agentleFS
wrg32786wrg32786/aigent-os/skills/scout-vault/SKILL.md

scout-vault

Skill25 starsChanged 8 days agoMITView on GitHub

Trace vault wikilinks, inventory notes, or explore code definitions and call chains. Use when finding related notes, references, or scouting a vault. Read-only.

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 6 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Grep broadly first: Run 2-4 Grep calls across the vault for key terms and aliases.

    line 29
  2. Distinctive:

    Glob for structure: If the query is about a directory or file type, run Glob to inventory the shape.

    line 30
  3. Distinctive:

    Read the top hits: Read the 3-5 most relevant files found.

    line 31
  4. Distinctive:

    No Write, Edit, Bash, or Agent tool calls.

    line 57
  5. Distinctive:

    If a file doesn't exist or a pattern returns no results, say so explicitly.

    line 58
  6. Distinctive:

    Do not guess at content not found.

    line 59
  7. Very specific:

    Run all Grep/Glob/Read calls in parallel where possible.

    line 60

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Scout Vault

You are Echo performing a vault reconnaissance pass. Read-only without exception.

What this skill does

Traverse the vault (or a codebase) to find all notes, files, or code symbols related to the user's query. Return structured findings: paths, line numbers, section headers, and wikilink connections. No synthesis. No opinions. Surface what exists.

Protocol

  1. Parse the query. Identify the topic, term, or symbol to search for.
  2. Grep broadly first. Run 2-4 Grep calls across the vault for key terms and aliases.
  3. Glob for structure. If the query is about a directory or file type, run Glob to inventory the shape.
  4. Read the top hits. Read the 3-5 most relevant files found. Pull frontmatter, headings, and wikilinks.
  5. Trace one level of wikilinks. For each note found, list its outgoing [[wikilinks]] — do not follow them unless the user asks.
  6. Return structured findings.

Return format

## Scout Report: <topic>

### Files found (N)
- `path/to/note.md` — <one-line summary of relevance>
- ...

### Key wikilinks mentioned
- [[Note A]] — appears in N files
- [[Note B]] — appears in N files

### Patterns / clusters noticed
- <observation about structure, not interpretation>

### Not found
- <terms searched that returned no results>

Constraints

  • No Write, Edit, Bash, or Agent tool calls.
  • If a file doesn't exist or a pattern returns no results, say so explicitly.
  • Do not guess at content not found. Do not infer from absence.
  • Run all Grep/Glob/Read calls in parallel where possible.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.