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.
git clone --depth 1 https://github.com/thangnguyenworkspace/company-research-pipelineWrote 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/commands/thangnguyenworkspace/company-research-pipeline/exa-crawl)<a href="https://agentmods.dev/commands/thangnguyenworkspace/company-research-pipeline/exa-crawl"><img src="https://agentmods.dev/badge/commands/thangnguyenworkspace/company-research-pipeline/exa-crawl/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/commands/thangnguyenworkspace/company-research-pipeline/exa-crawl"><img src="https://agentmods.dev/badge/commands/thangnguyenworkspace/company-research-pipeline/exa-crawl.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 | $0.00023 | $0.00497 |
| Opus 5 | $0.00012 | $0.00249 |
| Sonnet 5 | $0.00005 | $0.00099 |
| Haiku 4.5 | $0.00002 | $0.00050 |
Grade A, and why
exa-crawl scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
5. **Time-sensitive content warning**: if the page carries versions, prices, or live statuses, note in the file header that a cached or crawled copy may lag the system of record, and suggest a direct `curl` of the underl What it actually says
Exa Crawl
Crawl the URL(s) in $ARGUMENTS and save the raw content to disk. If no URL was given, ask for one. Default output directory: the current company's topic gather folder if one is active, otherwise ask.
Procedure
- Batch: put every requested URL into a single
crawling_exacall (urlsarray). SetmaxCharactersto a large value (e.g. 1000000); omitting it silently truncates pages at ~3,000 characters. PDFs crawl the same way as pages. - Save raw: write each result to its own file in the output directory, named from the URL host and path, with a small header recording the URL, fetch date, and tool used. Never paraphrase into the raw file; it is evidence, not summary.
- Classify honestly, per URL:
clean: substantive full content.partial: content present but visibly incomplete (truncated tables, missing body sections).paywalled: body under ~500 characters plus a subscribe/sign-in prompt. No fallback exists; report it and suggest finding the content elsewhere.failed: empty or error.
- Fallback (for
failedand empty results, one retry only):web_search_advanced_exawith the query set to the URL's host + path,numResults: 3. This hits Exa's cached index and often recovers JavaScript-heavy pages. If the cache hit succeeds, save it and mark the fileclean (via cached index; check in-body dates for staleness). - Time-sensitive content warning: if the page carries versions, prices, or live statuses, note in the file header that a cached or crawled copy may lag the system of record, and suggest a direct
curlof the underlying API when one exists (method/04-tools.mdsection 3).
Return
A per-URL table: URL, status, output file path, one-line content summary. The file on disk is authoritative; never report a save that did not happen.
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 · 25 lines · 23 tokens per session scan A 23655fe8ab28
exa-crawl is a command published in the GitHub repository thangnguyenworkspace/company-research-pipeline (2 stars, last pushed 1mo ago), licensed MIT. It adds 23 tokens to every session and 497 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
create-actor
Guided Apify Actor development with best practices and systematic workflow.
status
Show current research session state and progress.
resume
Resume a previous research session from progress file.
init
Manually initialize or reload research context for sigint.
augment
Deep-dive into a specific area of current research.
issues
Create GitHub issues from research findings as atomic deliverables.