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 agentmods add agents/greglas75/zuvo/geo-crawl-accessgit 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/geo-crawl-access)<a href="https://agentmods.dev/agents/greglas75/zuvo/geo-crawl-access"><img src="https://agentmods.dev/badge/agents/greglas75/zuvo/geo-crawl-access.svg" alt="Measured on agentmods" 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 | $0.00021 | $0.03714 |
| Opus 5 | $0.00010 | $0.01857 |
| Sonnet 5 | $0.00004 | $0.00743 |
| Haiku 4.5 | $0.00002 | $0.00371 |
Grade A, and why
geo-crawl-access 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 4d 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.
4. **`http-bot-status` (live only):** If `--live-url` provided: curl with retrieval bot User-Agent strings. 200 = PASS. 403/429/503 = FAIL. Skip with `INSUFFICIENT DATA` if no live URL. How it starts
The opening of the file, as written. The whole thing — 321 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent: GEO Crawl & Access (Group A)
Model: Sonnet | Type: Explore (read-only)
Evaluate GEO infrastructure dimensions: G1 (AI Crawler Access), G7 (Canonicalization & URL Hygiene), G8 (Sitemap & Discovery).
Mandatory File Loading
Read before starting:
../../../shared/includes/codesift-setup.md-- CodeSift discovery../../../shared/includes/geo-check-registry.md-- canonical GEO check slugs../../../shared/includes/seo-bot-registry.md-- canonical AI/search bot taxonomy
Read ../../../shared/includes/geo-check-registry.md for canonical check slugs. Use ONLY slugs from this registry in findings[].check_slug.
Read ../../../shared/includes/seo-bot-registry.md for canonical bot keys. Use ONLY bot keys from this registry in bot-matrix evidence.
Print the checklist:
CORE FILES LOADED:
1. codesift-setup.md -- [READ | MISSING -> STOP]
2. geo-check-registry.md -- [READ | MISSING -> STOP]
3. seo-bot-registry.md -- [READ | MISSING -> STOP]
If any file is missing, STOP.
Setup
- Run CodeSift discovery per codesift-setup.md
- Do NOT re-detect stack -- receive detected stack from dispatcher
- Use CodeSift when available, fall back to Grep/Read/Glob
Input (from dispatcher)
| Field | Type | Description |
|---|---|---|
detected_stack |
string | astro | nextjs | hugo | wordpress | react | html |
detected_profile |
string | marketing | docs | ecommerce | app-shell | blog |
cms_detected |
boolean | Whether a headless or traditional CMS was detected |
imported_findings |
object | null | seo-audit JSON output (may be null); contains D5 findings for overlap resolution |
file_paths |
string[] | Config files, robots.txt, head templates, sitemap configs |
codesift_repo |
string | null | Repo identifier if CodeSift available |
selected_dimensions |
string[] | e.g. ["G1", "G7", "G8"] |
Mode-aware filtering: Skip any dimension NOT in selected_dimensions.
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.
- 4d ago First seen · 321 lines · 21 tokens per session scan A 0d76b30cd4c3
geo-crawl-access is an agent published in the GitHub repository greglas75/zuvo (6 stars, last pushed yesterday), licensed MIT. It adds 21 tokens to every session and 3,714 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 agents, from other repositories
staff-reviewer
Internal reviewer: diff-first specification compliance, then code quality. Returns only supported, actionable findings.
triage-labels
Label vocabulary for triaging/grilling issues in this repository. Managed by smallhours setup — edit .smallhours.yml labels: to rename, then re-run setup; do not edit this file by hand.
ui-tester
E2E browser testing specialist - writes persistent test files using Playwright MCP tools.
frontend-verifier
Verifies frontend via browser automation — forms, interactions, visual regressions, responsive layouts. Also fixes issues found. General frontend QA when there's no Figma involved. Only non-Figma design agent. Good for catching functional bugs (broken forms, console errors) alongside visual issues.
implementer
Takes one self-contained story from plan to commit or PR on its own branch, with tests and a self-review. Works only in the directory it was given, respects the hardware ceiling and the manifest of shared zones, and reports with raw command output rather than adjectives.
codex-rescue
Hand an OPEN-ENDED or stuck problem to Codex for independent investigation. Use ONLY when the user says "stuck", "second opinion", "rescue", "dig deeper", "I'm not sure why X", OR hands off a substantial unbounded task with no written plan. Do NOT use when a plan or plan-step file is in context (use codex-execute) or…