Agent skill · mblode
chat-history
Recovers decisions, previous fixes, research, and subsequent actions from past AI conversations. Use when asked to "search past chats", "we fixed this before", "what followed this prompt", "why did the plan change", or use Claude Code Search for historical context. Supports local Claude Code, Codex, Grok, Cursor, and explicit ChatGPT or Claude exports.
What it needs
About 4k tokens when loaded.
What this skill does
Chat History IS: recover historical context with source evidence: prior fixes, decision trails, exact passages and what followed, research across sessions. IS NOT: browsing history, automatic memory writing, or proof of current repository or production state. For Obsidian notes use obsidian; for recent computer activity use an available computer-history capability. Agent compatibility The same skill and bundled script run in Codex, Grok, Cursor, and Claude Code. The model does not select the source adapter: every host can search every accessible supported source. No vendor SDK, host-specific tool names, or Claude-only substitutions are required. Read host setup when installing, moving between hosts, or diagnosing unavailable tools. Workflow 1. Discover available evidence. Resolve scripts/history.py relative to this installed SKILL.md, then execute it with python3. Run discover to report local source paths. Use explicit exports for web conversations; local Codex sessions do not include ChatGPT web history. Missing access is a coverage gap, not an empty search result. 2. Search narrowly, widen deliberately. Choose distinctive terms from the user's defect, artifact, project, or quoted passage. Start with known project/session paths; for cross-project research search the selected source roots. Batch spelling variants with repeated -e flags. Search results are literal OR matches in encounter order, not exhaustive or relevance-ranked when capped. Search both user and assistant messages; use --role user to locate the original request. Read source adapters when choosing paths, using Cursor/exports, or handling unsupported formats. 3. Read the sequence. Use each hit's path and line/key to read surrounding turns. Follow later corrections, linked sessions, commits, plans, and artifacts when they affect the answer. For "what followed", include assistant and tool evidence after the exact occurrence. A final summary alone may conceal scope changes. …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills mblode/chat-history