agent-handoff
agent-handoff is a Session continuity & handoff skill for AI agents, published by WeirdSky924 in the agent-handoff-skill repository on GitHub. Skillspace rates agent-handoff B (81/100) and it passed the safety scan; the rating is based on static analysis only.
Cross-platform Codex and Claude Code skill for creating, updating, repairing, or reviewing durable repository handoff mechanisms. Supports single-document and multi-document layouts. Use when the user asks to bootstrap cross-session project memory, create or maintain AGENT_HANDOFF.md and .agent-handoff state files, add Codex AGENTS.md rules, add Claude Code .claude/CLAUDE.md rules, create reusable session prompts, install optional Claude Code advisory hooks, enforce closeout, repair stale handoff state, or review handoff quality. Install under ~/.codex/skills/agent-handoff for Codex, ~/.claude/skills/agent-handoff for Claude Code personal use, or repo/.claude/skills/agent-handoff for Claude Code project use.
- Grade
- B
- Quality
- 81 / 100
- Safety
- Passed
- GitHub stars
- 23
Unproven: rated by static analysis only, not yet compared head-to-head.
This rating describes the version of the repository we crawled; it may have changed since, so go by its current files.
Our review
- Architecture
- 100 / 100
- Maturity
- Structured: ships references or scripts
- Security scan
- No issues found
- License
- Not declared. Check the repository before reusing it.
- Adoption
- Adopted by 0 other repositories, in 0 collections
Not checked yet
- Not judged on the rubric yet (not a contender in its category)
- No blind task eval yet
- Scope (portable / vendor / repo-internal) not assessed; only the top of each category is read for scope
- Sibling files (scripts, references) not fetched; security scan covers SKILL.md only
Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.