Start Technologies is a monorepo, meaning one repository containing the source for several related products, including StartOS, StartWRT, StartTunnel, developer tools, and shared libraries. Its products support personal servers, routers, VPN or forwarding, service packaging, registries, and related self-hosting tasks, with shared Rust and Angular code. Catalogue add-ons support development across this product repository.
Borrowing it
Nothing to install: this file belongs to Start9Labs/start-technologies. 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/Start9Labs/start-technologies/master/AGENTS.mdgit clone --depth 1 https://github.com/Start9Labs/start-technologiesWrote 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/start9labs/start-technologies/agents-md)<a href="https://agentmods.dev/instructions/start9labs/start-technologies/agents-md"><img src="https://agentmods.dev/badge/instructions/start9labs/start-technologies/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/start9labs/start-technologies/agents-md"><img src="https://agentmods.dev/badge/instructions/start9labs/start-technologies/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 | $0.15474 | $0.15474 |
| Opus 5.5 | $0.06190 | $0.06190 |
| Sonnet 5.5 | $0.03095 | $0.03095 |
| Haiku 4.5 | $0.01547 | $0.01547 |
Grade D, and why
start-technologies AGENTS.md scanned grade D with 3 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 yesterday.
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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
sudo apt update 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 --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh # proceed with default installation Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
sudo apt install -y ca-certificates curl gpg build-essential git \ How it starts
The opening of the file, as written. The whole thing — 382 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Agent/developer operating rules for the start-technologies monorepo root. This repo is the monorepo for all Start9 products. CLAUDE.md is a one-line @AGENTS.md import — do not edit it.
This file owns the shared contributor workflow and operating rules. See README.md for product context and ARCHITECTURE.md for the layout.
Keep these docs current. Every scope carries AGENTS.md / ARCHITECTURE.md / README.md (and CLAUDE.md, a one-line @AGENTS.md import). When a change makes a documented statement about structure, conventions, the build/test/release flow, or product context inaccurate, correct it in the same change — never defer. Leave accurate text alone. These docs are hierarchical: each scope's docs cover only what is specific to it and must not repeat anything already stated at a higher scope (e.g. commit/PR conventions live only in this root AGENTS.md).
Required scope rules belong in AGENTS.md. It is plain Markdown, with no import syntax; a link does not load its target. Inline the workflow rather than hiding it behind a contribution guide. For shared skills and topical references, state explicitly when they must be read instead of duplicating their contents. CLAUDE.md stays a one-line @AGENTS.md import.
Contributor instructions live in AGENTS.md at every scope. Do not create separate contribution guides. Each AGENTS.md must have a sibling CLAUDE.md containing exactly @AGENTS.md and a newline. Put project context in README.md, structural reference in ARCHITECTURE.md, and required workflows and rules here.
Documentation follows accuracy, not the diff. For user-facing books and developer-facing references, change existing text only when the change makes it inaccurate or misleading. If the docs remain accurate, leave them unchanged: touching a feature does not make it more important or warrant a special callout, caveat, or explanation of the fix. The exception is a new feature readers would not otherwise discover and that would have belonged in the docs had it existed when they were written; document it in the appropriate existing page or section, at the same level of emphasis as comparable features. Required documentation changes ship with the code in the same change, in the owning product's docs/ directory (e.g. projects/start-os/docs/, projects/start-tunnel/docs/, projects/start-sdk/docs/).
Changelog requirements are separate. Any change that alters user-visible behavior must add a fragment at projects/<product>/changelog/<tier>-<kind>-<descriptive-name>.md in the same change, whether or not its documentation needs editing. Use patch, minor, or major for the impact tier and lowercase added, changed, deprecated, removed, fixed, or security for the kind. The body is Markdown bullets without headings. Internal tooling changes need no product fragment. CHANGELOG.md is generated release history; contributors do not edit it.
Book authoring conventions. The conventions for authoring any product book — mdBook versions, admonitions, tabs, SUMMARY.md, the shared theme/ — live in projects/start-docs/AGENTS.md. That project is a sibling, not an ancestor, so nothing loads it for you: read it before editing book pages anywhere in the repo.
The highest pending fragment tier determines the next version. Freshly query origin before deciding release state — git fetch --tags origin or git ls-remote --tags origin '<product>/v*'. The highest stable <product>/v<version> tag is the baseline; prerelease tags do not advance it. Update the canonical manifest to that baseline plus the highest pending tier: patch increments patch, minor increments minor and resets patch, major increments major and resets minor and patch. StartOS keeps a leading 0 outside SemVer: 0.4.0.3 is effectively 4.0.3, with a zero patch omitted (0.4.1, not 0.4.1.0). With no pending fragments, keep the released version; before a product's first release, choose its initial version explicitly. PR CI enforces the calculation for products whose fragments or canonical manifests changed; push CI checks all products. manage-release.sh pre-check and tag enforce it for the release being cut. They use node scripts/changelog.mjs check-version projects/<product>. A version bump pairs with its fragments and release notes. If a change refines a feature still awaiting release, update that feature's fragment rather than describing a fix to something users never received.
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.
- yesterday Changed · +62 tokens per session fadc33162812
- 2d ago Changed · +2 lines · +117 tokens per session 6aec3990d63d
- 3d ago Changed · +1 lines · +84 tokens per session 99d1e1c157d8
- 4d ago Changed · +29 tokens per session e00aa2aa3b89
- 6d ago Changed · +1 lines · +18 tokens per session 0340609c60c3
- 10d ago Changed · +1 lines · +88 tokens per session 0c0cae4c835e
- 15d ago Changed · +1 lines · +63 tokens per session f385e167415c
- 16d ago Changed · +2 lines · +168 tokens per session 82bd0533ac50
- 18d ago Changed · +34 tokens per session 50f106bfa17d
- 20d ago First seen · 374 lines · 14,811 tokens per session scan D f1ec0049fcc3
start-technologies AGENTS.md is an instructions file published in the GitHub repository Start9Labs/start-technologies (1,994 stars, last pushed today), licensed MIT. It adds 15,474 tokens to every session, about $0.0619 per session on Opus 5.5. A static security scan graded it D with 3 findings (asks for root, 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.
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).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.