Borrowing it
Nothing to install: this file belongs to biulight/shine. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/biulight/shine/release/AGENTS.mdgit 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/instructions/biulight/shine/agents-md)<a href="https://agentmods.dev/instructions/biulight/shine/agents-md"><img src="https://agentmods.dev/badge/instructions/biulight/shine/agents-md/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/instructions/biulight/shine/agents-md"><img src="https://agentmods.dev/badge/instructions/biulight/shine/agents-md.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 | $0.01580 | $0.01580 |
| Opus 5.5 | $0.00632 | $0.00632 |
| Sonnet 5.5 | $0.00316 | $0.00316 |
| Haiku 4.5 | $0.00158 | $0.00158 |
Grade A, and why
shine AGENTS.md 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 4d 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 — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
shine bundles shell, app, and OS bootstrap presets into a Rust CLI with manifest-tracked
installation and uninstall. The root package is shine-cli (sources in cli/); core/ is
shine-core. Keep this entry point focused on repository rules; route details to the KB.
Workflow and authorization
- Complete authorized edits and verification using context for routine choices. Ask only when missing information changes the outcome or an action needs authorization not already given; continue independent work while resolving it.
- User instructions take precedence over skill workflow preferences. Skills and command examples do not grant permission to push, activate presets, execute external code, or bypass Shine's ownership, trust, and snapshot-bound approval checks. If an instruction blocks work, cite its file and exact requirement and explain what remains blocked.
- Preserve unrelated working-tree changes; do not overwrite or clean files you do not own.
- Before a non-trivial change, read the relevant sections of invariants and search lessons for the affected behavior. Check ADRs before proposing a design; consult data flows for changes spanning modules.
- Refactoring must reduce total maintenance cost while preserving behavior and safety boundaries. Prefer deletion and direct local code; fewer files, less duplication or more tests alone do not establish value. Count production, tests/support and docs separately, retain independent risk coverage, and follow the refactoring review gates.
- Update stale KB material in the same change using the maintenance protocol.
Hard repository rules
- Never run
git pushwithout explicit user approval, including branch, tag, and force pushes. A request to commit is not permission to push; retain approval already given for the same action. - Work lands on
release;mainreceives only automated post-release sync PRs (ADR 0001). CHANGELOG.mdis hand-written. Never generate it withgit cliff; the release workflow uses git-cliff only for the GitHub Release body.- Version decisions use the latest stable
v*tag, never the movingpreviewtag; follow versioning conventions. - Internal fixes caused by new code in the same release use the git-cliff-skipped scopes in commit conventions. Real user-facing fixes use their feature area.
- User-visible behavior changes must update both public manual locales in the same release change:
docs/manual/andwebsite/i18n/zh-Hans/docusaurus-plugin-content-docs/current/. Keep doc IDs, page sets, commands, identifiers, examples, and warnings semantically aligned. - Never publish
docs/kb/, PRDs, release runbooks, private paths, or internal procedures through the public site. Root READMEs are summaries, not a second command/configuration reference.
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.
- 4d ago Changed · +4 lines · +74 tokens per session a7b7a4efd204
- 5d ago Changed · +2 tokens per session f710d5015b8e
- 25d ago Changed · +8 tokens per session 8e5e505441c7
- 1mo ago Changed · -69 lines · -653 tokens per session 14258ef82cbf
- 1mo ago First seen · 174 lines · 2,149 tokens per session scan A 800e894290cd
shine AGENTS.md is an instructions file published in the GitHub repository biulight/shine (6 stars, last pushed yesterday), licensed MIT. It adds 1,580 tokens to every session, about $0.0063 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 instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.