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 biulight/shine --skill shine-preset-authorgit clone --depth 1 https://github.com/biulight/shineWrote 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/biulight/shine/shine-preset-author)<a href="https://agentmods.dev/skills/biulight/shine/shine-preset-author"><img src="https://agentmods.dev/badge/skills/biulight/shine/shine-preset-author/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/biulight/shine/shine-preset-author"><img src="https://agentmods.dev/badge/skills/biulight/shine/shine-preset-author.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 | $0.00047 | $0.00914 |
| Opus 5 | $0.00023 | $0.00457 |
| Sonnet 5 | $0.00009 | $0.00183 |
| Haiku 4.5 | $0.00005 | $0.00091 |
Grade A, and why
shine-preset-author 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 3d 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Shine Preset Author
Produce reviewable preset sources using the installed shine binary's templates and validator.
Infer routine details from the request and existing files. Ask only for missing choices that
materially affect the result; do not require a confirmation round before authorized authoring.
Follow the user's language for questions and results.
Authorization boundary
- Author only in the requested workspace, outside active Shine configuration and preset roots. Never link a source/overlay, activate a preset, grant trust, or run a real install, upgrade, bootstrap, artifact, hook, generator, or preset script in this workflow.
- Validation is static.
shine preset planis a hypothetical report, never an approval or input to apply. Permission declarations describe requirements; they do not grant trust or authority. - Use a fresh temporary
SHINE_CONFIG_DIRfor scaffolding as well as runtime dry-runs:preset newandpreset copycan initialize config. Set it per command; clean up only the exact temporary directory created for this task. Never supply real secrets to checks. - User instructions override workflow preferences; authoring authorization does not include activation. If a request also needs live changes, finish the reviewable sources first and identify the separate action and its authorization requirements. If this boundary blocks work, cite this file and the relevant rule rather than inventing an approval requirement.
Authoring
- Establish the outcome, target platforms, destinations, and required input names from the
request or existing preset. Check
shine preset validate --helponce for the installed binary. Useshine preset schema --format jsonwhen report, fixture, or bundle contracts are needed; it describes those contracts and live help, not the entire preset TOML grammar. If a needed command is unavailable, report that limitation without guessing support or upgrading Shine. - Read only the reference for each kind being changed: app, shell, or sys. A request spanning kinds may use more than one; unrelated kinds need no review.
- Edit an existing category in place. For a new
<repository>/<kind>/<name>/, runSHINE_CONFIG_DIR=<temp>/shine shine preset new <kind>from the empty category directory. For a built-in copy, runSHINE_CONFIG_DIR=<temp>/shine shine preset copy <kind>/<name>from the workspace root; it creates the category path. Preserve referenced support files and unrelated edits; do not scaffold over an existing category. - Keep explicit
shine.tomlmetadata and referenced sources, scripts, fragments, and dependency files inside the category. Retain schema-v1 permission declarations at the proper target boundary; declare identities and environment sensitivity (plain/secret), never argv, values, ciphertext, credentials, or physical checkout paths in permission tables.
What ships with it
4 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.
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.
- 3d ago Changed · -29 lines · -35 tokens per session aea48371ad1e
- 6d ago Changed · +22 lines · +5 tokens per session ba87b759fad4
- 10d ago First seen · 70 lines · 77 tokens per session scan A 74458a975904
shine-preset-author is a skill published in the GitHub repository biulight/shine (5 stars, last pushed yesterday), licensed MIT. It adds 47 tokens to every session and 914 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…