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 exa-labs/agent-skills --skill company-researchgit clone --depth 1 https://github.com/exa-labs/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/exa-labs/agent-skills/company-research)<a href="https://agentmods.dev/skills/exa-labs/agent-skills/company-research"><img src="https://agentmods.dev/badge/skills/exa-labs/agent-skills/company-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/exa-labs/agent-skills/company-research"><img src="https://agentmods.dev/badge/skills/exa-labs/agent-skills/company-research.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk warn
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 | $0.00046 | $0.01467 |
| Opus 5.5 | $0.00018 | $0.00587 |
| Sonnet 5.5 | $0.00009 | $0.00293 |
| Haiku 4.5 | $0.00005 | $0.00147 |
Grade A, and why
company-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 18d 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 — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Company Research
Tool Selection (Critical)
Two Exa surfaces, two jobs:
- Exa Agent (
agent_run) — the default for company research. Use it for deep dives, competitor analysis, multi-angle research (product + funding + news + people), and building company lists. One Agent run handles query decomposition, multi-step searching, and synthesis internally — do not orchestrate many manual searches for work an Agent run covers. web_search_advanced_exa— quick, low-latency lookups: a fastcategory: "company"discovery pass, a single news check, or finding a homepage.
Do NOT use other Exa tools.
Deep Dives and Lists: Exa Agent
Agent runs may stream to completion in one call. If a run outlives the MCP call window, continue waiting with its returned run ID.
- Call
agent_runwith a natural-languagequeryand, when you want repeatable structure, anoutputSchema(bound arrays withmaxItems). - If it returns
status: "running"with arunId, callagent_runagain with only thatrunIduntiloutputReadyis true. - Read
output.textoroutput.structured, plusoutput.groundingcitations, from theagent_runresult.
Useful inputs: systemPrompt (source preferences, dedup rules), input.exclusion (companies to avoid), previousRunId (a new follow-up run based on a completed run), effort ("low" default; "auto" or "high" for more depth).
Example: company deep dive
agent_run {
"query": "Research Anthropic: product lines, funding history and valuation, key executives, main competitors, and notable news from the last 6 months.",
"effort": "auto",
"outputSchema": {
"type": "object",
"properties": {
"overview": { "type": "string" },
"funding": { "type": "array", "maxItems": 10, "items": { "type": "object", "properties": { "round": { "type": "string" }, "amount": { "type": "string" }, "date": { "type": "string" } }, "required": ["round"] } },
"competitors": { "type": "array", "maxItems": 10, "items": { "type": "string" } },
"key_people": { "type": "array", "maxItems": 10, "items": { "type": "object", "properties": { "name": { "type": "string" }, "title": { "type": "string" } }, "required": ["name", "title"] } }
},
"required": ["overview", "competitors"]
}
}
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.
- 18d ago Changed 94c935e953e4
- 2mo ago First seen · 149 lines · 46 tokens per session scan A 20f819119fe3
company-research is a skill published in the GitHub repository exa-labs/agent-skills (65 stars, last pushed yesterday), licensed MIT. It adds 46 tokens to every session and 1,467 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 2026-08-30.
company-research compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| company-researchexa-labs/agent-skills | Skill | 65 | yesterday | MIT | A | 46 | Claude Code |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |