End-of-session wrap-up: detects what changed, updates CLAUDE.md with gotchas only, runs tests, commits only this session's files (creating a repo with a secret check for new projects), and prints a short status report.
Plugin done from marketplace efi-skills in EfiPerez/claude-code-skills. Commands read from the repo's manifest — 8 days ago.
codec-buildHands a frozen spec to a second model to IMPLEMENT, then runs a bounded review-and-fix loop between Claude and OpenAI Codex over the resulting diff. Claude picks the topology (Codex builds by default; a Sonnet subagent builds when the main context needs protecting), enforces a clean-tree or snapshot
codec-reviewRuns a bounded adversarial review loop between Claude (builder and arbiter) and OpenAI Codex (newest GPT Sol model, read-only critic) over a document or codebase. Codex attacks the work and returns a structured verdict; Claude judges each finding, rewrites the target, and re-submits to the SAME Code
doneEnd-of-session wrap-up skill. Run at the end of every working session to: summarize what changed, update any affected CLAUDE.md sections, run the project's test suite (if one exists), commit and push to git, and print a final status report. Trigger this skill whenever the user types /done, says "wra
handoffCompresses the current session's context, progress, and next steps into a Markdown file in the project's handoffs/ folder, so a future Claude Code session can resume exactly where this one stopped. Trigger this skill whenever the user types /handoff, or says "write a handoff", "hand off to the next
resume-handoffLoads the most recent session handoff document from the project's handoffs/ folder, reads the files it points at, checks whether anything has changed since it was written, and reports where the last session stopped so work can continue seamlessly. Trigger this skill whenever the user types /resume-h
Adversarial review and build loops between Claude and OpenAI Codex: codec-review has Codex critique a plan or codebase read-only while Claude judges and rewrites; codec-build hands a frozen spec to a second model to implement, then runs a bounded review-and-fix loop over the diff. Needs the Codex CLI and codex login; without them, an opt-in same-family mode uses a different Claude model as the critic (weaker, still independent). Windows and macOS (macOS untested).
5 skills
Save an unfinished session to a handoffs/ Markdown file (handoff) and pick it back up in a fresh session, with drift checks against the current code (resume-handoff).
5 skills
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
15 skills · hooks
Persistent memory for Claude Code: the next session starts where the last one left off.
29 skills · 1 MCP server · hooks
Cross-session memory and token savings for coding agents.
6 skills · 1 agent · 1 MCP server · hooks
Perform AI code review on Git diffs — supports workspace changes, branch ranges, and single commits with concurrent per-file analysis, codebase search, and deep context-aware review.
2 commands
Backend API design, GraphQL architecture, workflow orchestration with Temporal, and test-driven backend development
9 skills · 1 command · 8 agents
Persistent memory for AI coding agents -- captures tool usage, compresses via LLM, injects context into future sessions
17 skills · 1 MCP server · hooks
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.