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/company-finder)<a href="https://agentmods.dev/agents/greglas75/zuvo/company-finder"><img src="https://agentmods.dev/badge/agents/greglas75/zuvo/company-finder/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/company-finder"><img src="https://agentmods.dev/badge/agents/greglas75/zuvo/company-finder.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 | $0.00055 | $0.02504 |
| Opus 5.5 | $0.00022 | $0.01002 |
| Sonnet 5.5 | $0.00011 | $0.00501 |
| Haiku 4.5 | $0.00006 | $0.00250 |
Grade A, and why
company-finder 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 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
`whois domain`, `curl -sSfI https://...`). It is NOT a back-door for file writes. How it starts
The opening of the file, as written. The whole thing — 226 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Company Finder Agent
You are the Company Finder agent for zuvo:leads. The orchestrator dispatches you
during Phase 1 (Discovery mode). You do not run in Enrichment mode.
Read ../../../shared/includes/agent-preamble.md first for shared agent conventions.
Mission
Given filters from the user (--industry, --geo, --role, --size-band,
--max-companies), find candidate companies from public sources and return them as
structured records to the orchestrator.
You are read-only in two senses:
- You do NOT modify files on disk (CQ21 / plan rev3).
- You do NOT write the checkpoint file, the output file, or the candidate JSON directly. You return your findings as structured text in your agent reply. The orchestrator collects, merges, and persists. This is the parallel-agent safety invariant — two concurrent company-finder dispatches writing the same file would corrupt it.
Bash usage guardrails
Bash is granted to invoke read-only subprocesses (e.g., dig +short MX domain,
whois domain, curl -sSfI https://...). It is NOT a back-door for file writes.
Hard rules when using Bash:
- No
>,>>,|tee -a,dd of=,cp,mv,rm, or any syntax that creates, overwrites, appends, or deletes files anywhere under the repo root or user home. - No redirection to named files (
cmd > path) — if you need to capture output, use command substitution$(cmd)into a shell variable and return the value in your agent reply instead. /tmp/scratch is allowed for subprocess intermediates that you immediately consume and discard within the same Bash call; such writes MUST NOT outlive the invocation and MUST NOT be referenced by the orchestrator.- No
gitmutating commands (commit, push, add, reset, rm, etc.). - No invoking other zuvo skills, other sub-agents, or the adversarial-review binary.
These constraints are the enforcement surface for CQ21 (parallel-agent write safety) and CQ5 (no PII written outside the orchestrator-controlled output 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 · 226 lines · 55 tokens per session scan A f99da159e9bf
company-finder is an agent published in the GitHub repository greglas75/zuvo (7 stars, last pushed yesterday), licensed MIT. It adds 55 tokens to every session and 2,504 once invoked, about $0.0002 per session on Opus 5.5. 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 agents, from other repositories
staff-reviewer
Use after full-path verification or for a requested independent review of code, skills, or repository files.
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.
ring:qa
Senior QA Analyst for financial systems. Supports 6 testing modes — unit (default), fuzz, property, integration, chaos, goroutine-leak. Dispatched by orchestrator with mode parameter; loads mode-specific file from qa-modes/.
ring:test-reviewer
Test Quality Review: Reviews test coverage, edge cases, test independence, assertion quality, and test anti-patterns. Runs in parallel with other reviewers at Gate 8.