nanotracker-api-sdk: Skill for Codex

.agents/skills/api-subscribe-stream/SKILL.md

api-subscribe-stream is a skill for Codex from savannah-i-g/nanotracker-api-sdk. It costs 49 tokens per session (698 once invoked), scanned A, original, MIT.

Instructions for detecting changes in a live nanoTracker editing session from code outside the web page. Because the relay does not send event streams, the instructions use periodic checks of a small project summary.

In plain words
What is it for?
Use them to trigger visualisation updates, synchronize an external sequencer, or log edits when project-level nanoTracker data changes.
Why use it?
They provide a lightweight way to notice edits without sending requests so often that the relay is overloaded.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: installed under .agents/ (shared by several agents).

This is savannah-i-g/nanotracker-api-sdk's own configuration. It tells Codex how to work on nanotracker-api-sdk itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything nanotracker-api-sdk configures →

Reuse

Borrowing it

Nothing to install: this file belongs to savannah-i-g/nanotracker-api-sdk. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/savannah-i-g/nanotracker-api-sdk/main/.agents/skills/api-subscribe-stream/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/savannah-i-g/nanotracker-api-sdk

Made for: Codex.

Wrote 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.

agentmods badge for api-subscribe-stream

README.md
[![agentmods](https://agentmods.dev/badge/skills/savannah-i-g/nanotracker-api-sdk/api-subscribe-stream/github.svg)](https://agentmods.dev/skills/savannah-i-g/nanotracker-api-sdk/api-subscribe-stream)
Your own site
<a href="https://agentmods.dev/skills/savannah-i-g/nanotracker-api-sdk/api-subscribe-stream"><img src="https://agentmods.dev/badge/skills/savannah-i-g/nanotracker-api-sdk/api-subscribe-stream/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.

agentmods 80×15 button for api-subscribe-stream

Your own site · 80×15
<a href="https://agentmods.dev/skills/savannah-i-g/nanotracker-api-sdk/api-subscribe-stream"><img src="https://agentmods.dev/badge/skills/savannah-i-g/nanotracker-api-sdk/api-subscribe-stream.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 49 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 698 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00049 $0.00698
Opus 5.5 $0.00020 $0.00279
Sonnet 5.5 $0.00010 $0.00140
Haiku 4.5 $0.00005 $0.00070

Measured 2mo ago against content hash de7c063b1866, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

api-subscribe-stream 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 2mo 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.

.agents/skills/api-subscribe-stream/SKILL.md · 96 lines

How it starts

The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Subscribe to nanoTracker changes (from outside the page)

When to use

You need to react to changes the user makes in the editor (or that another agent makes via the API) — for example, regenerating a visualisation, syncing to an external sequencer, logging edits.

Why subscribe doesn't cross the relay

window.nanoTracker.subscribe(fn) exists in the page, but it fires local React effects. The relay forwards request/reply pairs, not event streams. So external callers must poll.

The good news: getProjectSummary is dirt cheap. A 1 Hz poll is totally fine. A 10 Hz poll is fine for small projects. Don't go faster — the relay's rate limit is 20 batches/sec across all sources.

Cheap-revision pattern

let lastSig = "";
async function poll() {
  const out = await call("read", { op: "getProjectSummary" });
  const sig = JSON.stringify(out.data);
  if (sig !== lastSig) {
    lastSig = sig;
    onChange(out.data);
  }
  setTimeout(poll, 1000);
}
poll();

getProjectSummary returns scalars — bpm, speed, channels, patternCount, orderListLength, sampleCount, instrumentTableSize. The JSON is short and stable; comparing as a string works.

Detecting cell-level changes

Project summary catches structural changes (pattern added, bpm changed). It doesn't catch a single cell edit. For finer detection, add getPatternList:

const list = await call("read", { op: "getPatternList" });
const fp   = list.data.map(p => `${p.id}:${p.filledCells}`).join(",");

filledCells increments/decrements with every cell edit. Combine with the summary signature to catch most changes cheaply.

Cell-exact diffing

If you really need to know which cell changed, you have to fetch the range and diff client-side. Do that lazily — only when one of the cheaper signatures has changed.

Don't busy-loop on errors

If the page disconnects you'll start seeing errors with code: "internal", message: "no nanoTracker tab connected". Back off:

let backoff = 1000;
async function poll() {
  try {
    /* ... */
    backoff = 1000;
  } catch (e) {
    backoff = Math.min(backoff * 2, 30000);
  }
  setTimeout(poll, backoff);
}

Read the full file on GitHub · 96 lines

Files

What ships with it

1 file 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.

Changes

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.

  1. 2mo ago First seen · 96 lines · 49 tokens per session scan A de7c063b1866

Subscribe to this mod's changes

api-subscribe-stream is a skill published in the GitHub repository savannah-i-g/nanotracker-api-sdk (20 stars, last pushed 6mo ago), licensed MIT. It adds 49 tokens to every session and 698 once invoked, about $0.0002 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 2026-08-30.

Related

Other skills, from other repositories

interactive-login

Log a CLI in with a browser/device-code flow (aws sso, gh, glab, gcloud, …) and save the result to the keychain so later commands can request it through execute.credentials.

yc-software/qm · 46 tokens

pinchtab-mcp

Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.

pinchtab/pinchtab · 52 tokens

azure-messaging-webpubsub-java

Build real-time web applications with Azure Web PubSub SDK for Java. Use when implementing WebSocket-based messaging, live updates, chat applications, or server-to-client push notifications.

microsoft/skills · 43 tokens

cua-driver

Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.

davidondrej/skills · 68 tokens

open-design-browser

Inspect and exercise local HTML design artifacts and library prototype previews with the existing agent-browser CLI, including screenshots, interaction checks, and rendered DOM snapshots. Use when rendered evidence helps author or review a design; excludes browser installation, remote services, and unrelated browser…

compozy/compozy · 56 tokens

browser_cdp

A health check for Python code that produces a score, letter grade, and measures of issues such as complexity, duplication, dead code, dependencies, and architecture.

mateaix/mateclaw · 44 tokens