Quality record

Know what you are installing.

Version, date and limits are read from the repo on every sync, and the check runs every night. Real-world runs are listed only with their evidence.

Version: Unversionedcommit 1bfa2a7
Updated: 31 Oct 2026last commit to the repo
Works in: Claude Code, Codex, Cursor, Qoder and any agent that loads a SKILL.mdplain text; no API keys
Nightly check: Not checked yetIt joins the nightly check after its first run. How it is checked
Last real-world run: No public run yetRuns are published only with their evidence.
Known limits: Not built for:
Searching code or project files (use Grep)
Summarizing the conversation already open, or durable project memory (use the workspace memory index)

What it is for

Find a past AI coding conversation from a fuzzy memory — "the session where we fixed the redirect" — across Qoder, Claude Code, Codex and Gemini CLI. Searches the transcript files those tools already keep on disk, ranks sessions with verbatim evidence and a session ID, then prints the chosen chat.

Reach for it when

The user cannot find an earlier session, asks which chat covered something, asks to search past sessions or conversation history, or wants to reopen a conversation from a rough recollection.

Not for

Searching code or project files (use Grep)
Summarizing the conversation already open, or durable project memory (use the workspace memory index)

Every file it installs

Measured from the packed archive at commit 1bfa2a7. A skill is plain text your agent reads, so this list is all of it.

File	Lines	Bytes
SKILL.md	54	4,744 B
references/test-cases.md	34	3,677 B
references/transcript-format.md	74	6,242 B
scripts/session_retrace.py	642	24,313 B
4 files	804	12 KB

Session Retrace

Know what you are installing.

What it is for

Reach for it when

Not for

Every file it installs

More in Build & Ship