Your AI brain, externalized. It remembers everything you do, then becomes whatever role you need. Same skeleton can run as your chief of staff, lawyer, PM, or investigator. Plain markdown. Built on Claude Code.
This repository also configures its own agents. See what kipi-system tells them →
Plugin Claude Code
Bundles 10 skills, 9 commands · 818 tokens together
Core founder OS — voice, research, AUDHD, LinkedIn/brand, RCA skills + kipi-mcp server.
Plugin Claude Code
Bundles 3 skills · 121 tokens together
Brand, UI/UX, and design skills.
Plugin Claude Code
Bundles 6 commands · 104 tokens together
DSSE issue workflow: scope-enforced edits, per-finding dispositions, Codex review gates. Provides /issue-start, /issue-approve, /issue-verify, /issue-review, /issue-amend, /issue-closeout. Consumes issue specs created by prd-os or dropped in manually.
Plugin Claude Code
Bundles 1 skill · 22 tokens together
GTM and council skills.
Plugin Claude Code
Bundles 2 skills, 9 commands · 334 tokens together
PRD operating system: capture rough ideas, draft reviewable PRDs, run standard and adversarial review (Codex or a Claude senior-staff-engineer subagent, recorded truthfully), triage findings, decompose approved PRDs into atomic issue specs, and execute those issues with scope enforcement, stop-gate receipts, and…
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: