SearchSAFE
A complete starter kit for an Obsidian + Claude Code personal knowledge management system.
Overview
A complete starter kit for an Obsidian + Claude Code personal knowledge management system.
855f65f39078OBSERVED · 2026-10-08What it tells the agent
The instruction file, verbatim from the audited commit — this is the text the model reads, and the surface the audit's instruction layer examines. Quoted here so you can judge it without cloning anything.
--- name: search description: Search vault content by keyword using Grep. Zero dependencies — works in any vault without indexes or plugins. Groups results by directory for easy scanning. allowed-tools: Grep, Glob, Read user-invocable: true --- # Search Skill Fast keyword search across all vault markdown files using the Grep tool. No indexes, no plugins, no setup — just structured search with directory grouping. ## Usage ``` /search <term> ``` Examples: - `/search project planning` - `/search weekly review` - `/search TODO` ## How to Execute When the user invokes `/search <term>`: ### Step 1: Search for the term Use the **Grep** tool to search all `.md` files for the term: ``` Grep: pattern: <search term> glob: "*.md" output_mode: content -n: true -C: 1 ``` Exclude hidden directories (`.claude/`, `.obsidian/`) and templates: ``` Grep: pattern: <search term> glob: "*.md" path: . output_mode: content -n: true -C: 1 ``` Filter out results from `.claude/`, `.obsidian/`, and `Templates/` directories. ### Step 2: Group results by directory Organise matches into sections by their parent directory: - **Daily Notes/** — journal entries - **Goals/** — goal and vision documents - **Projects/** — project notes - **Archives/** — archived content - **Inbox/** — unprocessed items - **(root)** — top-level notes ### Step 3: Present results Format output as: ```markdown ## Search: "<term>" ### Daily Notes/ - **2024-01-15.md** (line 23): ...matching context... - **2024-01-14.md** (line 8): ...matching context... ### Projects/ - **Project Alpha.md** (line 45): ...matching context... ### Goals/ - **2024 Goals.md** (line 12): ...matching context... **Found X matches across Y files** ``` ### Step 4: Suggest related content After showing results, check if any matched files contain `[[wiki-links]]` to other notes. If so, briefly mention: ``` 💡 Related notes mentioned in results: [[Note A]], [[Note B]] ``` ## No Results If no matches are found: 1. Suggest alternative search terms (synonyms, related words) 2. Offer to search with case-insensitive matching if the original search was case-sensitive 3. Suggest checking `Archives/` if not already included ## Tips - Search is case-sensitive by default. Add `-i: true` to the Grep call for case-insensitive search - Use regex patterns for advanced searches: `task.*complete`, `#tag-name` - Combine with `/daily` to quickly find when something was mentioned
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | NA |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- none-observed
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (0)
No findings outside the package's declared scope.
Gates applied: no_behavioural_pass.
855f65f39078full audit observations/trust-audit/skill/ballred__search.json · Report an issue / request a re-scanAudit history
Every audit this skill has had.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-08 | 855f65f39078 | SAFE | B | 89 | first audit |
Questions
What does the Search skill do?
A complete starter kit for an Obsidian + Claude Code personal knowledge management system.
Is Search safe to install?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean skill reads B.
What can Search access on my machine?
The audit observed no filesystem, network or shell use at all in its source.
How current is this page?
The grade is for one exact copy of the source (855f65f39078), read on 2026-10-08. The repository is watched, and a new audit runs when it changes — this is the first audit.