brilliant_sdk: Skill for Claude Code

.claude/skills/release/SKILL.md

release is a skill for Claude Code from brilliantlabsAR/brilliant_sdk. It costs 52 tokens per session (2,327 once invoked), scanned C, original, BSD-3-Clause.

A release guide for publishing related Python, JavaScript, and Flutter packages to PyPI, npm, and pub.dev. These are package registries where developers download libraries, and the packages share a single code repository, called a monorepo.

In plain words
What is it for?
Use it to compare local package versions with registry versions, decide which packages to publish, and prepare releases across the three package ecosystems.
Why use it?
Local tests can pass because the repository links packages directly to each other, even when those links will not exist for users installing published versions. The guide helps check what is actually ready to release.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is brilliantlabsAR/brilliant_sdk's own configuration. It tells Claude Code how to work on brilliant_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 brilliant_sdk configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is ./.venv/bin/python -c "import <module>; ..." # exercise connect()/the new API.

Reuse

Borrowing it

Nothing to install: this file belongs to brilliantlabsAR/brilliant_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/brilliantlabsAR/brilliant_sdk/main/.claude/skills/release/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/brilliantlabsAR/brilliant_sdk

Made for: Claude Code.

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 release

README.md
[![agentmods](https://agentmods.dev/badge/skills/brilliantlabsar/brilliant_sdk/release/github.svg)](https://agentmods.dev/skills/brilliantlabsar/brilliant_sdk/release)
Your own site
<a href="https://agentmods.dev/skills/brilliantlabsar/brilliant_sdk/release"><img src="https://agentmods.dev/badge/skills/brilliantlabsar/brilliant_sdk/release/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 release

Your own site · 80×15
<a href="https://agentmods.dev/skills/brilliantlabsar/brilliant_sdk/release"><img src="https://agentmods.dev/badge/skills/brilliantlabsar/brilliant_sdk/release.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 52 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,327 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 2 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 $0.00052 $0.02327
Opus 5 $0.00026 $0.01163
Sonnet 5 $0.00010 $0.00465
Haiku 4.5 $0.00005 $0.00233

Measured 10d ago against content hash 76b05b795e5d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade C, and why

release scanned grade C with 2 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 10d 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.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

curl -s https://pypi.org/pypi/<name>/json | python3 -c "import json,sys;print(json.load(sys.stdin)['info']['version'])"

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -s https://pypi.org/pypi/<name>/json | python3 -c "import json,sys;print(json.load(sys.stdin)['info']['version'])"
.claude/skills/release/SKILL.md · 195 lines

How it starts

The opening of the file, as written. The whole thing — 195 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Releasing brilliant_sdk packages

Three independent ecosystems live in this monorepo: python/ (PyPI), webbluetooth/ (npm) and flutter/ (pub.dev). Each has its own versions and its own publish mechanics. A release round usually touches only a subset.

The rule that matters most

Local checkouts do not resolve dependencies the way users do. The uv workspace, the npm node_modules symlinks, and the Flutter pubspec_overrides.yaml files all point sibling packages at local source. So a package can call an API that exists only in its unreleased sibling, pass every local test, and still fail instantly for anyone installing from a registry.

This has already shipped broken releases. Treat "tests pass locally" as no evidence at all about whether a release will install and run.

1. Work out what actually needs publishing

Compare each package's manifest version against its registry:

# PyPI — the JSON API lags after a publish; prefer a real resolve to confirm
curl -s https://pypi.org/pypi/<name>/json | python3 -c "import json,sys;print(json.load(sys.stdin)['info']['version'])"
npm view <name> version
curl -s https://pub.dev/api/packages/<name> | python3 -c "import json,sys;print(json.load(sys.stdin)['latest']['version'])"

Publish only packages whose manifest is ahead. Meta-packages usually need nothing: the Python and Dart ones resolve dependencies at install time, so an existing range already picks up a new sibling. npm is different — see section 4.

2. Check for unreleased API in dependencies

For every package about to be published, diff each dependency against what is actually on the registry. A dependency whose source has moved ahead without a version bump is the failure mode this repo has hit before.

# unpack the published artifact, then diff against local source
diff -ru <unpacked-published>/<module> <local>/src/<module> -x __pycache__

If a dependency has gained API, release the dependency first and raise the consumer's floor in the same change. A floor of >=3.0.0 is a promise that the package works against 3.0.0 — not merely that it works against whatever you have installed.

Read the full file on GitHub · 195 lines

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. 10d ago First seen · 195 lines · 52 tokens per session scan C 76b05b795e5d

Subscribe to this mod's changes

release is a skill published in the GitHub repository brilliantlabsAR/brilliant_sdk (101 stars, last pushed 14d ago), licensed BSD-3-Clause. It adds 52 tokens to every session and 2,327 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.