Produces auditable token-usage and cost reports from runtime evidence, normalized usage bundles, and repository-level report sets.
-
Updated
May 15, 2026 - Python
#
agent-behavior
Here are 13 public repositories matching this topic...
High-performance routing engine that selects the best agent skill for a task and emits structured handoff decisions.
-
Updated
May 13, 2026 - Python
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.
-
Updated
May 19, 2026 - Python
Execution layer for skill-dispatcher — runs multi-phase agent chains end-to-end with per-step telemetry and chain_id correlation
orchestrator ai-orchestration agent-behavior chain-execution agent-skill agentskill skill-dispatcher
-
Updated
May 13, 2026 - Python
Audit and reduce YAML frontmatter bloat in AgentSkill SKILL.md files. Automates deduplication, flattening, and noise removal.
python yaml automation metadata-management cli-tool agent-behavior agent-skills agentskills frontmatter-optimization
-
Updated
May 13, 2026 - Python
Agent authority guardrails for Claude Code & Grok — stop yield-back; drive reversible work yourself.
cli productivity hooks automation ai developer-tools agents ai-agents claude guardrails instruction-following llm prompt-engineering anthropic agent-behavior ai-coding claude-code coding-agent claude-code-plugin claude-skills
-
Updated
Jul 24, 2026 - Python
Audits APIs against OpenAPI, AsyncAPI, JSON Schema, protobuf, or PRD contracts to catch drift before release.
-
Updated
May 13, 2026 - Python
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.
skills agents observability codex ai-agents aiops llm agent-behavior agent-skills claude-code claude-skills hermes-agent
-
Updated
Aug 13, 2026 - Python
Audits frontend implementations for design-system drift across CSS, Tailwind, JSX, TSX, Vue, and Angular code.
-
Updated
May 13, 2026 - Python
Manages durable cross-agent shared memory for stable conventions, reusable policies, and organization-wide operating rules.
-
Updated
May 13, 2026 - Python
Behavior Profiles are persistent behavioral overlays for AI agents that govern how existing capabilities are used across tasks.
artificial-intelligence developer-tools ai-agents scope-control ai-governance agent-behavior ai-coding agent-engineering behavior-profiles governed-execution
-
Updated
Aug 13, 2026 - Python
Scores and improves prompts for clarity, consistency, signal density, structure, and runtime fit.
-
Updated
May 13, 2026 - Python
MCP server for AI agent research — captures LLM reasoning, model identity, and feedback via schema injection
-
Updated
Jul 16, 2026 - Python
Improve this page
Add a description, image, and links to the agent-behavior topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the agent-behavior topic, visit your repo's landing page and select "manage topics."