scout-search

scout-search is a skill for Claude Code from glidermcp/glidermcp.com. It costs 40 tokens per session (448 once invoked), scanned A, original, MIT.

A repository-wide code-search skill called Scout. It supports ranked fuzzy searches, exact literal or regular-expression searches, structural patterns, symbol outlines, and natural-language queries across programming languages.

In plain words
What is it for?
Use it to locate files and symbols, audit or survey exact matches, search code structure, inspect declarations, or ask questions about a repository in plain language.
Why use it?
It helps find code without relying on one search style, while distinguishing ranked results from exhaustive searches and reporting when advanced searches fall back to text matching.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the scout plugin — 1 skill shipped together

Good fit Use it to locate files and symbols, audit or survey exact matches, search code structure, inspect declarations, or ask questions about a repository in plain language.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/glidermcp/glidermcp.com/scout-search
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.

Any agent
npx skills add glidermcp/glidermcp.com --skill scout-search
Clone the repo
git clone --depth 1 https://github.com/glidermcp/glidermcp.com

Made for: Claude Code.

Or install scout, the plugin that ships this one along with the rest of its 1 skill.

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 scout-search

README.md
[![agentmods](https://agentmods.dev/badge/skills/glidermcp/glidermcp.com/scout-search/github.svg)](https://agentmods.dev/skills/glidermcp/glidermcp.com/scout-search)
Your own site
<a href="https://agentmods.dev/skills/glidermcp/glidermcp.com/scout-search"><img src="https://agentmods.dev/badge/skills/glidermcp/glidermcp.com/scout-search/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for scout-search

Your own site · 80×15
<a href="https://agentmods.dev/skills/glidermcp/glidermcp.com/scout-search"><img src="https://agentmods.dev/badge/skills/glidermcp/glidermcp.com/scout-search.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 40 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 448 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00040 $0.00448
Opus 5 $0.00020 $0.00224
Sonnet 5 $0.00008 $0.00090
Haiku 4.5 $0.00004 $0.00045

Measured 9d ago against content hash bf5094c47666, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

scout-search 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 9d 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.

plugins/scout/skills/scout-search/SKILL.md · 15 lines

What it actually says

Scout Code Search Workflow

Use Scout's find as the primary workspace search instead of shell grep, rg, or find. If Glider (C#) or TGlider (TypeScript and JavaScript) is installed, prefer it for its language, and use Scout for every other language and as the universal fallback.

target: auto routes by query shape, and every response echoes the resolved route in data.route. Use strict match modes - literal, regex, or word - when you need exhaustive grep semantics for an audit or a rename survey; fuzzy is ranked top-N with frecency and is never exhaustive. A zero-hit strict search returns an honest empty result rather than silently falling back, so treat it as evidence. Use target: structural for ast-grep patterns ($NAME for one node, $$$ for many), target: symbols for a tree-sitter declaration outline, and target: semantic for natural-language questions. Outside a shipped grammar, or without a semantic model, these degrade to lexical search and say so in meta.degraded - check server_status.tiers before relying on them.

Narrow with path prefixes, include and exclude globs, and language scoping before widening the query, and page through results instead of loosening the match. Results carry workspace-relative paths, 1-based line and column, and trimmed previews, never whole files. Use server_status for index, watcher, and tier health, and sync {full: true} only to force a full rescan, since ordinary queries already flush pending changes.

Scout never mutates workspace source - its only writes are its own state under .glider/scout/ and ~/.glidermcp. When a hit needs semantic follow-up or an edit, hand the file and span to Glider for C#, or TGlider for TypeScript and JavaScript.

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. 9d ago First seen · 15 lines · 40 tokens per session scan A bf5094c47666

Subscribe to this mod's changes

scout-search is a skill published in the GitHub repository glidermcp/glidermcp.com (16 stars, last pushed 1mo ago), licensed MIT. It adds 40 tokens to every session and 448 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.

Related

Other skills, from other repositories