AGENTS.md · debpalash/VoiceStudio
AGENTS.md from debpalash/VoiceStudio: 85 lines covering Active desktop: Electron only, Mobile: native iOS and Android (owner-set 2026-10-17), Token economy…
Template by debpalash
Chalk Labs
Need help deploying AGENTS.md · debpalash/VoiceStudio?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode, Claude Code. Read the repository before you give any tool access to your data.
curl -fsSL https://raw.githubusercontent.com/debpalash/VoiceStudio/main/AGENTS.md -o AGENTS.md
Read it and adapt it to your project before use.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: prompt-engineering
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
What's in it
An AGENTS.md file: instructions coding agents (Codex, Cursor, Copilot, Gemini CLI and others) read before working in a repo.
- For
- Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode, Claude Code
- Length
- 85 lines
- File
AGENTS.md
Sections
- Active desktop: Electron only
- Mobile: native iOS and Android (owner-set 2026-10-17)
- Token economy (owner directive, 2026-07-20; tightened 2026-07-28)
- Cross-platform parity: behaviour, not performance
- Merge protocol (hard rules)
- Change rules (see CLAUDE.md for full text)
- Shared select controls
- Agent skills
First lines (shown under the repo's AGPL-3.0 license)
## Active desktop: Electron only Electron (`electron/`) is the only desktop and web UI. The Tauri shell and legacy UI entrypoints are removed; do not restore build, runtime, release, or CI paths for them. Triage reports from final Tauri installations toward the migration guide and preserve their immutable updater feeds. Some modules under `electron/src/shared/` remain temporarily shared by Electron; they are not a runnable app. New UI, IPC, setup instructions, tests, and browser assets belong in Electron; validate Electron on macOS, Windows and Linux. ## Mobile: native iOS and Android (owner-set 2026-10-17) Every release builds desktop, iOS, Android and Docker from the same release tag and version (owner-set 2026-10-26). Phone downloads belong on the same GitHub Release; a missing channel is a release bug. `mobile/ios/` (Swift/SwiftUI) and `mobile/android/` (Kotlin/Compose) are native apps that run models **on the phone** (TTS, dictation, voice cloning, dub translation; owner-set 2026-10-18) and can also drive a user's own VoiceStudio computer. Phone first: once models are downloaded they work offline with no computer; pairing adds the heavy engines, chosen per task. The companion-only build is the base, not the product. They implement one shared contract, `mobile/contract/SPEC.md`: a mobile feature ships on both or neither. Theme, API and strings are generated, never hand-copied: `bun scripts/export-mobile-tokens.ts` (from the Electron theme), `uv run python scripts/export_openapi.py` (from the backend) and the Electron locale catalogs; `tests/test_mobile_contract.py` fails on drift. Desktop/web UI still belongs in Electron only. # Agent Rules — VoiceStudio Binding for every AI agent (Claude, Codex, Cursor, review bots, …). CLAUDE.md is the full constitution; this is the operating contract. When they conflict, CLAUDE.md wins. ## Token economy (owner directive, 2026-07-20; tightened 2026-07-28) - **Default to the shortest response that fully answers.** Outlines and tables over prose; no preamble, no recap of what you just did, no re-explaining a fix the diff already shows. Applies to every response, not just status updates. - Lead with the outcome. No narration, no restating diffs, no filler praise, no plans you're about to execute anyway. - Status updates: one line. Final reports: only what changes the reader's next action. - Don't re-derive what CI, linters, or review bots already computed — read their output first (`gh pr checks`, bot comments via `gh api .../pulls/N/comments`). - Mechanical rules live in deterministic tests, never in agent effort: changelog style (`tests/test_changelog_style.py`), locale parity (`tests/test_locale_parity.py`), version lockstep (`tests/test_app_version.py`), CJK (`tests/test_no_hardcoded_cjk.py`). - Run targeted tests while iterating; full suites only before landing. - Tests and CI simulate CI honestly: `HF_HUB_OFFLINE=1` + empty `HF_HUB_CACHE` — a populated dev cache masks real failures. ## Cross-platform parity: behaviour, not performance - The parity rule covers user-visible BEHAVIOUR. Hardware acceleration varies by host by design (CUDA/MPS/DirectML, Triton availability, `torch.compile`); skipping an optimization where it physically cannot work is not a parity violation. - Do not "fix" a parity finding by disabling a working optimization everywhere. That trades a real regression for a semantic one. - A feature the user can see and use on one OS but not another IS a violation. Judge by what the user can do, not by how fast it runs. ## Merge protocol (hard rules) 1. Never merge without review. Harvest CodeRabbit + Greptile comments first; never merge with an unread Critical/P1. 2. Never accept a PR as-is: fix findings ON the PR branch pre-merge (maintainer commits fine; credit contributors in the changelog fragment). No merge-then-fix, no comment-and-walk-away. 3. Merge current `main` into stale branches before judging their CI — PR-green under an old workflow ≠ main-green. 4. Gate: "Tests (backend + frontend)" green + MERGEABLE. 5. After EVERY merge: watch `main`'s own post-merge runs to green (`gh run list --branch main`). Red main = drop everything and fix. 6. Start every PR, fix and feature from freshly fetched `origin/main` (owner rule, 2026-10-26): `git fetch origin`, confirm local `main` has no incoming or outgoing commits (resolve first if it does), branch from `origin/main`, and merge the latest `main` again right before pushing. `main` requires branches to be up to date before merging; that setting stays on. ## Change rules (see CLAUDE.md for full text) - Root-cause the class, not the instance; fail-before/pass-after regression test; smallest correct change. - Default behavior identical on macOS/Windows/Linux; platform-only features go behind explicit opt-in. Divergent default = P0. - Local-first: no new required network calls; any HF download gated on installed-ness or explicit user action; all synthetic audio through the `mark_synthetic` chokepoint. Sanctioned calls are listed in `.github/CONTRIBUTING.md` → Quality gates: user-started first-run setup (ffmpeg from GitHub `zackees/ffmpeg_bins`, the huggingface.co/hf-mirror.com reachability probe, `uv.lock`-pinned package downloads from their locked URLs or the chosen/auto-selected regional mirror incl. the parallel wheel prefetch, the Auto region's one-wheel PyPI vs Aliyun speed check, HF model downloads), opening/enabling the galleries (jsDelivr manifest, GitHub Releases), packaged update checks, user-clicked yt-dlp updates from PyPI, user-selected Windows ROCm setup (owner-approved 2026-10-26, hash-pinned: `repo.radeon.com` wheels and the OpenNMT/CTranslate2 GitHub release), consent-gated analytics, prefilled-URL bug reports, phone content reports sent from a result's Report sheet, the Pro licence check after a key is entered, and VoiceStudio Cloud sign-in/account calls (and settings sync once cloud sync is on) only after the user turns them on (off by default; switching off stops them at once). Owner-approved exception (2026-09-28): the public GitHub star count may refresh automatically every 20 minutes, without credentials/referrer or user content; offline use remains unaffected. - Every user-facing string via i18n, present in ALL 21 `electron/src/renderer/src/i18n/locales/*.json` files (the catalog the app loads) with real translations; `tests/test_locale_parity.py` and Electron `locale:check` enforce it. The legacy `electron/src/shared/i18n/` catalog is loaded only by shared-module tests. - Docs-sync in the same PR. Changelog: one quiet one-liner per PR in `changelog.d/<PR#>.<type>.md` (not `CHANGELOG.md`), ending `(#N)` + `— thanks @user!` for community work; the release script folds fragments into Unreleased. - Tagged release announcements lead with the biggest user-visible change; redesigns need real UI screenshots and migrations need installer links and steps. Verify all contributor credits from the tag comparison and included PRs; list authors and bug reporters separately (see `docs/RELEASING.md`). - Versioning: root `package.json` is the single source of truth; never bump without the owner asking. - JavaScript dependency changes require regenerating root `bun.lock` (Docker runs `--frozen-lockfile`). - Attribution: commits, PR descriptions and comments carry only the submitter's git identity. Never credit an agent (no agent `Co-authored-by:`, "Generated with …", session links) and never add other names/emails. Human co-authors are fine. Enforced by the `commit-identity` check. - Issues: absorb or decline — never defer to a future version. Check the open-PR queue before implementing community-reported fixes. ## Shared select controls - Use `electron/src/shared/components/SearchableSelect.jsx` for all new or redesigned select boxes. Reuse `VoiceSelector` for voice choices. Do not introduce native `<select>` controls. - Provide a localized `ariaLabel`; use `menuPortal` inside scrolling or clipping containers. Preserve keyboard selection and disabled states. ## Agent skills Project development skills are pinned in `skills-lock.json` and installed under `.agents/skills/`: Vite and FastAPI. Repository rules and tracker mappings override generic skill guidance. ### Issue tracker GitHub Issues on `debpalash/VoiceStudio`, via the `gh` CLI. See `docs/agents/issue-tracker.md`. ### Triage labels The five canonical roles, each label string equal to its name. See `docs/agents/triage-labels.md`. ### Domain docs Single-context: `docs/adr/` plus a root `CONTEXT.md` that is created lazily and does not exist yet — skip it when absent. See `docs/agents/domain.md`.
Signals
- Stars
- 84,584
- Forks
- 9,351
- Open issues
- 160
- Last commit (this folder)
- Oct 24, 2026 (6 days ago)
- Last release
- Sep 23, 2026 (1 month ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- AGPL-3.0
- Repository
- github.com/debpalash/VoiceStudio
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from debpalash
- 0.744score
CLAUDE.md · debpalash/VoiceStudio
debpalash
CLAUDE.md from debpalash/VoiceStudio: 138 lines covering Active desktop: Electron only, Mobile: native iOS and Android (owner-set 2026-10-17), Project…
TemplateAFreshness: A★ 84.6KClaude Code - 0.704score
owner-judge
debpalash
Subagent "owner-judge" from debpalash/VoiceStudio: Reviews proposed changes to VoiceStudio against the owner's documented standards.
TemplateBFreshness: B★ 84.6KClaude Code
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get AGENTS.md · debpalash/VoiceStudio running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
AGENTS.md · debpalash/VoiceStudio. Agent Mart. https://agentmart.dev/templates/debpalash-voicestudio-agents-md (last updated 2026-10-24)