dev-doctor
Skill16k starsChanged 15 days agoMITView on GitHub
Find what is going wrong with Devs in production, file each cause once in the Devs and Channels Linear project, and refine the Devs architecture one rough edge at a time. Run by the "Dev doctor" automations; use when asked to diagnose Dev failures or review the Devs architecture.
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
- incident-triageSkill
- mobile-android-verificationSkill
- mobile-demo-filmSkill
- mobile-demo-recordSkill
- mobile-eas-devSkill
- mobile-sim-verificationSkill
- redesignSkill
- superset-settingsSkill
- ticket-formatSkill
- trpc-compatSkill
The file
We split this skill into the rules it gives an agent
12 rules. About 0 are common, 8 are distinctive, and 4 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈8
Distinctive · estimate
This author's own choices. Worth a look.
4
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 26
Read it first: get_document on the Linear plugin.
- Very specific: line 27
Update it last. Two runs can overlap, so read it again right before you write, and change only your parts with save_document's patch, never …
- Distinctive: line 31
When this procedure is wrong or missing something, open a PR that edits this file.
- Very specific: line 78
Search the project for an issue that already names the cause: list_issues on project 124fd465-3c78-43dc-a252-e99f5f8c33e0, then look for …
- Distinctive: line 81
Known cause: add a comment with the new count and one example id.
- Distinctive: line 92
Never assign issues, change their status, or edit issues you did not open.
- Distinctive: line 96
Read "Rough edges" in the notebook and pick the one that costs the most right now.
- Distinctive: line 99
Read the code it names, and the history behind it (git log -S, the PRs).
- Very specific: line 100
Read the reference designs listed under "Research" in the notebook (superset pages pull <page id>).
- Distinctive: line 103
Write what you learned into the notebook as its own section, with sources.
- Distinctive: line 118
Update the notebook, then write your final message: mode, what you found, what you filed (with links), and anything that blocked you.
- Distinctive: line 128
Do not create other workspaces.
≈ “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
Dev doctor
Devs are Paradev's agent teammates (see "Architecture map" in the notebook). Their code was written fast on purpose. You keep it honest: you find the failures that slip through, you turn each understood failure into code so nobody treats it by hand again, and you move the architecture toward a good end state one change at a time.
The reconciler (packages/trpc/src/router/agent/reconcile.ts) already repairs the failures we
understand. You handle the ones nobody has seen before, and you make yourself unnecessary: a kind
of failure you have diagnosed three times with the same fix becomes a reconciler rule or a code
fix, and you stop seeing it.
You run in a cloud workspace of the Paradev repo. Nobody is watching: do not ask questions. When something blocks you, write it in the run log and in your final message, and continue.
Your notebook
The Linear document Dev doctor notes (id b74e1574-7fef-4297-b3b9-d99976cfcd26, in project
Devs and Channels, id 124fd465-3c78-43dc-a252-e99f5f8c33e0) is your memory between runs.
- Read it first:
get_documenton the Linear plugin. - Update it last. Two runs can overlap, so read it again right before you write, and change only
your parts with
save_document'spatch, never a full rewrite. Keep everything people wrote. Add one line at the top of "Run log" for this run. Update the "Failure kinds" table and the "Rough edges" list from what you learned. When you research something, add a section with what you found and the sources. - When this procedure is wrong or missing something, open a PR that edits this file.
Reach the plugins with superset mcp call-tool <tool> '<json args>' --plugin <linear|neon|posthog|sentry> --json, or the matching MCP tools if your agent has them.
Mode
The prompt says which mode: incidents (hourly) or architecture (daily). Do only that mode.
Incidents
1. Gather the last day
Until Devs v2 is in production, there is nothing to gather: if agent_turns has no attempts
column, add a run log line saying so and finish.
Production database: Neon plugin run_sql with project_id frosty-lab-32416990,
database_name neondb. SELECT only. Never write to production.
- Failed turns by cause:
select error_code, count(*), max(started_at) from agent_turns where status = 'failed' and started_at > now() - interval '1 day' group by 1 order by 2 desc - Turns that retried:
select id, session_id, attempts, last_attempt_error, status from agent_turns where attempts > 1 and started_at > now() - interval '1 day' order by attempts desc limit 50 - Turns the reconciler found lost:
error_code = 'lost'in the first query. - Writer tasks that finished without a pull request:
select s.id, t.id as task_id, t.title from agent_sessions s join tasks t on t.id = s.task_id where s.kind = 'task' and s.role = 'writer' and s.task_status = 'done' and t.pr_url is null and s.last_activity_at > now() - interval '1 day' - Loops, meaning turns with many tool calls:
select id, session_id, jsonb_array_length(tool_calls) as calls, reply from agent_turns where started_at > now() - interval '1 day' and jsonb_array_length(coalesce(tool_calls, '[]')) > 20 - Slow main-session answers:
select t.id, extract(epoch from t.settled_at - t.started_at) as seconds from agent_turns t join agent_sessions s on s.id = t.session_id where s.kind = 'main' and t.started_at > now() - interval '1 day' and t.settled_at - t.started_at > interval '60 seconds' order by 2 desc limit 20 - Possible router misses: a channel message with no mention and no turn, followed within 10 minutes by a message in the same channel that mentions a Dev.
PostHog (exec): count dev_reconciler_fixed by fix, and dev_turn_retried by reason, over
the last 7 days.
Sentry: search_issues in organization superset-sh for agent-worker, agentWorker, devTools
and reconcile, unresolved, last 7 days.
2. Group by cause
Many incidents share one cause. Group them, then read the evidence for one representative of
each group: the turn's row (reply, tool_calls, error_code, last_attempt_error), the code
on the path it took, and the Sentry event if there is one. Name the cause in one sentence, in
your own words. If you cannot name it, say what you ruled out.
3. File each cause once
Search the project for an issue that already names the cause: list_issues on project
124fd465-3c78-43dc-a252-e99f5f8c33e0, then look for the cause's fingerprint line.
- Known cause: add a comment with the new count and one example id. Do not open a second issue.
- New cause: open an issue in team
SUPERand project124fd465-3c78-43dc-a252-e99f5f8c33e0, with labeldev-doctor(create the label once if it is missing). Write it in the format in.agents/skills/ticket-format/SKILL.md. End the description with a lineFingerprint: <kind>/<short key>. - Fix clear and small: also open a draft PR. Branch
dev-doctor/<slug>fromorigin/main, one cause, a regression test, and the checks AGENTS.md asks for. Link it from the issue. Never merge. - Same fix a third time: the fix belongs in code. Make the PR a reconciler rule or a code fix that ends the kind, and say so in the notebook.
Never assign issues, change their status, or edit issues you did not open.
Architecture
- Read "Rough edges" in the notebook and pick the one that costs the most right now. Prefer one that incidents point at.
- Research it:
- Read the code it names, and the history behind it (
git log -S, the PRs). - Read the reference designs listed under "Research" in the notebook
(
superset pages pull <page id>). The teardowns of other products are the reference; current Paradev code is not a constraint. - Write what you learned into the notebook as its own section, with sources.
- Read the code it names, and the history behind it (
- Propose the end state, then the smallest step toward it that improves the codebase on its own:
- A design question: an issue in the project with the options, each option's costs, and your recommendation.
- A behaviour-preserving step: a draft PR with tests.
- Gate any PR before you open it. Give a fresh subagent the diff and your claim, nothing that
suggests it is good, and ask whether it makes the repository better: no net complexity, no
second way of doing something, no abstraction used once, no lighter shape missed. It ends with
VERDICT: OPENorVERDICT: DO NOT OPEN. Do not overrule it or ask again. - Mark the rough edge in the notebook: what you proposed, and the link.
One rough edge per run. Add any new rough edges you notice to the list.
Finish
- Update the notebook, then write your final message: mode, what you found, what you filed (with links), and anything that blocked you. When a step failed, put the command, its output, and the ids involved in the notebook and the final message; the workspace does not outlive the run.
- Last command, every run:
superset workspaces archive "$SUPERSET_SANDBOX_WORKSPACE_ID".
Rules
- Production data is read only.
- The repo is public: no customer names, domains, or message text in PRs or commits. Refer to turns, sessions, and Devs by id there. Linear and the notebook are internal.
- Do not create other workspaces.
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.

