agent-behavior

Standards for defining and evaluating agent behavior

Studying the gap between what agents know and when they act on it.

The senior dev, unbundled — ten opinionated skills that make an AI coding agent push back, verify, attack its own code, and finish like a senior engineer.

The meta layer behind AI skills. Persistent behavioral overlays that make expected agent conduct explicit across changing tasks and capabilities.

High-performance routing engine that selects the best agent skill for a task and emits structured handoff decisions.

Claude Code 插件 | Cursor 插件 | Trae 插件 | Codex 插件 — AI 智能体行为准则：请示报告、督促检查、信息服务。跨 Claude Code / Cursor / Codex / Trae 的 agent 工作纪律插件。

RL-style eval measuring intent/action divergence in frontier agents: model acknowledges a correction, then acts on the stale value anyway. 3 scenarios, 655 trials on claude-haiku-4-5, Sonnet 4.6, GPT-5.4, and Gemini 3.1 Pro Preview.

Reviews and modernizes stacks, packages, SDKs, and tooling before code is written against them.

Toy 7. An elimination-filter landscape applying two structural constraints simultaneously to map which objective classes can persist under sustained optimization pressure — and which cannot. Includes a four-stage scenario engine and open-question frontier. Companion simulation for The Shape of What Does Not End — Series 2, Part 4.

Produces auditable token-usage and cost reports from runtime evidence, normalized usage bundles, and repository-level report sets.

Toy 5. An interactive proxy decay simulator showing how optimization pressure erodes the modeling capacity required to distinguish proxy from territory — producing self-reinforcing V(t) degradation that becomes progressively harder to correct. Companion simulation for The Depth Constraint — Series 2, Part 2.

Execution layer for skill-dispatcher — runs multi-phase agent chains end-to-end with per-step telemetry and chain_id correlation

IAB — The First Workshop on Interpreting Agent Behavior @ NeurIPS 2026. Human-centered interpretation for understanding agents, humans, and interaction.

Persistent homology on agent behavior: TDA detects personality (long-lived features) vs noise (short-lived). Vietoris-Rips complexes, barcodes, Betti curves

Canonical home for AI Behavior Science research and the Founding Territory Paper

Audit and reduce YAML frontmatter bloat in AgentSkill SKILL.md files. Automates deduplication, flattening, and noise removal.

Agent authority guardrails for Claude Code & Grok — stop yield-back; drive reversible work yourself.

Agent cognitive guard that prevents blind debugging and premature optimization by enforcing reality validation before any code change. Compatible with OpenCode / OhMyOpenAgent and any platform supporting Skills.

A pressure-release valve for AI coding agents: agents vent friction to a structured log, an analyzer mines it for systemic fixable causes. Portable SKILL.md format - Claude Code, Hermes, Codex, Cursor.

Audits frontend implementations for design-system drift across CSS, Tailwind, JSX, TSX, Vue, and Angular code.