Continuous self-referential AI loops for interactive iterative development, implementing the Ralph Wiggum technique. Run Claude in a while-true loop with the same prompt until task completion.
★not rated 30 todayA
tokens not measured
copy · 100%MIT
v9.29.2 — Model defaults refreshed: Opus 4.7 for planning/strategy/security-review, GPT-5.4 for code-review/implementation. New GPT-5.4 prompting guide. Set OCTOPUSLEGACYROLES=1 to opt out. Run /octo:setup.
★not rated 31 3mo agoA
tokens not measured
originalMIT
Open-source intelligence tradecraft for agents: 29 investigation workflows covering people, companies, domains, images, phones, emails, usernames, crypto and vessels. Every workflow sets an authorised scope before collecting, sources each claim independently, and grades identity attribution separately from the claim…
★not rated 29 1mo agoA
tokens not measured
originalMIT
Unity-aware AI infrastructure for Claude Code: a queryable knowledge graph of your Unity project, plus observability, project memory, and 22 skills. Connects to the standalone Hades macOS app, which serves 32 MCP tools.
★not rated 27 yesterdayA
tokens not measured
originalMIT
A contract-law add-on for Russian commercial agreements, including non-disclosure, services, supply, lease, and licence contracts. It cites the Russian Civil Code, marks risks by red, yellow, or green status, and checks mandatory rules and court practice.
Tool-agnostic agentic coding setup: 30 agents, 55 skills, 74 rules, 33 commands, 7 hooks, MCP servers, and a CLI-tool surface generated for 3 AI coding tools from a single canonical source. Counts derived from governance/inventory.json.
★not rated 26 7d agoA
tokens not measured
originalMIT
Embedded debugging on real hardware through SEGGER J-Link, OpenOCD, and Black Magic probes. Skills for crash diagnosis, hangs, peripheral inspection, and RTT — including loading ELF symbols for source-level backtraces and SVD files for named peripheral fields.
★not rated 27▲
+1 7d agoA
tokens not measured
originalMIT
Plan iron, verify real. Ironclad planning with independent verification chain. Turns any input into a bulletproof plan, executes with TDD, verifies with independent agents.
★not rated 25 1mo agoA
tokens not measured
originalMIT
v0.4.1 — Portable execution playbook for Claude Code with three pilot modes: Haiku Pilot (cost-first default, 70–85% savings, 7-step pre-flight incl. Source-Verify + hard-task anchor ≥5), Sonnet Pilot (quality-first, 55–65% savings, 7-step pre-flight incl. Line-Level Source-Verify + hard-task auto-escalate gate), and…
★not rated 24 3mo agoA
tokens not measured
originalMIT
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: