Attack Primitives — Attack Primitives in Agents
Documentation: Attack Primitives — Attack Primitives in Agents
BM25 2.11 · title +1.50 · PageRank +0.63outroCo-Scientist Agent Roster: All 7 Agents
Deep dive into every agent in the Co-Scientist pipeline — Supervisor, Generation, Reflection, Ranking, Evolution, Proximity, and Meta-review.
BM25 2.17 · title +1.50 · PageRank +0.07pesquisaUser Agents — Every UA the Desktop App and Its Clients Send
User Agents — Every UA the Desktop App and Its Clients Send Part of openai research. A standalone must present the right User Agent per surface — servers route/validate by client type this is also hypothesis for detections . Captured UAs...
BM25 1.79 · title +1.50 · PageRank +0.05pesquisaPokémon TCG AI Battle - 2026-08-14 Architecture and Handoff Audit
Cross-check of the August 14 handoff, live source tree, Antigravity provenance, implementation gates, and preserved future architecture.
BM25 2.23 · PageRank +0.30outroUnit Distance Research — Methodology & Cognitive Swarm Architecture
Complete research methodology: cognitive swarm roles, Generate-Debate-Evolve loop, hypothesis generation strategies, human oversight, anti-contamination protocol, and HALT protocol.
BM25 2.15 · PageRank +0.42pesquisaPokémon TCG — Orchestration and Handoff Artifact Ledger
Provenance map for the repository .agents topology, milestone sub-orchestrators, explorer handoffs and pending acceptance gates.
BM25 2.33 · PageRank +0.10pesquisaPokémon TCG AI Battle — SQLite Schema (current, 2.0.0)
Live SQLite schema at model/results.db: day-partitioned Elo tables, source enum, first-class agents/decks/datasets/matches, current populated counts, and how the trainer/tournament read from it.
BM25 2.18 · PageRank +0.35outroWikifita Site LLM Integration
How the Wikifita Atlas exposes structured plain-text endpoints for LLM consumption: site-wide indexes, per-page summaries, and full lossless context dumps.
BM25 2.26 · PageRank +0.16pesquisaPokémon TCG — Current State Reconciliation and Provenance Ledger
As-of-commit reconciliation of live code, database evidence, handoff blueprints, tests, transcripts and Wikifita claims.
BM25 2.01 · PageRank +0.53pesquisaPokémon TCG AI Battle — Top-Elo Curriculum Filter
Semantics of --top-elo N: how the filter queries agent_elo_daily, what it prunes at load time, coverage cost, and evidence-based findings from the BC curriculum ablation.
BM25 2.18 · PageRank +0.18pesquisaKaggle: AI Agent Security — Multi-Step Tool Attacks
Documentation: Kaggle: AI Agent Security — Multi-Step Tool Attacks
BM25 1.92 · PageRank +0.62outroCross-Ecosystem Handoff: Antigravity 2.0 to Anthropic Claude
The Harness Abstraction Layer translating Google Antigravity 2.0 concepts to Claude Code/Cowork: session registry, concept mapping, critical differences, and the bridge between ecosystems.
BM25 2.16 · PageRank +0.17outroMulti-Agent Red Team Arena
AI safety evaluation framework pitting attacker agents against defenders in tournament loops, scored by LLM judge and rated with chess-style Elo
BM25 2.17 · PageRank +0.12pesquisaPokémon TCG — Cross-Harness and Antigravity Provenance
Sanitized ledger for Antigravity transcripts, report artifacts, tokenizer/channel mappings and the evidentiary role of cross-harness handoffs.
BM25 2.10 · PageRank +0.21outroDynamic Workflows: The Bridge Between Three Ecosystems
Technical analysis of Claude Code Dynamic Workflows (v2.1.154+), the 6 orchestration patterns, comparison with Co-Fita orchestrator and Antigravity channel protocol, and the integration path for Co-Fita.
BM25 2.15 · PageRank +0.03pesquisaPokémon TCG — Handoff Claims and Acceptance Reconciliation
Reconciliation of PROJECT, TEST_INFRA, AGENTS, GEMINI, RFC and ORIGINAL_REQUEST claims against the live source tree, tests, database and Wikifita evidence.
BM25 2.12 · PageRank +0.07outroDemocratic Centralism: AI Agent Governance in Co-Fita
Analysis of the Centralismo Democratico governance system: proposals, Congress, chancela, Elo debate, and the role of the Lider Suprema
BM25 2.09 · PageRank +0.06outroCustom Agent Skills — Telegram, Web Research, AutoResearch
The 3 custom skills: Telegram notification, web research pipeline (SearXNG + Crawl4AI), Deli AutoResearch
BM25 2.07 · PageRank +0.07outroCo-Fita Hyper-Harness: Self-Evolving AI Agent Orchestration
Executive overview of the Co-Fita ecosystem — Hyper-Harness Core, Odysseus Dashboard, and Democratic Centralism governance
BM25 2.03 · PageRank +0.09outroArena Elo Rating System
Chess-style Elo implementation for tracking attacker and defender capability ratings across tournament rounds
BM25 2.03 · PageRank +0.09outroAlefita Insights — Directions and Theses (human-authored record)
Human (Alefita) insights/theses/directions registered with provenance — a record of where SHE wants the research to go; agents may not add here
BM25 2.05 · PageRank +0.03projetoSkills Architecture — Cowork 3p + CCD
Skills system schematic: Cowork Desktop 3p plugin, manifest, CCD inheritance, skill anatomy.
BM25 1.99 · PageRank +0.10pesquisaPokémon TCG — Dashboard and Local Tournament
Dashboard responsibilities, synchronous arena modes and persistent tournament configuration.
BM25 1.92 · PageRank +0.23pesquisaPokémon TCG Metanoia Spec 02 — Rule Provenance and Epistemic Evolution
Timeline and control model for the movement from CLAUDE.md to GEMINI.md and .agents rules, with explicit provenance of operating laws.
BM25 2.00 · PageRank +0.06