agentmods.dev

Context-Engine: Skill for Claude Code

.skills/mcp-tool-selection/SKILL.md

mcp-tool-selection is a skill for Claude Code, Codex from m1rl0k/Context-Engine. It costs 46 tokens per session (444 once invoked), scanned A, original, from a forked repository, MIT.

A guide for choosing between semantic code search through Qdrant-Indexer and exact text searches such as grep. Semantic search finds related code by meaning, while exact search looks for a known word or symbol.

In plain words
What is it for?
Use it to explore unfamiliar code, understand relationships across files, investigate architecture or behavior, and decide when an exact file or line lookup is enough.
Why use it?
It helps the coding agent choose an appropriate search method when exploring, debugging, or answering where-and-why questions about code.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

This is m1rl0k/Context-Engine's own configuration. It tells Claude Code and Codex how to work on Context-Engine itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything Context-Engine configures →

not rated 4repo 8mo ago A scan 46 tokens fork MIT
View source ↗ m1rl0k/Context-Engine
Reuse

Borrowing it

Nothing to install: this file belongs to m1rl0k/Context-Engine. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/m1rl0k/Context-Engine/mit-base-salvage/.skills/mcp-tool-selection/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/m1rl0k/Context-Engine

Made for: Claude Code, Codex.

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 mcp-tool-selection

README.md
[![agentmods](https://agentmods.dev/badge/skills/m1rl0k/context-engine/mcp-tool-selection/github.svg)](https://agentmods.dev/skills/m1rl0k/context-engine/mcp-tool-selection)
Your own site
<a href="https://agentmods.dev/skills/m1rl0k/context-engine/mcp-tool-selection"><img src="https://agentmods.dev/badge/skills/m1rl0k/context-engine/mcp-tool-selection/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 mcp-tool-selection

Your own site · 80×15
<a href="https://agentmods.dev/skills/m1rl0k/context-engine/mcp-tool-selection"><img src="https://agentmods.dev/badge/skills/m1rl0k/context-engine/mcp-tool-selection.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 46 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 444 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 fork From a forked repository.
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 $0.00046 $0.00444
Opus 5.5 $0.00018 $0.00178
Sonnet 5.5 $0.00009 $0.00089
Haiku 4.5 $0.00005 $0.00044

Measured 2mo ago against content hash 41a783fe7c15, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mcp-tool-selection 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 2mo 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.

.skills/mcp-tool-selection/SKILL.md · 51 lines

What it actually says

MCP Tool Selection Rules

Core principle: MCP Qdrant-Indexer tools are primary for exploring code and history. Start with MCP for exploration, debugging, or "where/why" questions; use literal search/file-open only for narrow exact-literal lookups.

Use MCP Qdrant-Indexer When

  • Exploring or don't know exact strings/symbols
  • Need semantic or cross-file understanding (relationships, patterns, architecture)
  • Want ranked results with surrounding context, not just line hits
  • Asking conceptual/architectural or "where/why" behavior questions
  • Need rich context/snippets around matches

Use Literal Search/File-Open Only When

  • Know exact string/function/variable or error message
  • Only need to confirm existence or file/line quickly (not to understand behavior)

Grep Anti-Patterns (DON'T)

grep -r "auth" .        # → Use MCP: "authentication mechanisms"
grep -r "cache" .       # → Use MCP: "caching strategies"  
grep -r "error" .       # → Use MCP: "error handling patterns"
grep -r "database" .    # → Use MCP: "database operations"

Literal Search Patterns (DO)

grep -rn "UserAlreadyExists" .      # Specific error class
grep -rn "def authenticate_user" .  # Exact function name
grep -rn "REDIS_HOST" .             # Exact environment variable

Quick Decision Heuristic

Question Type Tool
"Where is X implemented?" MCP repo_search
"How does authentication work?" MCP context_answer
"Does REDIS_HOST exist?" Literal grep
"Why did behavior change?" search_commits_for + change_history_for_path

If in doubt → start with MCP

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. 2mo ago First seen · 51 lines · 46 tokens per session scan A 41a783fe7c15

Subscribe to this mod's changes

mcp-tool-selection is a skill published in the GitHub repository m1rl0k/Context-Engine (4 stars, last pushed 8mo ago), licensed MIT. It adds 46 tokens to every session and 444 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. It comes from a forked repository.

Building agentsDebugging
Related

mcp-tool-selection compared with skills from other repositories

mcp-tool-selection next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
mcp-tool-selectionm1rl0k/Context-EngineSkill48mo agoMITA46Claude Code, Codex
systematic-debuggingopen-metadata/OpenMetadataSkill16ktodayApache-2.0A37Claude Code
log-error-digestzebbern/claude-code-guideSkill4.7kyesterdayMITA71Claude Code, Codex
cwv-optimizeradobe/skillsSkill320todayApache-2.0A112Claude Code
ci-fixersipyourdrink-ltd/bernsteinSkill1.2kyesterdayApache-2.0A15Claude Code, Codex
incident-response-incident-responsermyndharis/antigravity-skillsSkill2.0k24d agoMITA36Claude Code
diagnosing-missing-recordingsPostHog/posthogSkill41ktodaynoneA76Claude Code, Codex