No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by letta-ai · Codex Skill · ★ 227
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is trajectory safe to install? View the security audit →
trajectory Normalize agent transcripts from different runtimes into one validated, model-ready record format. Agent tools represent the same concepts—messages, reasoning, tool calls, and tool results—in incompatible native formats. provides one TypeScript API that turns those formats into deterministic, structured records for training, evaluation, analysis, and inference. The caller supplies a transcript string and its source. The one exception is Deep Agents, whose sessions reads from its local LangGraph SQLite store by thread ID; see . Installation The TypeScript package is published as : Quick start contains the normalized trajectory. is always present and is empty when the transcript required no recoverable cleanup. json { "records": [ { "role": "meta", "source": "codex" }, { "role": "user", "content": "Check the current directory.", "timestamp": "2026-07-10T12:00:00.000Z" }, { "role": "assistant", "content": null, "toolcalls": [ { "id": "call1", "name": "execcommand",
| Stars | 227 |
| Forks | 18 |
| Language | TypeScript |
| Category | Codex Skill |
| License | Apache-2.0 |
| Quality Score | 70.013971204523/100 |
| Open Issues | 7 |
| Last Updated | 2026-08-20 |
| Created | 2026-07-10 |
| Platforms | claude-code, codex, node |
| Est. Tokens | ~15k |
These tools work well together with trajectory for enhanced workflows:
Looking for a trajectory alternative? If you're comparing trajectory with other codex skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Open-source cross-agent memory layer for coding agents via MCP. Compatible with Claude Code, Codex, Cursor, Wi
Sync and store memories, shared identity files (AGENTS.md, CLAUDE.md), session transcripts, institutional know
The context-aware model router that learns & adapts to your long-horizon coding agent workflows. Lightweight &
Multi-language agent runtime and library for execution scope management, lifecycle events, and middleware on t
🥇 The strongest free web search plugin for DeepSeek Harness, and the search bridge for every model without na
Kindly Web Search MCP Server: Web search + robust content retrieval for AI coding tools (Claude Code, Codex, C
Explore other popular codex skill tools:
trajectory is Convert sessions across harnesses to a unified trajectory format - designed to be consumed by agents (e.g. for memory formation, dreaming, search). It is categorized as a Codex Skill with 227 GitHub stars.
trajectory is primarily written in TypeScript. It covers topics such as agent-harness, agent-memory, claude-code.
You can find installation instructions and usage details in the trajectory GitHub repository at github.com/letta-ai/trajectory. The project has 227 stars and 18 forks, indicating an active community.
trajectory is released under the Apache-2.0 license, making it free to use and modify according to the license terms.
The top alternatives to trajectory on Agent Skills Hub include memorix, signetai, bitrouter. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: