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 TheSmokeDev/geo-skills --skill tokenmax-fleet-orchestratorgit clone --depth 1 https://github.com/TheSmokeDev/geo-skillsWrote 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/thesmokedev/geo-skills/tokenmax-fleet-orchestrator)<a href="https://agentmods.dev/skills/thesmokedev/geo-skills/tokenmax-fleet-orchestrator"><img src="https://agentmods.dev/badge/skills/thesmokedev/geo-skills/tokenmax-fleet-orchestrator/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/skills/thesmokedev/geo-skills/tokenmax-fleet-orchestrator"><img src="https://agentmods.dev/badge/skills/thesmokedev/geo-skills/tokenmax-fleet-orchestrator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00079 | $0.00843 |
| Opus 5 | $0.00039 | $0.00421 |
| Sonnet 5 | $0.00016 | $0.00169 |
| Haiku 4.5 | $0.00008 | $0.00084 |
Grade A, and why
tokenmax-fleet-orchestrator 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 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.
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.
How it starts
The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TokenMax Fleet Orchestrator
Use this skill above tokenmax-site-factory. The site factory discovers and
generates one site; this skill sequences many sites and records what actually
passed, shipped, and reached production.
Start
- Read the target repo's deploy manual and its existing TokenMax/fleet files.
- Inspect active processes, worktrees, schedules, disk, and available memory.
- Read
references/stage-contract.mdand validate the fleet YAML againstreferences/fleet-config.schema.json. - Run a dry plan before any mutation:
python scripts/fleet_controller.py --config /path/to/fleet.yaml validate-config
python scripts/fleet_controller.py --config /path/to/fleet.yaml init
python scripts/fleet_controller.py --config /path/to/fleet.yaml run-next --dry-run
- Forward-test one unproven site through production before installing a recurring timer.
Controller
The controller is generic. Fleet-specific behavior belongs in YAML stage commands and a versioned repo driver. Commands receive site/stage context via environment variables and write an optional JSON stage result.
python scripts/fleet_controller.py --config /path/to/fleet.yaml status
python scripts/fleet_controller.py --config /path/to/fleet.yaml run-next --max-sites 1
python scripts/fleet_controller.py --config /path/to/fleet.yaml resume --site <id>
python scripts/fleet_controller.py --config /path/to/fleet.yaml retry --site <id>
python scripts/fleet_controller.py --config /path/to/fleet.yaml pause
python scripts/fleet_controller.py --config /path/to/fleet.yaml index-queue
Required Gates
- One clean, isolated worktree per site.
- Scan/profile confidence before content writes.
- A small rendered pilot before the full batch.
- Per-page and full-batch word, uniqueness, fact, structure, and prohibited claim validation.
- Exact app build before any commit or deploy.
- Rendered HTTP, canonical, JSON-LD, internal-link, text/HTML, robots, and sitemap validation.
- Scoped staging and the target platform's required commit identity.
- Merge current remote base and rerun affected gates before pushing.
- Production content and sitemap proof after deploy.
What ships with it
8 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- agents/openai.yaml 280 B
- assets/fleet.example.yaml 771 B
- assets/systemd/tokenmax-fleet.service 505 B
- assets/systemd/tokenmax-fleet.timer 211 B
- references/fleet-config.schema.json 2.4 KB
- references/stage-contract.md 2.1 KB
- scripts/fleet_controller.py 32 KB runs code
- scripts/test_fleet_controller.py 7.4 KB runs code
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 · 88 lines · 79 tokens per session scan A 7b79ce40a713
tokenmax-fleet-orchestrator is a skill published in the GitHub repository TheSmokeDev/geo-skills (22 stars, last pushed 8d ago), licensed MIT. It adds 79 tokens to every session and 843 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
orangeo-ai-visibility-skill
Audit brand AI visibility readiness and prepare OranGEO-style GEO, AEO, LLM SEO, and AI search optimization action plans. Use when asked for a Claude Code skill, Codex skill, GEO skill, generative engine optimization skill, answer engine optimization skill, AI visibility audit, AI search visibility checker, llms.txt…
ganhuo-geo-engineer
Use this Skill when the user provides an existing article, product page, tutorial, FAQ, or knowledge note and wants to rebuild it into a GEO or AI-search-friendly content asset. Use it for old-content refresh, citation-readiness improvement, answer-first restructuring, GEO upgrades, and Ganhuo AI content workflows. Do…
ai-answer-trace
Ask Claude, ChatGPT, and Gemini a question and capture the full evidence trail behind each answer: the search queries each engine ran, the pages it retrieved, and the sources it cited. The raw material of GEO measurement. Needs AI engine API keys, not an Xpoz account.
geo-visibility-check
One-shot GEO audit: does your brand appear in Claude, ChatGPT, and Gemini answers for the buyer questions that matter? Runs a prompt panel through the engines with citation tracing and reports per-prompt verdicts, who wins instead, and which sources the answers come from.
crazyseo
Measure and fix whether AI assistants (ChatGPT, Gemini, Perplexity) recommend a website. Use when someone asks "am I visible in AI search", "does ChatGPT recommend us", "why doesn't AI mention my brand", "GEO/AEO audit", "AI SEO", "llms.txt", "is my site readable by AI crawlers", or wants to know which sources AI…
xerj-code
Reference-coding with XERJ. Clone the libraries that already solved your problem, index them locally, and retrieve the exact implementation before writing code — so the agent reads passages instead of re-deriving algorithms across retry loops. Use when starting a task in an unfamiliar API, porting an algorithm, or…