session-index — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited session-index (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
You have access to a session index — a SQLite database with FTS5 full-text search across all Claude Code sessions. Use it whenever the user asks about past sessions, previous conversations, or wants to know what they've tried before.
The user's interface is this conversation. They ask naturally ("Didn't we discuss browser control recently?"), you translate to CLI commands, and present results conversationally. They should never need to know the CLI syntax.
The user says: "Didn't we discuss browser control recently?" You search: sessions "browser control"
The user says: "What approaches have I tried for form automation?" You search: sessions "form automation"
The user says: "How much time did I spend on Acme this week?" You run: sessions analytics --client "Acme" --week
Search — find sessions by topic:
sessions "relevant keywords"
sessions "relevant keywords" --context # includes conversation excerptsContext — read the actual conversation from a session:
sessions context <session_id> "search term" # exchanges matching a term
sessions context <session_id> # all exchangesAnalytics — effort, time, tool usage:
sessions analytics # overall
sessions analytics --client "Acme" # per client
sessions analytics --week # this week
sessions analytics --month # this monthFilter — find sessions by metadata:
sessions find --client "Acme" # by client
sessions find --tool Task --week # by tool + date
sessions find --project myapp # by project
sessions recent 20 # last N sessionsThis is the most valuable capability. When the user asks a question that spans multiple sessions:
sessions "topic" -n 10sessions context <id> "topic" -n 3model="haiku" to synthesize:claude --resume <id> links for each source sessionThis uses an in-session Haiku subagent — no external API key needed.
Don't dump raw CLI output. Summarize:
claude --resume <session_id> links so they can jump back inpip install claude-session-indexFirst run of any command auto-indexes all existing sessions.
~/.session-index/sessions.db~/.claude/session-topics/~/.session-index/config.json (optional)~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.