House standard for architecting modern web frontends — opinionated, type-safe, agent-first defaults for stack, data, state, styling, security, logging, i18n, and deploy.
★not rated 1
changed 8d agoA
tokens not measured
originalMIT
The work tracker that slowly writes your case study. Evidence-backed kanban board + session bookends + a case-study doc that accretes from your real commits.
★not rated 1 2mo agoA
tokens not measured
originalMIT
Copy-paste-first coding principles. Makes AI work like a senior engineer who never writes from scratch: grep, copy, adapt, ship. Code is memory. Comments are search indexes.
★not rated 1 3mo agoA
tokens not measured
originalMIT
Governed, spec-driven delivery for agent-built software: operator-authorized acceptance contracts, an honestly-tiered merge floor on your own branch protection + CI, deploy-once certification, and a citation-graph MCP.
★not rated 1
changed yesterdayA
tokens not measured
originalMIT
LLM security guardrails for Claude Code, for a self-hosted AgentGuards appliance — jailbreak detection, prompt-injection and web-content scanning, data-exfiltration blocking, and destructive-command authorization, enforced entirely by hooks. No bundled MCP server: Claude Code's .mcp.json cannot point at a…
★not rated 1▲
+1 23d agoA
tokens not measured
originalMIT
Installs 'The Fable Way' working discipline, built for a frontier Claude model at medium-xhigh effort: an auto-triggering method skill (reflexes, risk tiers, plan shape, a calibrated-code stance) plus runner skills (scope, debug, adversarial review, verify, ship) that dispatch a capability-confined fable-lens reviewer.
★not rated 1 1mo agoA
tokens not measured
originalMIT
A four-command suite (/agy, /agy-review, /agy-debug, /agy-panel) that consults Gemini, Claude, and GPT-OSS models through Google's Antigravity (agy) CLI from inside Claude Code.
★not rated 1 3mo agoA
tokens not measured
originalMIT
D∞ — the ⟨parts | Ω⟩ shape every durable teaching, framework, plan, and joke has, as a working toolchain: an agent embodied in a directory, three operators (FACTOR / ADJOIN / CHRISTEN), and a gate that catches a missing closure at the syntax level.
★not rated 1 1mo agoA
tokens not measured
originalMIT
Agentic loop-engineering for complex tasks. PRD -> tagged phase plan -> autonomous TDD execution loop with deterministic escalation, command-based verification, and disk-backed state that survives compaction.
★not rated 1 2mo agoA
tokens not measured
originalMIT
Clear, action-first output for Claude Code. Lead with the point, explicit assumptions, literal language, complete detail, no filler - applied every turn by hooks.
★not rated 1 2mo agoA
tokens not measured
originalMIT
Long-term memory for Claude Code and Open Claw — stores notes as .md files with YAML frontmatter, syncs via GitHub, indexes via Neon Postgres. Progressive setup: works with just files, scales to full cross-machine sync.
★not rated 1 3mo agoA
tokens not measured
originalMIT
Skills da Imersão Founders AI (Paris Group) + método da sala: playbook → PRD com mapa de ondas → protótipo → onda 1 → publicar. Comandos /imersao:pg-imersao-.
★not rated 1 1mo agoA
tokens not measured
originalMIT
Your agent stopped. It was not finished. flipback reads the conversation, works out whether the work you asked for actually got done, and puts the agent back on when it did not.
★not rated 1 1mo agoA
tokens not measured
originalMIT
Scratch-notebook context management for any project: per-thread STATE.md handoff docs with one-command create-or-resume (/ccx:start-thread), a compiled parallel-session-safe INDEX dashboard that recompiles itself on every STATE write (/ccx:save-state · /ccx:tidy-scratch), a Stop-hook freshness guard so working state…
★not rated 1 2mo agoA
tokens not measured
originalMIT