Borrowing it
Nothing to install: this file belongs to sybrew/troy. 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/sybrew/troy/main/.github/instructions/local.instructions.mdgit clone --depth 1 https://github.com/sybrew/troyWrote 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/sybrew/troy/local)<a href="https://agentmods.dev/instructions/sybrew/troy/local"><img src="https://agentmods.dev/badge/instructions/sybrew/troy/local/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/sybrew/troy/local"><img src="https://agentmods.dev/badge/instructions/sybrew/troy/local.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 | $0.00650 | $0.00650 |
| Opus 5.5 | $0.00260 | $0.00260 |
| Sonnet 5.5 | $0.00130 | $0.00130 |
| Haiku 4.5 | $0.00065 | $0.00065 |
Grade A, and why
troy local.instructions.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 2d 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 — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Local Workspace Rules
.local/is gitignored. Agent Grep and Glob cannot search it, even with an explicit path..cursorignore!.local/**does not fix those tools. Use Read/Write with an explicit path, or Shell (Get-ChildItem,Select-String,rg --no-ignore-vcs). A zero Grep/Glob result does not mean.localis empty.- Treat
.local/as private workspace-only context. - Do not expose
.local/details or related-repository context in public-facing instructions or responses unless the user asks for them. - Keep private workspace-only guidance, partner or outreach rules, and related-repository cross-references in
.local/.instructions/*.instructions.md, not in tracked repo instruction files. - Troy is a monorepo. When local guidance refers to Troy, Troy Server, Troy Client, Troy Client Daemon, or Troy Installer, keep the target package explicit.
- Treat support, partner, or outreach inquiries as first-class engineering work.
- These inquiries may require code inspection, reproduction, remediation, product explanation, or patches.
- Do not assume an inquiry is explanation-only.
- Diagnose whether the issue is configuration, expected behavior, a defect, a documentation gap, or a feature gap before recommending action.
- Fix the cause, not the symptom.
- Prefer the smallest safe remediation that prevents end-user issues.
- If the issue cannot be resolved from current context, gather the missing evidence or ask precise follow-up questions.
Load .local instruction files
.local/.instructions/*.instructions.md is not auto-injected. Do not Read them all.
- From the repo root, extract YAML frontmatter only (commands below).
- Read the files whose
applyTomatches the current paths, or whosedescriptionmatches the task. Files with noapplyTostill match ondescription. - Do not paste the extract or private bodies into chat.
Windows
Get-ChildItem -LiteralPath '.local/.instructions' -Filter '*.instructions.md' | ForEach-Object {
$raw = [System.IO.File]::ReadAllText($_.FullName)
if ($raw -match '(?s)\A---\r?\n(.+?)\r?\n---') {
Write-Output ("FILE: {0}`n{1}`n" -f $_.Name, $Matches[1].Trim())
}
}
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.
- 2d ago First seen · 50 lines · 650 tokens per session scan A 1ca3169b15c0
troy local.instructions.md is an instructions file published in the GitHub repository sybrew/troy (55 stars, last pushed 14d ago), licensed MIT. It adds 650 tokens to every session, about $0.0026 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 2026-10-26.
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).
vscode model-prompts.instructions.md
Model-specific prompt authoring and registry guidelines.