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 agentmods add instructions/sybil-solutions/local-studio/agents-mdgit clone --depth 1 https://github.com/sybil-solutions/local-studioWrote 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/sybil-solutions/local-studio/agents-md)<a href="https://agentmods.dev/instructions/sybil-solutions/local-studio/agents-md"><img src="https://agentmods.dev/badge/instructions/sybil-solutions/local-studio/agents-md.svg" alt="Measured on agentmods" 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 | $0.00534 | $0.00534 |
| Opus 5 | $0.00267 | $0.00267 |
| Sonnet 5 | $0.00107 | $0.00107 |
| Haiku 4.5 | $0.00053 | $0.00053 |
Grade A, and why
local-studio 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.
What it actually says
AGENTS.md
Local Studio is a local-first workstation whose Bun/Hono controller and Next.js/Electron frontend share one controller API for model lifecycle, serving, system state, settings, usage, and agent sessions.
Work decisively without asking questions during execution, preserve user changes, never expose credentials, never use disable cuda graphs, enforce eager, or max_tokens with vLLM or SGLang, and leave no code comments in touched code.
Keep code composable and typed, use Effect for async and streaming, use the shared UI kit and design tokens, validate boundary data with Effect Schema, and keep contracts defined once in controller/contracts/ or shared/agent/ as appropriate.
NEVER WRITE TESTS. Do not add or restore unit, integration, end-to-end, snapshot, browser, smoke, or any other automated test code.
Branch from the current origin/dev, keep one owner and one scoped pull request per branch, target dev, and never push directly to dev or main.
semantic-release's computed version is the authority for stable desktop releases. The release workflow injects that exact version into Electron package metadata, signing, staging, updater metadata, and versioned asset names before publishing the tag and GitHub release. Checked-in versions for the root app, frontend, controller, controller contracts, and agent runtime are synchronized development fallbacks for local and dev builds; they do not predict or define the next stable release. shared/package.json intentionally remains independently versioned at 0.0.0 and is not a desktop release version source.
Run npm run check before handoff. It is node scripts/project.mjs check — every gate CI runs (repo layout/contracts/structure, controller, agent-runtime tests, frontend quality including the production build) in one command. Never bypass git hooks.
Repo automation lives in frontend/desktop/automation/*.mjs as plain readable modules; scripts/project.mjs (a symlink to frontend/desktop/project.mjs) only dispatches. Edit the module, not the entry.
Commit conventionally as you go. CI builds and packages the desktop app on every run, so rebuild and reinstall locally only when you need to verify something by hand — use scripts/install-desktop-app.sh [stable|dev], never a hand-rolled backup copy.
Use the documented local, remote, deployment, and agent-runtime workflows in the repository, keep secrets in ignored .env.local, and treat the live browser, controller, installed app, or deployed domain as the acceptance target for visible behavior.
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 First seen · 17 lines · 534 tokens per session scan A 3219d06d580e
local-studio AGENTS.md is an instructions file published in the GitHub repository sybil-solutions/local-studio (1,752 stars, last pushed yesterday), licensed Apache-2.0. It adds 534 tokens to every session, about $0.0027 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 2026-08-30.
Other instructions, from other repositories
gptme AGENTS.md
AGENTS.md instructions for gptme/gptme, covering agent instructions for gptme, git workflow, code style, testing and project structure.
paddler CLAUDE.md
Instructions for intentee/paddler: When working with this codebase, prioritize readability over cleverness. Ask clarifying questions before making architectural changes.
localvoxtral AGENTS.md
AGENTS.md instructions for T0mSIlver/localvoxtral, covering localvoxtral — agent guide, build & test — read this first on a non-mac dev box, proof culture — non-negotiable, test tiers — the short version and ci / shipping.
cai CLAUDE.md
Instructions for cai-layer/cai, covering claude.md, what is cai?, design system, build & run and dev.
Bonsai-demo AGENTS.md
AGENTS.md instructions for PrismML-Eng/Bonsai-demo, covering agent guide — tuning the bonsai demo, why the 27b models (what to show off), the models, knobs that matter (27b) and adding mcp servers.
Meldwork AGENTS.md
Instructions for Ryder-MHumble/Meldwork, covering meldwork development rules, working style, product boundaries, frontend and desktop and verification.