maintain — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited maintain (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.
Markdown is the source of truth; the search index and the generated views are disposable and rebuilt from it. This skill keeps them in sync and surfaces drift.
add_entry).reindex MCP tool rebuilds search from themarkdown sources. (CLI: ai-journal-mcp reindex <paths...> --db <path>.) The index is disposable — rebuild anytime, it changes no source data.
ai-journal-mcp refresh <root>regenerates JOURNAL.md and themes/. It also rescues any dated entry a stale session appended directly to JOURNAL.md — saving it as a real entry before regenerating, so no text is lost.
list_themes and entries_over_time (MCP) show the shapeand spot gaps such as (unthemed) entries. ai-journal-mcp scan <root> (CLI) reports orphan files with no dated entries and duplicate groups.
JOURNAL.md, themes/*.md) are never hand-edited — editsgo in the entry files, then regenerate.
indexed-mode journals are read-only; maintenance never rewrites them.~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.