.agents/skills/session-recall/SKILL.md
Recover and summarize prior Codex conversations from local Codex history and session logs. Use when the user asks what happened in a previous chat, asks to "remember" past work, wants the last or previous session, gives a specific date or approximate time, wants to search old dialogs by keyword/topic/project, or asks to inspect Codex files/config for prior conversation context.
npx skillsauth add kissrosecicd-hub/agents-evolution session-recallInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Use local Codex logs instead of claimed model memory. Base the answer only on files found under CODEX_HOME_DIR="${CODEX_HOME:-$HOME/.codex}".
$CODEX_HOME_DIR/history.jsonl: fastest way to see recent user messages and map them to session_id$CODEX_HOME_DIR/session_index.jsonl: thread names and timestamps$CODEX_HOME_DIR/sessions/YYYY/MM/DD/*.jsonl: full session transcripts$CODEX_HOME_DIR/archived_sessions/*.jsonl: fallback for older moved sessionsTreat config.toml, state_*.sqlite, and logs_*.sqlite as fallback only. Conversation recall should usually come from history.jsonl and sessions/.../*.jsonl.
last, previous, specific date, date plus approximate time, keyword, project path, or session id.history.jsonl to find candidate session_id values and the user's own wording.sessions/.../*.jsonl file to reconstruct the conversation.Use:
CODEX_HOME_DIR="${CODEX_HOME:-$HOME/.codex}"
tail -n 40 "$CODEX_HOME_DIR/history.jsonl"
ls -1t "$CODEX_HOME_DIR"/sessions/*/*/*/*.jsonl 2>/dev/null | head -10
If the user asks for the previous session while already in a new chat, do not return the current session. Pick the most recent distinct earlier session_id.
Use the exact calendar date, not relative wording:
CODEX_HOME_DIR="${CODEX_HOME:-$HOME/.codex}"
ls -1 "$CODEX_HOME_DIR/sessions/YYYY/MM/DD"/*.jsonl 2>/dev/null
rg -n 'YYYY-MM-DD|keyword|session_id' "$CODEX_HOME_DIR/history.jsonl"
If the user says "yesterday" or "that day", convert it to an absolute date in the answer.
List that day's session files and choose the nearest timestamp:
CODEX_HOME_DIR="${CODEX_HOME:-$HOME/.codex}"
ls -1 "$CODEX_HOME_DIR/sessions/YYYY/MM/DD"/*.jsonl
Then open the closest candidate and verify by reading nearby user messages.
Search both the lightweight index and the full transcripts:
CODEX_HOME_DIR="${CODEX_HOME:-$HOME/.codex}"
rg -n 'CAMvisualD|virtual camera|docker|build|mic' \
"$CODEX_HOME_DIR/history.jsonl" \
"$CODEX_HOME_DIR/sessions" \
"$CODEX_HOME_DIR/archived_sessions"
Prefer the user's own exact phrase first, then broaden the search if needed.
When a session_id is already known, resolve it directly:
CODEX_HOME_DIR="${CODEX_HOME:-$HOME/.codex}"
find "$CODEX_HOME_DIR/sessions" "$CODEX_HOME_DIR/archived_sessions" \
-type f -name '*session-id-fragment*.jsonl' 2>/dev/null
history.jsonl for quick mapping, not as the sole source for a full recap.Keep the answer short and concrete:
CODEX_HOME_DIR="${CODEX_HOME:-$HOME/.codex}"
tail -n 40 "$CODEX_HOME_DIR/history.jsonl"
tail -n 20 "$CODEX_HOME_DIR/session_index.jsonl"
ls -1t "$CODEX_HOME_DIR"/sessions/*/*/*/*.jsonl 2>/dev/null | head -10
rg -n 'keyword' "$CODEX_HOME_DIR/history.jsonl" "$CODEX_HOME_DIR/sessions" "$CODEX_HOME_DIR/archived_sessions"
sed -n '1,120p' /path/to/session.jsonl
tail -n 120 /path/to/session.jsonl
tools
KISS reference skill for v2rayA on Arch/Ubuntu/Fedora with TUN, RoutingA, DoH DNS and Outline key import.
testing
Identifies dependencies at heightened risk of exploitation or takeover. Use when assessing supply chain attack surface, evaluating dependency health, or scoping security engagements.
development
Run Semgrep static analysis scan on a codebase using parallel subagents. Supports two scan modes — "run all" (full ruleset coverage) and "important only" (high-confidence security vulnerabilities). Automatically detects and uses Semgrep Pro for cross-file taint analysis when available. Use when asked to scan code for vulnerabilities, run a security audit with Semgrep, find bugs, or perform static analysis. Spawns parallel workers for multi-language codebases.
development
Identifies error-prone APIs, dangerous configurations, and footgun designs that enable security mistakes. Use when reviewing API designs, configuration schemas, cryptographic library ergonomics, or evaluating whether code follows 'secure by default' and 'pit of success' principles. Triggers: footgun, misuse-resistant, secure defaults, API usability, dangerous configuration.