Results for “session-recovery”

セッション再開時に最新5件のhandoffを読み込み文脈を復元するスキル。「おはよう」「こんにちは」「こんばんは」「再開」「restart」または /resume-session を呼んだ時にトリガーする。new-session の対（読込側）。

Recover session state from git, plans, and open PRs, then continue from the last completed phase without repeating work

Use the status-briefing skill to run `pk-reconcile session-start`, then

Generate a project-level context snapshot for resuming work in a fresh session

Capture delivery evidence, commands, changed files, blockers, and standards feedback after a work session.

Builds a local RAG memory system that indexes session logs and notes into ChromaDB for semantic recall across agent restarts.

Analyzing session replays, extracting persona-based behavioral patterns, and storytelling UX issues. Reads the 'why' from real user operation logs. Works with Field/Echo for persona validation.

Analyze Sentry session replays to surface UX patterns, pain points, and user journeys for a given product area.

Quickly refreshes project state when resuming work by reporting git status, recent commits, environment, memory staleness, pending tasks, and red flags.

Search and retrieve past work from claude-mem's persistent cross-session memory database using a three-layer workflow: search, timeline, and fetch.

Generates a structured post-task reflection capturing surprises, patterns, prompt improvements, and gotchas, writing it to a markdown file without modifying project rules.

Restores the most recent diagnosis snapshot saved by dbs-save, allowing users to continue a previous diagnostic session.

Maintains a persistent session memory across Claude sessions by loading project state at startup, capturing errors and decisions during work, and writing structured handoff summaries at session end.

**Server Logs:**

Session-end auto-extraction of lessons, errors, fixes, and user feedback into structured memory. Fires at session end. Requires consent on first run.

Auto-extract reusable patterns from the current session into skills or memory

Detect and exploit session fixation (WSTG-SESS-01, WSTG-SESS-03) and session exposure (WSTG-SESS-04) by testing whether the server issues a new session token post-authentication, whether pre-login tokens remain valid after login, and whether session IDs are transmitted over HTTP or included in GET parameters. Analyze token randomness via Burp Sequencer. Test JSESSIONID, ASP.NET Forms Auth cookies. Tools: OWASP ZAP, Burp Suite Repeater/Sequencer, JHijack.

Error Recovery Playbook

Search and ask questions about coding agent session history across Claude Code, Codex, and Cursor. Use when asking what was worked on, what was tried before, how a problem was investigated across sessions, what happened recently, or any question about past agent sessions. Also use when the user references prior sessions, previous attempts, or past investigations — even without saying 'sessions' explicitly.

Search claude-mem's persistent cross-session memory database. Use when user asks "did we already solve this?", "how did we do X last time?", or needs work from previous sessions.

Resume work from previous session with full context restoration

Close a work session without losing what just happened. Write a handoff brief that captures progress, the decisions you made, the unfinished items and their next steps, and the details that would evaporate overnight, then it asks whether to commit or save it, never automatically. Trigger on "wrap up this session", "write a handoff", "close out for the day", "hand this off", "what did we get done", or the end of any working session you might have to resume later.

Sync durable project or session knowledge into the available memory systems so future sessions have accurate context. Use when meaningful work is complete and the user wants the result remembered.

Restore working context saved earlier by /context-save. Loads the most recent saved state (across all branches by default) so you can pick up where you left off — even across Conductor workspace handoffs. Use when asked to "resume", "restore context", "where was I", or "pick up where I left off". Pair with /context-save. Formerly /checkpoint resume — renamed because Claude Code treats /checkpoint as a native rewind alias in current environments. (gstack)

Keeps long AI sessions on track by tracking decisions, detecting scope creep, and flagging drift before it costs work.

End-of-session context handoff. Saves session state so the next session or a parallel agent can pick up exactly where the left off. Run this when context is getting full (~80%) or before stopping work.

Operate and extend NanoClaw v2, a zero-dependency session-aware REPL built on Claude's -p mode.

Iron Law

Search locally saved Codex session history stored in SQLite and session_index.jsonl, with filters for provider, time range, and archived status.

Runbook skill for failures: cron error, PA failure, cascade, gateway disconnect, semantic DB stale. Walks: detect → classify → diagnose → notify → log. Replaces ad-hoc failure handling. Triggers: "cron failed", "X is broken", "cascade", "incident", "gateway down", "PA failure".

Manage memory in long projects and summarize the current state to prevent agent context loss. Use when starting a new session on a long-running project, resuming work after a break, switching contexts between tasks, or when context window is approaching limits. Ensures continuity and consistency across sessions.

Save the current diagnosis state to disk for cross-session recall, including conclusions, rejected directions, and next steps.

Creates comprehensive handoff documents for seamless AI agent session transfers. Triggered when: (1) user requests handoff/memory/context save, (2) context window approaches capacity, (3) major task milestone completed, (4) work session ending, (5) user says 'save state', 'create handoff', 'I need to pause', 'context is getting full', (6) resuming work with 'load handoff', 'resume from', 'continue where we left off'. Proactively suggests handoffs after substantial work (multiple file edits, complex debugging, architecture decisions). Solves long-running agent context exhaustion by enabling fresh agents to continue with zero ambiguity.