Compound Labs
Get the newsletter
THE STANDUPAnthropic fixes Claude 5.1 error spikesERROR SPIKES, FIX DEPLOYEDCOMPOUND MASTODONSkillWorks records inactive files beside their roster status22 INACTIVE FILES STILL LOADCTXWINDOWContext Window tracks AI lab changes and filters their evidenceFILTERS KEEP EVIDENCE TOGETHERAGENTWIREmicrosoft/agent-governance-toolkit - AI Agent Governance ToolkitPOLICY ENFORCEMENT FOR AI AGENTSCOMPOUND FACEBOOKCompound Portfolio restores its sweep after a missing module stops desk dataSWEEP RESTORED, DESK DATA WRITTENBLOCKDEXBlockDex shows no destination for captured rows with rejected slash names31 ROWS, NO DESTINATIONCONTEXT WINDOWOpenAI adds 1024p image pricing: $0.50 and $0.251024P IMAGE, $0.50 AND $0.25COMPOUND BLUESKYCompound Labs renamed job labels so job-run finds breaker stateBREAKER STATE, NOW FINDABLECTXWINDOWContext Window tracks document changes but failed mobileMOBILE WORKFLOW, ONE COLUMNAGENTWIREMineDojo Voyager: Open-Ended Embodied AgentOPEN-ENDED EMBODIED AGENTFOUNDER BLUESKYdeploy.sh now fails false Vercel production landingsFALSE LANDINGS NOW FAILCOMPOUNDlast known fixes redirect tracking after migrationSTUDIO SOURCES NOW SAY COMPOUNDCONTEXT WINDOWOpenAI adds sora-2-pro pricing720P VIDEO, $0.15, $0.30FOUNDER LINKEDINdeploy.sh now stops failed promotes from marking production landedFAILED PROMOTES NO LONGER LANDUSINGITUPUsing It Up records a receipt fixing a wobbling wooden tableONE RECEIPT, TABLE STAYED LEVELCOMPOUNDpnpm v12.4.2POSIX BIN SHIMS REPLACEDFOUNDER PEERLISTCompound Labs' deploy runner rejects failed promotesFAILED PROMOTES NO LONGER LANDTRUSTDESKTrustDesk fixes host migration redirects while keeping /api/ outOLD HOST, 308; API STAYS LIVE
Independent product R&D labFounded and run by Isaiah Kim, @kyisaiah47Newest commit Sep 16, 2026, AgentwireNewest writing Sep 16, 2026Site changelog Sep 16, 2026
Sep 16, 20264 products2 min read

Four directories that turn source material into working decisions

This issue carries four directories that turn public source material into a browsable answer.

What is inside

Each section names the question the page answers, who it serves, and the concrete record it leaves you with.

---

StoreReady

StoreReady

StoreReady answers which AI app builders can reach App Store submission on your own developer account. It is for people choosing a mobile app builder, and it gives you a sourced docket with builder output, submission ownership, verdicts, and caveats.

storeready.thecompound.tech

---

KitGrade

KitGrade

KitGrade scores SaaS starter kits against what a buyer can check in the repository, documentation, pricing page, and install transcript. It is for developers choosing a boilerplate, and it gives you a score, capability grid, evidence method, price, and build transcript where available.

kitgrade.thecompound.tech

---

RuleStack

RuleStack

RuleStack counts real AGENTS.md, CLAUDE.md, Cursor rules, Copilot instructions, and related files across repositories. It is for developers working with coding agents, and it gives you counts by format, topic, stack, repository, and file path.

rulestack.thecompound.tech

---

SkillWorks

SkillWorks

SkillWorks scores Claude Code skills, subagents, plugins, and marketplaces on whether they load, how they are maintained, how widely they are adopted, and how they are documented. It is for developers choosing a skill, and it gives you a scored listing with source details, install evidence, documentation notes, and load verdicts.

skillworks.thecompound.tech

All writing