toolport-studio
AGENTS.md4 starsChanged 4 months agoMITView on GitHub
Use these as implementation references when designing protocol handling, UX flows, and operational safeguards. This project vendors external repositories under .repos/ as read-only reference material for coding agents. - Prefer examples and patterns from the vendored source code over generated guesses or web search results. - Do not edit files under .repos/ unless explicitly asked. - Do not import from .repos/; application code must continue importing from normal package dependencies. - Manage vendored subtrees with vpr sync:repos; use vpr sync:repos…
1 other project uses a version of this.
Adopted by
Most recently taken up by
- btsouth/toolport-studioword for word, first seen Jul 28, 2026
Other versions1 project uses a version of this.
Word for word · 1
- btsouth/toolport-studio★ 4100% same
Edited · 0
None found.
Wrote their own version · 0
None found.
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.
Of the AGENTS.md files we read, the 32,671 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.
In this repository6 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- .cursor/rules/cursor-cloud.mdcCursor rule
- ios-debugger-agentSkill
- ios-simulator-browserSkill
- test-t3-appSkill
- test-t3-mobileSkill
The file
We split this AGENTS.md into the rules it gives an agent
11 rules. About 0 are common, 5 are distinctive, and 6 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈5
Distinctive · estimate
This author's own choices. Worth a look.
6
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 5
Keep local verification focused on the files and packages changed.
- Very specific: line 6
Use vp test run <test-files> for focused built-in Vite+ tests.
- Distinctive: line 8
Run targeted formatting, lint, and type checks for the affected scope when available.
- Very specific: line 9
Do not run repo-wide vp check, vp run typecheck, vp run test, or equivalent full-suite commands locally unless the user explicitly requests …
- Distinctive: line 14
Stop dev servers, watchers, and other long-running verification processes when the focused verification is complete.
- Distinctive: line 28
Use these as implementation references when designing protocol handling, UX flows, and operational safeguards.
- Distinctive: line 35
Prefer examples and patterns from the vendored source code over generated guesses or web search results.
- Very specific: line 36
Do not edit files under .repos/ unless explicitly asked.
- Very specific: line 37
Do not import from .repos/.
- Very specific: line 39
When updating a dependency with a configured vendored subtree, sync that subtree in the same change so .repos/ matches the installed …
- Very specific: line 41
When writing Effect code, read .repos/effect-smol/LLMS.md first and inspect .repos/effect-smol/ for examples of idiomatic usage, tests, …
≈ “Common” is an estimate: at least 1 in 5 of the 41,581 AGENTS.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
AGENTS.md
Task Completion Requirements
- Keep local verification focused on the files and packages changed. Run the smallest relevant test set; do not run the full workspace test suite as a routine completion step.
- Use
vp test run <test-files>for focused built-in Vite+ tests. Usevp run testonly when the affected package specifically requires itstestscript. - Backend changes must include and run focused tests for the changed behavior.
- Run targeted formatting, lint, and type checks for the affected scope when available.
- Use
- Do not run repo-wide
vp check,vp run typecheck,vp run test, or equivalent full-suite commands locally unless the user explicitly requests them. CI is responsible for the full verification suite. - After changing frontend interaction behavior, the primary agent must run one integrated verification pass for the web/desktop client after integrating the work. Interaction behavior means drag and drop, focus and selection, scroll and virtualization, animation and transitions, and pointer or keyboard handling — anything a unit test is structurally incapable of exercising, because jsdom reproduces neither native drag nor layout nor real event ordering.
- Web: use the
test-t3-appskill. Launch one isolated environment, authenticate through the printed pairing URL, and verify the affected flow in the controlled browser. - A change whose behavior a focused logic test fully covers — copy, labels, formatting, conditional rendering driven by a pure derivation — does not need this pass. Say so in the PR rather than running it out of habit.
- Subagents must not independently launch dev servers or repeat integrated client verification unless their delegated task explicitly requires it.
- Stop dev servers, watchers, and other long-running verification processes when the focused verification is complete.
- Web: use the
Package Roles
apps/server: Node.js WebSocket server. Wraps Codex app-server (JSON-RPC over stdio), serves the React web app, and manages provider sessions.apps/web: React/Vite UI. Owns session UX, conversation/event rendering, and client-side state. Connects to the server via WebSocket.packages/contracts: Shared effect/Schema schemas and TypeScript contracts for provider events, WebSocket protocol, and model/session types. Keep this package schema-only — no runtime logic.packages/shared: Shared runtime utilities consumed by both server and client applications. Uses explicit subpath exports (e.g.@toolport-studio/shared/git) — no barrel index.packages/client-runtime: Shared runtime package for sharing client code across web and mobile.
Reference Repos
- Open-source Codex repo: https://github.com/openai/codex
Use these as implementation references when designing protocol handling, UX flows, and operational safeguards.
Vendored Repositories
This project vendors external repositories under .repos/ as read-only reference material for coding
agents.
- Prefer examples and patterns from the vendored source code over generated guesses or web search results.
- Do not edit files under
.repos/unless explicitly asked. - Do not import from
.repos/; application code must continue importing from normal package dependencies. - Manage vendored subtrees with
vpr sync:repos; usevpr sync:repos --repo <id>to sync one configured repository. - When updating a dependency with a configured vendored subtree, sync that subtree in the same change so
.repos/matches the installed dependency version. - When writing Effect code, read
.repos/effect-smol/LLMS.mdfirst and inspect.repos/effect-smol/for examples of idiomatic usage, tests, module structure, and API design.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

