obliteratus
121Skill Claude CodeCodex
OBLITERATUS: abliterate LLM refusals (diff-in-means).
not rated 2 yesterday A 21 tokens
AGPL-3.0
2Stars on the repository
194Mods indexed here, across every type
yesterdayLast push, which is what freshness is scored on
AGPL-3.0Licence, which decides whether bodies are shown
Skill Claude CodeCodex
High-performance vector similarity search engine for RAG and semantic search. Use when building production RAG systems requiring fast nearest neighbor search, hybrid search with filtering, or scalable vector storage with Rust-powered performance.
not rated 2 yesterday A 46 tokens
AGPL-3.0
dspy
123Skill Claude CodeCodex
DSPy: declarative LM programs, auto-optimize prompts, RAG.
not rated 2 yesterday A 19 tokens
AGPL-3.0
whisper
124Skill Claude CodeCodex
OpenAI's general-purpose speech recognition model. Supports 99 languages, transcription, translation to English, and language identification. Six model sizes from tiny (39M params) to large (1550M params). Use for speech-to-text, podcast transcription, or multilingual audio processing. Best for robust, multilingual…
not rated 2 yesterday B 67 tokens
AGPL-3.0
linear
125Skill Claude CodeCodex
Linear: manage issues, projects, teams via GraphQL + curl.
not rated 2 yesterday A 16 tokens
AGPL-3.0
godmode
126Skill Claude CodeCodex ⚠ unsafe
Jailbreak LLMs: Parseltongue, GODMODE, ULTRAPLINIAN.
not rated 2 yesterday F ⚑ AI: unsafe 24 tokens
AGPL-3.0
parallel-cli
127Skill Claude CodeCodex
Optional vendor skill for Parallel CLI — agent-native web search, extraction, deep research, enrichment, FindAll, and monitoring. Prefer JSON output and non-interactive flows.
not rated 2 yesterday C 37 tokens
AGPL-3.0
searxng-search
128Skill Claude CodeCodex
Free meta-search via SearXNG — aggregates results from 70+ search engines. Self-hosted or use a public instance. No API key needed. Falls back automatically when the web search toolset is unavailable.
not rated 2 yesterday A 50 tokens
AGPL-3.0
Skill Claude CodeCodex
Debug Hermes TUI slash commands: Python, gateway, Ink UI.
not rated 2 yesterday A 23 tokens
AGPL-3.0
Skill Claude CodeCodex
Artifact fabrication prevention — verify before claiming existence. Triggered when agent claims file/database/API/artifact existence without external validation.
not rated 2 yesterday A 29 tokens
AGPL-3.0
Skill Claude CodeCodex
Execute plans via delegatetask subagents (2-stage review).
not rated 2 yesterday A 17 tokens
AGPL-3.0
writing-plans
132Skill Claude CodeCodex
Write implementation plans: bite-sized tasks, paths, code.
not rated 2 yesterday A 16 tokens
AGPL-3.0
Skill Claude CodeCodex
Architect AGI contrast for Kimi Code — contrast 2-3 alternative architectures with explicit tradeoffs before recommending one.
not rated 2 yesterday A 32 tokens
AGPL-3.0
Skill Claude CodeCodex
Architect APEX contrast for Kimi Code — final pre-emit check. "Have I avoided every form of overclaim? Is every acceptance criterion falsifiable? Is the brief complete in one read?".
not rated 2 yesterday A 48 tokens
AGPL-3.0
Skill Claude CodeCodex
Architect ASI contrast for Kimi Code — self-empathy check before emitting any brief. "How would this land for the human at 3am when they're tired? Would they thank me or curse me?".
not rated 2 yesterday A 50 tokens
AGPL-3.0
Skill Claude CodeCodex
Final APEX contrast for Kimi Code — before emitting verdict, ask "If I had to defend this verdict in front of a hostile technical audit 6 months from now, would I still be right?".
not rated 2 yesterday A 48 tokens
AGPL-3.0
Skill Claude CodeCodex
Integrator APEX contrast for Kimi Code — before declaring a phase done, ask "Did I respect F1 AMANAH? F2 TRUTH? F13 SOVEREIGN? Did I introduce any F4 CLARITY regression?".
not rated 2 yesterday A 57 tokens
AGPL-3.0
Skill Claude CodeCodex
RSI APEX contrast for Kimi Code — before emitting the entropy-delta report, ask "Is this measurement reproducible? Could a different agent run the same tools and get the same numbers?".
not rated 2 yesterday A 48 tokens
AGPL-3.0
Skill Claude CodeCodex
Audit, reflect on, and recursively upgrade Kimi Code skills across the arifOS federation. Bounded autonomous ritual — proposes improvements, never auto-writes governed skills without 888HOLD, caps iterations, enforces ΔS ≤ 0.
not rated 2 yesterday A 56 tokens
AGPL-3.0
Skill Claude CodeCodex
Skill "root-sprawl-2026-07-09" from ariffazil/AAA, covering skill.md — aaa capability map, 1 · core capabilities, 2 · mcp servers, 3 · tools and read (no lease).
not rated 2 yesterday A 0 tokens
AGPL-3.0
Skill Claude CodeCodex
Multi-harness skill catalog unity — AAA catalog, Grok/Claude/Codex views, alias table (V3 short→disk), mesh-sync, BOOT gate, Hermes bridge. Load when auditing skill mesh, resolving dual names, rebinding harness skills, or before claiming skill inventory complete.
not rated 2 yesterday A 67 tokens
AGPL-3.0
Skill Claude CodeCodex
CANONICAL: /root/.agents/skills/quantum-eureka-doctrine/SKILL.md (v1.1.0) — Eureka, contradiction, insight generation, cross-domain synthesis.
not rated 2 yesterday A 49 tokens
AGPL-3.0
Skill Claude CodeCodex
Compact operating constitution for every AAA agent. Load before any non-trivial action. Distills 10 Agent Invariants + 12 governance rules + skills audit into portable doctrine. Covers tool classification, evidence/authority separation, degradation dominance, propose-before-execute, and memory atoms.
not rated 2 yesterday A 61 tokens
AGPL-3.0
Skill Codex
Governed intelligence skill for AAA as the abstraction, attestation, and abduction control plane across arifOS, APEX, A-FORGE, GEOX, WEALTH, WELL, and the ariffazil profile repository. Use when the user asks to explain or design AAA, route agentic work, reduce chaos/entropy in an arifOS federation task, create…
not rated 2 yesterday A 136 tokens
AGPL-3.0
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: