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/StructureIntelligence/SemeshWrote 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/commands/structureintelligence/semesh/deploy)<a href="https://agentmods.dev/commands/structureintelligence/semesh/deploy"><img src="https://agentmods.dev/badge/commands/structureintelligence/semesh/deploy/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/commands/structureintelligence/semesh/deploy"><img src="https://agentmods.dev/badge/commands/structureintelligence/semesh/deploy.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 | $0.00016 | $0.00559 |
| Opus 5.5 | $0.00006 | $0.00224 |
| Sonnet 5.5 | $0.00003 | $0.00112 |
| Haiku 4.5 | $0.00002 | $0.00056 |
Grade A, and why
deploy 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 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.
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.
What it actually says
Prepare the app in the current directory, report the current deployment availability truth, and observe existing deployment records when ids are provided.
Steps:
- Confirm auth: run
semesh whoami --json. If it returns 401, tell the user to runsemesh login(or setSEMESH_API_KEY) and stop — never proceed past a 401. - Treat deployment as a Platform Action, not a Service Unit. Read the current agent guide or
semesh deploy --helpfor its contract; do not search the Service Unit catalog for a deployment target. - Inspect the project shape and run the authenticated, read-only preflight:
Read preflightsemesh deploy preflight . --full-stack --jsonadmission.can_start_now,code,message, andfix. Production deployment authorization is currently unavailable:app_deployments.createis disabled and deploy fails closed withdeployment_authorization_unavailablebefore upload, build, payment, publication, or a live URL. Report that result and stop without a mutation. - For ids that already exist, use
semesh deploy status <app-id> --json,semesh deploy logs <build-id> --json, andsemesh deploy url <app-id> --json. Existing observation does not authorize a new release, and queued/candidate/preview state is not serving proof. - When deployment authorization becomes available and preflight allows the operation, the intended full-stack command is
semesh deploy . --name "$(basename "$PWD")" --full-stack --wait --json(drop--full-stackfor a plain static site). Report a live URL only from a successful serving response or URL readback; never construct one. - If the user wants an already serving app to charge end users, explain end-user-pays: the app attaches
X-Semesh-Payerso each call is billed to the signed-in user's Aev balance, with a quote before spend and terminal capture evidence afterward.
A direct user request authorizes ordinary paid invocation, deploy, and mechanical publish without a duplicate confirmation. Quote/preflight informs cost and availability; it is not a second confirmation. Ask for a separate confirmation only for destructive, high-impact, authorization-expanding, truly irreversible, or explicitly requires_confirmation actions. Mechanical protocol checks are intended to publish automatically after authorization is available; there is no default human approval queue. If an already-started deployment's --wait times out, poll semesh deploy status <app-id> --json rather than concluding failure.
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 Changed · -3 lines 2b195bbf3e8c
- 1mo ago First seen · 24 lines · 16 tokens per session scan A 04d7671c3531
deploy is a command published in the GitHub repository StructureIntelligence/Semesh (0 stars, last pushed 22d ago), licensed Apache-2.0. It adds 16 tokens to every session and 559 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-08-31.
Other commands, from other repositories
start-13-5
A guided lesson on deploying a project to Vercel, a service that hosts web applications.
start-13-5.en
Command "start-13-5.en" from minicoohei/ai-agent-camp, covering 🎓 lesson 13-5: vercel deploy, 📍 what you'll do, 🎯 readiness check, 🔍 step 0: check project existence and check if output/lp-project directory exists.
start-13-5.es
Bienvenido a Lección 13-5: Despliegue en Vercel.
setup-vercel
A guided setup command for the Vercel command-line tool, which is used to manage deployments on Vercel.
setup-vercel.en
Command "setup-vercel.en" from minicoohei/ai-agent-camp, covering vercel cli setup, step 0: check setup progress, what you'll do in this session, readiness check and step 1: create vercel account.
setup-vercel.es
Command "setup-vercel.es" from minicoohei/ai-agent-camp, covering configuración de vercel cli, step 0: verificar progreso de configuración, lo que hará en esta sesión, verificación de preparación and step 1: crear cuenta de vercel.