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 bytefer/geo-seo-codex --skill geo-prospectgit clone --depth 1 https://github.com/bytefer/geo-seo-codexWrote 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/bytefer/geo-seo-codex/geo-prospect)<a href="https://agentmods.dev/skills/bytefer/geo-seo-codex/geo-prospect"><img src="https://agentmods.dev/badge/skills/bytefer/geo-seo-codex/geo-prospect.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 5.1 | $0.00087 | $0.01709 |
| Opus 5 | $0.00044 | $0.00855 |
| Sonnet 5 | $0.00017 | $0.00342 |
| Haiku 4.5 | $0.00009 | $0.00171 |
Grade A, and why
geo-prospect 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 8d 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.
This is a copy
97% identical to geo-prospect — 54 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 186 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GEO Prospect Manager
Purpose
Manage GEO agency prospects and clients through the full sales lifecycle.
All data is stored in ~/.geo-prospects/prospects.json (persistent across sessions).
Invocations
| Invocation | What It Does |
|---|---|
$geo-prospect new <domain> |
Create new prospect (interactive prompts) |
$geo-prospect list |
Show all prospects with pipeline status |
$geo-prospect list <status> |
Filter: lead, qualified, proposal, won, lost |
$geo-prospect show <id-or-domain> |
Full prospect detail with history |
$geo-prospect audit <id-or-domain> |
Run quick GEO audit and save to prospect record |
$geo-prospect note <id-or-domain> "<text>" |
Add interaction note with timestamp |
$geo-prospect status <id-or-domain> <new-status> |
Move through pipeline |
$geo-prospect won <id-or-domain> <monthly-value> |
Mark as won, set contract value |
$geo-prospect lost <id-or-domain> "<reason>" |
Mark as lost with reason |
$geo-prospect pipeline |
Visual pipeline summary with revenue forecast |
Data Structure
Each prospect is stored as a JSON record:
{
"id": "PRO-001",
"company": "Electron Srl",
"domain": "electron-srl.com",
"contact_email": "[email protected]",
"contact_name": "",
"industry": "Educational Equipment Manufacturing",
"country": "Italy",
"status": "qualified",
"geo_score": 32,
"audit_date": "2026-03-12",
"audit_file": "~/.geo-prospects/audits/electron-srl.com-2026-03-12.md",
"proposal_file": "~/.geo-prospects/proposals/electron-srl.com-proposal.md",
"monthly_value": 0,
"contract_start": null,
"contract_months": 0,
"notes": [
{
"date": "2026-03-12",
"text": "Initial GEO quick scan. Score 32/100 - Critical tier. Strong candidate for GEO services."
}
],
"created_at": "2026-03-12",
"updated_at": "2026-03-12"
}
Orchestration Instructions
$geo-prospect new <domain>
- Check if
~/.geo-prospects/prospects.jsonexists, create if not (empty array) - Auto-detect company name from domain (e.g.,
electron-srl.com→Electron Srl) - Assign next sequential ID:
PRO-001,PRO-002, etc. - Ask user for:
- Contact name (optional)
- Contact email
- Monthly contract value estimate (optional)
- Set status to
lead - Save to JSON file
- Suggest next step: "Run
$geo-prospect audit electron-srl.comto score this prospect"
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.
- 8d ago First seen · 186 lines · 87 tokens per session scan A c8e48f8d4e9a
geo-prospect is a skill published in the GitHub repository bytefer/geo-seo-codex (11 stars, last pushed 2mo ago), licensed MIT. It adds 87 tokens to every session and 1,709 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. It is 97% identical to geo-prospect, differing in 54 lines, and is treated as a copy.
Other skills, from other repositories
triage
Apply a formal state machine to issues — assign category (bug/enhancement/question/spike) and state (needs-triage → needs-info → ready-for-agent → ready-for-human → wontfix). Issues marked ready-for-agent become inputs to supergraph:plan. Use when processing a backlog, reviewing new issues, or preparing work for…
frappe-gameplan
Frappe Gameplan guidance for team discussions, projects, tasks, notes, decisions, async collaboration, permissions, and workspace workflows. Use when work touches Gameplan or planning/collaboration features in the Frappe ecosystem.
issue-readiness-review
Review tracker issue readiness before implementation and draft the appropriate no-mutation tracker update.
linear-issue-closeout
Close a Linear issue only after independent evidence review; move it to the team's completed state and leave one closeout comment with retry-safe reuse. Stop without mutation on incomplete work, reviewer veto, uncertainty, stale evidence, unsafe overwrites, or unavailable subagents.
issue-preflight
Preflight a tracker issue, linked change, or branch-scoped work reference before implementation; stop with a tracker draft and do not implement or mutate trackers.
studio-goal-progress
Use when a KIT-managed Codex or Hermes Goal needs evidence-backed percentage, ETA range, live read-only progress views, or portable append-only progress recovery.