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 skills/obto-inc/platform/obto-deploynpx skills add obto-inc/platform --skill obto-deploygit clone --depth 1 https://github.com/obto-inc/platformWrote 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/obto-inc/platform/obto-deploy)<a href="https://agentmods.dev/skills/obto-inc/platform/obto-deploy"><img src="https://agentmods.dev/badge/skills/obto-inc/platform/obto-deploy.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 | $0.00101 | $0.02527 |
| Opus 5 | $0.00051 | $0.01264 |
| Sonnet 5 | $0.00020 | $0.00505 |
| Haiku 4.5 | $0.00010 | $0.00253 |
Grade A, and why
obto-deploy 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 6d 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.
1. **Editing or deleting part of an existing artifact → `obto_patch_artifact`.** Line-addressed, surgical, and it NEVER reproduces the whole file. This sidesteps byte-exactness entirely, so it is the right tool for almos How it starts
The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OBTO Deploys and Large Files
Choose the write path FIRST
Before deploying, decide which path fits — picking wrong is the most common deploy failure. The deciding question is whether the bytes already live in OBTO (an edit) or are entering fresh (a new artifact):
- Editing or deleting part of an existing artifact →
obto_patch_artifact. Line-addressed, surgical, and it NEVER reproduces the whole file. This sidesteps byte-exactness entirely, so it is the right tool for almost all changes to existing code — including large files (a 305KB platform module change is still just a few changed lines). On a large file, useobto_grep_artifactto find the exact lines without pulling the whole file (it returnsN| textblocks); for a small filefetch(id)is fine. Then patch with ananchorTextguard. A deletion is justnewContent: "". The chunked / base64 / from_url paths below are ONLY for bytes entering the platform fresh — never reach for them to make an edit. - A new artifact small enough for one call →
obto_upsert_record({script})directly. - A new artifact too large for one call, that you can reproduce as text → the chunked path (below). Reliable up to ~9KB per emitted chunk — see the emission ceiling.
- A new artifact too large to reproduce as chunks at all (≈300KB+), or already reachable at an https URL →
obto_stage_chunk({action:'from_url'})(deploy-by-reference, below). The server fetches the bytes; the agent never emits them.
Reproducing a whole large file just to change a few lines is the trap. If the change is an edit, patch it.
pltf_script_server is transpiled — patch the right layer. Server scripts are authored as ESM/TypeScript and the engine compiles on save: the record's script holds the COMPILED output, ts_source holds the original source (standard platform design — see the build-loop skill's artifact rules). grep/patch address script, which is workable for small tweaks, but: (1) every save recompiles and renumbers the whole file — re-grep before the next patch and never reuse pre-save line numbers (insert mode has no anchor check and lands blind); (2) a line patch lands in the compiled text, so the change is invisible to anyone working from the source. For module-scale changes, edit the SOURCE (local mirror, or read ts_source via obto_db_query) and re-deploy the full file via from_url + expectedSha256 — the save recompiles and re-syncs both fields. (Some records/stores still hold plain source in script — there, line patches ARE source edits; check what you fetched before assuming.) Note the full-file path runs the export-shape gate: before server 3.5.26 the bare-export scan false-fires if the source merely mentions module.exports = X inside a string (3.5.26 line-anchors it).
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.
- 6d ago First seen · 82 lines · 101 tokens per session scan A c5553e343311
obto-deploy is a skill published in the GitHub repository obto-inc/platform (1 stars, last pushed 3d ago), licensed Apache-2.0. It adds 101 tokens to every session and 2,527 once invoked, about $0.0005 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 skills, from other repositories
canvas-design
Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
specflow-use
To connect Rosetta with Grid Dynamics SpecFlow MCP; only when SpecFlow is mentioned and the MCP is installed.
ue-mcp-epic-routing
Use when deciding between ue-mcp's native category actions and Epic's wrapped ToolsetRegistry tools (the epic actions, incl. the Blueprint graph DSL) for a task in Unreal. Pulls in when authoring Blueprint graph bodies, or any time both a native action and an epic action could do the job and you need to pick.
mcp-google-map-project
Project knowledge for developing and maintaining @cablate/mcp-google-map. Architecture, Google Maps API guide, GIS domain knowledge, and design decisions. Read this skill to onboard onto the project or make informed development decisions.
frontmcp-setup
Use when starting, scaffolding, or organizing a FrontMCP project. Covers creating a new project (CLI scaffold or manual) for Node, Vercel, and other targets; standalone versus Nx-monorepo layout, naming conventions, generators, and dependency rules; composing multiple @App classes, ESM packages, and remote MCP servers…