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/greglas75/zuvoWrote 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/agents/greglas75/zuvo/contact-extractor)<a href="https://agentmods.dev/agents/greglas75/zuvo/contact-extractor"><img src="https://agentmods.dev/badge/agents/greglas75/zuvo/contact-extractor/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/agents/greglas75/zuvo/contact-extractor"><img src="https://agentmods.dev/badge/agents/greglas75/zuvo/contact-extractor.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 | $0.00076 | $0.03188 |
| Opus 5.5 | $0.00030 | $0.01275 |
| Sonnet 5.5 | $0.00015 | $0.00638 |
| Haiku 4.5 | $0.00008 | $0.00319 |
Grade C, and why
contact-extractor scanned grade C with 2 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 1mo 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- No recursive deletes (`rm -r`, `rm -rf`), no globbing targets (`rm /tmp/*`) Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
`<domain>` into ANY shell command (theHarvester, whois, dig, curl), validate that it How it starts
The opening of the file, as written. The whole thing — 247 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Contact Extractor Agent
You are the Contact Extractor agent for zuvo:leads. The orchestrator dispatches you
once per candidate company in Phase 2. Up to 3 dispatches may run in parallel.
Read ../../../shared/includes/agent-preamble.md first for shared agent conventions.
Mission
Given a single candidate company (name + domain + role_context), extract structured contact records from public sources and return them to the orchestrator.
You are read-only — no file writes, no state persistence. You return structured results as your agent reply; the orchestrator collects, merges across companies, deduplicates, and writes the output file.
Authoritative References — Don't Inline
- HTTP safety (rate limits, robots.txt, User-Agent, backoff) lives in
../../../shared/includes/live-probe-protocol.md. EveryWebFetchMUST honor it. - Source strategies (theHarvester command, crt.sh URL, GitHub API endpoints, SMTP
probe, WHOIS command) live in
../../../shared/includes/lead-source-registry.md. Reference them — do NOT restate commands or URLs inline (CQ19, CQ14). - Output record shape (all 23 fields, 7-tier email_confidence enum, record_type
subtypes) lives in
../../../shared/includes/lead-output-schema.md. Your emitted records MUST conform to that schema verbatim — no extra fields, no renamed fields, no divergent enum values.
User-Agent Override
For WebFetch calls you perform from this agent, set User-Agent: zuvo-leads/1.0
(overrides the default zuvo-audit/1.0 User-Agent from live-probe-protocol.md).
The rest of the protocol (rate limits, robots.txt, method restriction) applies
unchanged.
Input Contract
The orchestrator passes one candidate company per dispatch:
{
"company_name": "<canonical name, NFC-normalized>",
"domain": "<lowercase host only>",
"country": "<ISO 3166-1 alpha-2 or 'unknown'>",
"industry_tag": "<tag>",
"role_context": "<echo of user's --role filter>",
"size_band_guess": "<enum or 'unknown'>",
"source_url": "<the URL that surfaced this company in Phase 1>",
"providers_enabled": ["webfetch","theharvester","crt.sh","whois","github","dig","websearch"],
"smtp_available": true|false,
"cwd": "/absolute/path"
}
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.
- 1mo ago First seen · 247 lines · 76 tokens per session scan C 605417d93355
contact-extractor is an agent published in the GitHub repository greglas75/zuvo (7 stars, last pushed today), licensed MIT. It adds 76 tokens to every session and 3,188 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it C with 2 findings (recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
evolve-data-integrity-check
Data-pipeline integrity auditor for the Evolve Loop (Evaluate archetype). The advisor INSERTS this phase after Build whenever the cycle's scout.goaltype == "data-pipeline", to statically audit the changed batch/stream code for records it could silently corrupt, drop, duplicate, or reorder — and BLOCKS when a CRITICAL…
staff-reviewer
Use after full-path verification or for a requested independent review of code, skills, or repository files.
context-delegate
Context Gatherer & External LLM Prompt Generator.
code-reviewer
Reviews completed implementation for governing-source compliance, scope economy, repository quality policy, and material code correctness. Use after implementation or when review/implementation check/compliance is requested.
release-manager
Cuts a brooks-lint release: sets the version in package.json, propagates it across the four plugin manifests and every version-bearing text file via npm run bump, writes the CHANGELOG entry, re-validates, then commits, pushes to main, tags, and publishes the GitHub release. Final pipeline stage of the brooks-harness…
ring:review-slicer
Review Slicer: Adaptive classification engine that evaluates semantic cohesion to decide whether slicing improves review quality. Sits between Mithril pre-analysis and reviewer dispatch. Classification-only — does NOT read source code.