as research gaps.
Process
- Parse the public profile.
- Summarize role, background, and expertise.
- Tie relevant experience to the stated context.
- List affiliations explicitly stated.
- Record research gaps.
Output format
Return one summary per person with the following fields:
- current_role
- professional_background
- areas_of_expertise
- relevant_experience
- affiliations
- research_gaps
Validation
- Confirm no sensitive attributes were inferred.
- Confirm each field cites profile evidence.
- Confirm gaps are listed, not filled.
Limitations
- Profiles may be outdated or incomplete.
- Professional relevance is an interpretation, not a fact.
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.
- 2mo ago First seen · 81 lines · 42 tokens per session scan A af847bf39fc6
person-research is a skill published in the GitHub repository spiralcrew-ou/profilespider-agent-skills (11 stars, last pushed 4mo ago), licensed MIT. It adds 42 tokens to every session and 440 once invoked, about $0.0002 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 2026-08-31.
person-research compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| person-researchspiralcrew-ou/profilespider-agent-skills | Skill | 11 | 4mo ago | MIT | A | 42 | Claude Code, Codex |
| squeeze-page-builderAffitor/affiliate-skills | Skill | 767 | 18d ago | MIT | A | 114 | Claude Code |
| deepline-ads-audiencesgetaero-io/gtm-eng-skills | Skill | 73 | yesterday | MIT | A | 133 | Claude Code, Codex |
| deepline-enginegetaero-io/gtm-eng-skills | Skill | 73 | yesterday | MIT | A | 43 | Claude Code, Codex |
| deepline-plays-reviewgetaero-io/gtm-eng-skills | Skill | 73 | yesterday | MIT | A | 121 | Codex |
| b2b-marketing-playbookGingiris-1031/gingiris-skills | Skill | 89 | 2d ago | MIT | A | 53 | Claude Code, Codex |
| deepline-crm-cleaninggetaero-io/gtm-eng-skills | Skill | 73 | yesterday | MIT | A | 73 | Claude Code, Codex |