trpc-compat
Skill16k starsChanged 15 days agoMITView on GitHub
Check that a tRPC change is safe for released desktop, mobile, CLI, and SDK builds, pick the compatible pattern, and decide when a deprecated procedure can be removed. Use when changing, renaming, or removing an existing procedure, input field, or output field in packages/trpc or packages/host-service, when reviewing such a PR, or when a deploy broke released clients.
1 other project uses a version of this; 1 new project in the last 4 weeks, against 0 the 4 before.
Adopted by
Surging: 1 new project took it in the last 4 weeks, none the 4 weeks before.thin data
Most recently taken up by
- ParadevAI/Paradevword for word, first seen Nov 1, 2026
Who's talking about superset-sh/superset
- Paradev“Introducing Superset”YouTube · Feb 27, 2026 · 13k views
- Paradev“What is Superset in 60s?”YouTube · Jan 3, 2026 · 5.6k views
- Repocast | GitHub 일일 브리핑“AI 에이전트 IDE, Superset으로 생산성 10배 올리기!”YouTube · Mar 1, 2026 · 2.7k views
- Gourcer“superset-sh/superset - Gource visualisation”YouTube · Mar 1, 2026 · 1k views
- DevDrop“Superset: Run an Army of Claude Code Agents in Parallel”YouTube · May 14, 2026 · 422 views
The biggest 5 of 50 mentions linking to the repository that our crawl found. Each line is their own headline.
See all 50
Talked about on GitHub, Bluesky, YouTube, Hacker News and the web (50 times).
On GitHub · 20
- Mar 18, 2026[bug] unable to create worktree from existing branch — ParadevAI/Paradev14 reactions · 6 comments
- Oct 25, 2026"Use this instead of publishing a Claude artifact whenever the reader is a teammate" — ParadevAI/Paradev3 reactions · 2 comments
- Mar 24, 2026Feat/linux desktop support — ParadevAI/Paradev2 reactions · 10 comments
- Jan 9, 2026[Question]: How is OMOC compared to the other OpenCode tools? — code-yeongyu/oh-my-openagent2 reactions · 2 comments
- Oct 27, 2026chore(marketing): say Paradev in marketing, email, and agent docs copy — ParadevAI/Paradev1 reaction · 3 comments
15 more on GitHub
- Oct 27, 2026docs(marketing): show the former name in structured data and llms.txt — ParadevAI/Paradev1 reaction · 4 comments
- Oct 20, 2026chore(desktop): bundle pdev 0.1.5 — ParadevAI/Paradev1 reaction · 3 comments
- Oct 6, 2026chore(dev): isolate the pinned PostgreSQL 18 development volume — ParadevAI/Paradev1 reaction · 2 comments
- Oct 6, 2026fix(desktop): allow configured S3 upload origins in CSP — ParadevAI/Paradev1 reaction · 2 comments
- Oct 1, 2026fix(desktop): stop links from swallowing text typed after a URL — ParadevAI/Paradev1 reaction · 3 comments
- Sep 9, 2026Changes pane fails to refresh and displays stale diffs after committing and making follow-up changes — ParadevAI/Paradev1 reaction · 1 comment
- Sep 4, 2026chore(desktop): bump version to 1.26.0 — ParadevAI/Paradev1 reaction · 3 comments
- Jun 24, 2026feat(sidebar): show worktrees symlinked into a project's dependencies — ParadevAI/Paradev1 reaction · 3 comments
- Apr 8, 2026feat(desktop): workspace number badges on modifier hold — ParadevAI/Paradev1 reaction · 5 comments
- Mar 27, 2026Support independent working trees? — siteboon/claudecodeui1 reaction · 1 comment
- Mar 8, 2026[bug] github no longer connected (1.0.7 => 1.1.2) — ParadevAI/Paradev1 reaction · 1 comment
- Mar 6, 2026[bug][security] Masked terminal input (passwords) leaked into tab titles via commandBuffer — ParadevAI/Paradev1 reaction · 2 comments
- Oct 14, 2026Forgejo/codeberg support — ParadevAI/Paradev0 reactions · 1 comment
- Oct 12, 2026Add Superset agent workspace detection — auron-labs/harness-detect0 reactions
- Oct 10, 2026feat(desktop): add an optional centered reading width for terminal panes — ParadevAI/Paradev0 reactions · 1 comment
On Bluesky · 14
- Mar 2, 2026Turn your terminal into a coding agent command center - run Claude Code, Codex, and 10+ AI agents simultaneously with git worktree… — @arifsolmaz.bsky.social4 likes and reposts · 1 reply
- Feb 28, 2026🔥 Hot Repo! 🔥 (100+ new stars) 📦 superset-sh / superset ⭐ 2,233 (+156) 🗒 TypeScript IDE for the AI Agents Era - Run an army of Claude… — @github-trending-js.bsky.social4 likes and reposts
- May 24, 2026Parallel agent execution is smart – but the real win here is finally getting proper observability into what these coding agents are… — @sirile.bsky.social3 likes and reposts · 2 replies
- May 23, 2026Superset is an open-source IDE for running multiple AI coding agents in parallel on macOS. — @druce.ai3 likes and reposts
- Sep 2, 2026📦 superset-sh / superset ⭐ 13,646 (+48) 🗒 TypeScript Superset is an agentic IDE to orchestrate 100+ coding agents in parallel. Run any… — @github-trending-js.bsky.social2 likes and reposts
9 more on Bluesky
- May 25, 2026📦 superset-sh / superset ⭐ 11,101 (+64) 🗒 TypeScript Code Editor for the AI Agents Era - Run an army of Claude Code, Codex, etc. on your… — @github-trending-js.bsky.social2 likes and reposts
- Mar 21, 2026the bottleneck with AI coding agents was always "one task at a time." Superset runs 10+ agents in parallel, each in its own git worktree so… — @ai-nerd.bsky.social2 likes and reposts
- Mar 6, 2026Superset : un terminal turbochargé pour faire tourner une équipe d'agents IA de code en parallèle (Claude Code, Codex…). Chaque agent… — @camilleroux.com2 likes and reposts · 1 reply
- May 22, 2026⚡ ALPHA · score 8/10 Launch HN: Superset (YC P26) – IDE for the agents era https://github.com/superset-sh/superset — @alpha-pipeline.bsky.social1 likes and repost
- Apr 9, 2026🔥 Hot Repo! 🔥 (100+ new stars) 📦 superset-sh / superset ⭐ 9,006 (+192) 🗒 TypeScript Code Editor for the AI Agents Era - Run an army of… — @github-trending-js.bsky.social1 likes and repost
- Mar 5, 2026🎉 Celebrating! 🎉 (500+ new stars) 📦 superset-sh / superset ⭐ 4,675 (+795) 🗒 TypeScript IDE for the AI Agents Era - Run an army of… — @github-trending-js.bsky.social1 likes and repost · 1 reply
- Mar 2, 2026github.com/superset-sh/sup... GitHub - superset-sh/superset: IDE for the AI Agents Era - Run an army of Claude Code, Codex, et... — @technews4869.bsky.social1 likes and repost
- Feb 28, 2026🔥 Hot Repo! 🔥 (100+ new stars) 📦 superset-sh / superset ⭐ 2,233 (+156) 🗒 TypeScript IDE for the AI Agents Era - Run an army of Claude… — @github-trending.bsky.social1 likes and repost
- May 23, 2026📰 Superset, an open-source agentic IDE for running coding agents like Claude Code and Codex in parallel, has been launched by Avi, Kiet,… — @sagalinked.bsky.social0 likes and reposts · 1 reply
On YouTube · 13
- Feb 27, 2026Introducing Superset — Paradev13k views · 7 comments
- Jan 3, 2026What is Superset in 60s? — Paradev5.6k views · 2 comments
- Mar 1, 2026AI 에이전트 IDE, Superset으로 생산성 10배 올리기! — Repocast | GitHub 일일 브리핑2.7k views · 1 comment
- Mar 1, 2026superset-sh/superset - Gource visualisation — Gourcer1k views · 2 comments
- May 14, 2026Superset: Run an Army of Claude Code Agents in Parallel — DevDrop422 views
8 more on YouTube
- Mar 24, 2026You're Not Using AI Agents Efficiently (Here's Why) — Dhaval Bhatt | AI Product Accelerator211 views · 1 comment
- Mar 6, 2026Superset — Open Source Scribes82 views
- Aug 2, 2026Superset: Give Every Coding Agent Its Own Worktree — BACKFIRED X78 views · 1 comment
- May 27, 2026GitHub - superset-sh/superset: IDE for the AI Agents Era - Run an army of Claude Code, Codex, etc... — GitHub Daily Trend AI Podcast47 views
- Mar 7, 2026This Repo Got 7.3K Stars in 4 months — Here's Why 🔥 #Superset #AgenticAi #AiAgents #ClaudeCode #Cli — Pulse39 views · 1 comment
- Jun 26, 2026Claude Code, Codex e Cursor — superset-sh/superset orquestra agentes #AI #Shorts — RepoShots34 views · 1 comment
- May 19, 2026Superset — Open Source Scribes22 views
- May 22, 2026Synthetic Signal - Afternoon - May 22, 2026 — Synthetic Signal0 views
On Hacker News · 2
- May 22, 2026Launch HN: Superset (YC P26) – IDE for the agents era108 points · 135 comments
- Dec 1, 2025Show HN: Superset – Run 10 parallel coding agents on your machine24 points · 3 comments
On the web · 1
- Nov 9, 2026100개 이상의 AI 코딩 에이전트를 병렬로 실행하는 개발자용 ... — gitbap.com
Other versions1 project uses a version of this.
Word for word · 1
- ParadevAI/Paradev★ 16k100% 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.
In this repository16 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- autumnSkill
- cdp-verificationSkill
- db-migrationsSkill
- decideSkill
- dev-doctorSkill
- incident-triageSkill
- mobile-android-verificationSkill
- mobile-demo-filmSkill
- mobile-demo-recordSkill
- mobile-eas-devSkill
- mobile-sim-verificationSkill
- redesignSkill
- superset-settingsSkill
- ticket-formatSkill
The file
We split this skill into the rules it gives an agent
7 rules. About 0 are common, 4 are distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
Distinctive · estimate
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 16
Search the release tags, not main.
- Very specific: line 27
Desktop: every desktop-v* tag at or above the floor is live.
- Very specific: line 30
Mobile: no tags, and MINIMUM_MOBILE_VERSION is 1.0.0.
- Distinctive: line 78
Keep the schema migration in its own PR.
- Distinctive: line 83
Only when both are true:
- Very specific: line 88
If a live desktop build still calls it, the only path is to raise MINIMUM_DESKTOP_VERSION.
- Distinctive: line 97
Yes: write a forward fix that restores the old contract and moves the new shape to a new procedure, as #7756 did.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill 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
tRPC compatibility
On 2026-09-23, #7726 changed page.list from a bare array to { items, nextCursor }. It
updated every caller on main, so typecheck and tests passed. Desktop 1.30.0–1.30.2 still called
.map on the result, and every workspace view crashed (SEV1, 337 Sentry events, postmortem
"page.list response change crashed released desktop apps"). CI only sees main. This skill is how
you check the builds CI cannot see.
1. Find released callers
Search the release tags, not main. Run git fetch --tags first in a fresh clone.
PROC='page\.list(?!Paginated)' # the procedure path; exclude longer names that share the prefix
FLOOR=1.29.0 # MINIMUM_DESKTOP_VERSION in apps/api/src/app/api/desktop/version/route.ts
for v in $({ echo "$FLOOR"; git tag -l 'desktop-v*' | sed 's/^desktop-v//'; } | awk '!/-/' | sort -uV | sed -n "/^$FLOOR\$/,\$p"); do
git rev-parse -q --verify "refs/tags/desktop-v$v" >/dev/null || continue
git grep -q -P "$PROC" "desktop-v$v" -- apps/desktop && echo "desktop-v$v calls it"
done- Desktop: every
desktop-v*tag at or above the floor is live. - CLI: same loop with
cli-v*tags and-- packages/cli. The CLI has no floor, so check every tag you can; old installs stay in use. - Mobile: no tags, and
MINIMUM_MOBILE_VERSIONis1.0.0. Ifapps/mobileon main calls it, orgit log -Sshows it ever did, treat it as called by a live build. - SDK:
packages/sdkcalls procedures by string (/api/trpc/<procedure>). Search main andgit log -Sthe same way. - host-service procedures: callers are desktop, CLI, and mobile, and the host can be older or
newer than the client. See
packages/host-service/AGENTS.md.
Any hit means the procedure is live. Its input and output are frozen.
2. Check usage data
The API samples 1% of calls into the PostHog event api_procedure_called. Run this in the
PostHog SQL editor or through the PostHog MCP:
SELECT properties.client_product AS product, properties.client_version AS version,
count() * 100 AS est_calls, max(timestamp) AS last_seen
FROM events
WHERE event = 'api_procedure_called' AND properties.procedure = 'page.list'
AND timestamp > now() - INTERVAL 30 DAY
GROUP BY product, version ORDER BY product, versionZero rows is weak evidence for a rarely called procedure: 1% of a small number rounds to zero.
Calls from web and from builds older than the x-superset-client header are not recorded.
3. Pick the pattern
| You want to | Do this | Example |
| Change an output shape | New procedure; old one keeps its shape | page.list + page.listPaginated (#7756) |
| Add an input | New optional field, default in the handler (safe: old clients do not send it) | |
| Accept a new input shape | Accept both, convert server-side | rrule + triggers in automation/schema.ts |
| Rename a procedure | New name; old name stays as a @deprecated alias | task.all → task.list in task/task.ts |
| Drop an input | Keep accepting it and ignore it | branch in task/schema.ts |
| Drop an output field | Keep sending it until removal is allowed | the plugins catalog field that #7317 removed crashed old desktops |
| Drop or rename a DB column | Pick the procedure's output columns first, keep the old field | db.query.*.find* without columns returns every column |
| Make an input stricter | Only on a new input or procedure | publishPageSchema is .strict() from the start, so a newer CLI fails loudly on an older server |
| Change an error code, default, or sort order | New procedure, or a new optional input that opts in (absent keeps the old behavior) | desktop branches on NOT_FOUND and CONFLICT |
| Call a new procedure from a client | Merge the API first, then the client after the API is live | #7317's API deploy stalled two days behind migration 0119 |
To check the API is live, the latest Deploy Production run after your API merge must have
passed: gh run list --workflow deploy-production.yml --branch main --limit 5.
In client code, expect the unknown: guard new optional fields, handle enum values the client has not seen, and keep a failing widget from taking its parent view down with it. #7726 crashed the whole workspace view from one menu.
Keep the schema migration in its own PR. #7726 had a migration inside it, so the bad API change could not be reverted.
4. Remove a deprecated procedure or field
Only when both are true:
- Step 1 finds no call in a live desktop tag and no call from mobile, CLI, or SDK.
- Step 2 shows no calls from a live version over the last 30 days.
If a live desktop build still calls it, the only path is to raise MINIMUM_DESKTOP_VERSION. That
is a product decision; ask, do not do it in a cleanup PR. Put the evidence in the PR description,
as d1aee0922f did for device.heartbeat.
5. If released clients are already broken
- Confirm with Sentry: a new desktop issue that starts at the API deploy time.
- Does the PR that broke it include a migration that production already applied?
- No: revert the PR. The API redeploys on merge.
- Yes: write a forward fix that restores the old contract and moves the new shape to a new procedure, as #7756 did. Do not roll back the migration.
- Tell affected users to reload (Cmd+R). Some needed to restart the app or the terminal daemon.
Checklist
- Step 1 run for every procedure whose input or output changed, with the result in the PR
- No existing input field is new-required, renamed, retyped, or more strictly validated
- No existing output field is removed, renamed, retyped, wrapped, or newly nullable,
including through a DB column change on a
find*withoutcolumns - No change to an existing error code, default limit, sort order, or meaning of
null - No change to a procedure's type (query, mutation, subscription), the link, or the transformer
- No new required header or stricter auth on an existing procedure
- Client code that needs a new procedure merges after the API is live in production
- Every new input field is optional with a server-side default
- A replaced procedure is kept as a
@deprecatedalias - No schema migration in the same PR as the contract change
- Removals: step 1 and step 2 evidence is in the PR
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.

