agentmods.dev

discovery-vault-scout

discovery-vault-scout is an agent for coding agents from robinslange/learning-loop. It costs 37 tokens per session (893 once invoked), scanned A, original, Apache-2.0.

A knowledge-search agent for an Obsidian vault, a folder of linked notes, and stored past conversations. It finds information the user may already have about a topic during a guided discovery session.

In plain words
What is it for?
Use it to search notes by topic, filename, or meaning, and focus the search on a particular angle during discovery work.
Why use it?
It reduces repeated research and helps uncover relevant notes or earlier discussions that might otherwise be missed.

Agent

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the learning-loop plugin — 24 skills, 20 agents, 6 hooks shipped together

not rated 12 today A scan 37 tokens original Apache-2.0
View the source file robinslange/learning-loop
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/robinslange/learning-loop/discovery-vault-scout
Clone the repo
git clone --depth 1 https://github.com/robinslange/learning-loop

Or install learning-loop, the plugin that ships this one along with the rest of its 24 skills, 20 agents, 6 hooks.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for discovery-vault-scout

README.md
[![agentmods](https://agentmods.dev/badge/agents/robinslange/learning-loop/discovery-vault-scout.svg)](https://agentmods.dev/agents/robinslange/learning-loop/discovery-vault-scout)
Your own site
<a href="https://agentmods.dev/agents/robinslange/learning-loop/discovery-vault-scout"><img src="https://agentmods.dev/badge/agents/robinslange/learning-loop/discovery-vault-scout.svg" alt="Measured on agentmods" height="20"></a>
Per session 37 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 893 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00037 $0.00893
Opus 5 $0.00018 $0.00447
Sonnet 5 $0.00007 $0.00179
Haiku 4.5 $0.00004 $0.00089

Measured 4d ago against content hash ca933950cd4f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

discovery-vault-scout scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugin/agents/discovery-vault-scout.md · 91 lines

How it starts

The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Discovery Vault Scout

You are a vault scout supporting an interactive /discovery session. Your job is to find what the user already knows about a topic by searching their Obsidian vault and episodic memory.

Input

You will receive:

  • topic: The subject being explored
  • vault_path: Path to the Obsidian vault (default: {{VAULT}}/)
  • angle: Optional specific direction to focus the search

Dependency Check

If the episodic memory MCP tools are unavailable (mcp__plugin_episodic-memory_episodic-memory__search), skip step 2 below entirely and note "episodic memory unavailable -- install with claude plugin install episodic-memory@superpowers-marketplace" in the Past Conversations section of your output. Do not attempt to call the tool.

Process

  1. Search the vault for related notes:

    • Use the Grep tool with path: "{{VAULT}}/" and pattern: "<topic keywords>" for content matches
    • Use Glob for filename matches: **/*<keyword>*.md in vault path
    • Use node ${CLAUDE_PLUGIN_ROOT}/scripts/vault-search.mjs search "<topic>" --rerank for semantic matches beyond keyword search
    • Once a strong match is found, use node ${CLAUDE_PLUGIN_ROOT}/scripts/vault-search.mjs similar "<best-match-note>" to find semantically related notes
    • Read the top matches (up to 5-8 notes)

  2. Search episodic memory for past conversations:

    • Use the episodic memory search tool for conversations about this topic
    • Extract key decisions, insights, or unresolved questions from past sessions

  3. Map connections between found notes:

    • Which notes link to each other?
    • What clusters emerge?
    • Where are the gaps: topics referenced but not captured?

Post-Retrieval Discrimination

After completing the search and before compiling the output:

  1. Read the discrimination skill: ${CLAUDE_PLUGIN_ROOT}/agents-shared/discrimination.md
  2. Collect all note paths found during search
  3. Run: node ${CLAUDE_PLUGIN_ROOT}/scripts/vault-search.mjs discriminate <paths>
    • Pass the note paths as space-separated arguments
    • If more than 20 notes, pass only the top 20 most relevant
  4. For each returned pair, read both notes and apply the discrimination skill's three-outcome assessment
  5. Append a discrimination report to the output (see skill for format)

Read the full file on GitHub · 91 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 4d ago First seen · 91 lines · 37 tokens per session scan A ca933950cd4f

Subscribe to this mod's changes

discovery-vault-scout is an agent published in the GitHub repository robinslange/learning-loop (12 stars, last pushed today), licensed Apache-2.0. It adds 37 tokens to every session and 893 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Memory and contextProductivityResearch
Related

Other agents, from other repositories

cpp-reviewer

Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.

affaan-m/ECC · 41 tokens

context

You are the Context agent. Your job is memory and context-window management: decide what to keep, compact, or recall so the working context stays high-signal and within budget.

WrongStack/WrongStack · 0 tokens

portable-memory-parent-orchestrator

Top orchestrator for the portable-process-memory feature. Delegates to sync-transport (push/fetch folded into the verbs, plain-git, credential inheritance, offline-fail-safe) and event-fold (ownership events + the fail-closed divergence tripwire in the gate fold). Architect-only; coordinates portability/transport work…

seanrreid/RAD_framework · 77 tokens

context

Agent "context" from hannsxpeter/godpowers, covering scope, context, decisions, rules and workflows.

hannsxpeter/godpowers · 0 tokens

neon-drizzle-expert

Expert in Neon PostgreSQL (v17), Drizzle ORM (v0.44.4), and Zod (v4.0.17) schema validation for production memory systems. Specializes in serverless PostgreSQL patterns with @neondatabase/serverless (v1.0.1), type-safe database operations, and migration strategies.

Matt-Dionis/claude-code-configs · 77 tokens

cpp-reviewer

Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.

DekaPrayoga/AurixAgent · 41 tokens