tool-stats

A command that summarizes how tools were used during the current coding session. It reports counts, response-time information, file operations, and use of MCP tools.

In plain words
What is it for?
Run it to review tool-call totals, search-method usage, performance comparisons, compliance, and suggested improvements.
Why use it?
It helps identify inefficient tool use and whether the session followed an MCP-first search approach.

Command for Claude Code

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 commands/consiliency/code-index-mcp/tool-stats
Clone the repo
git clone --depth 1 https://github.com/Consiliency/Code-Index-MCP

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 397 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 $0.00000 $0.00397
Opus 5 $0.00000 $0.00198
Sonnet 5 $0.00000 $0.00079
Haiku 4.5 $0.00000 $0.00040

Measured 2d ago against content hash b5d6875e417d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

tool-stats 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 2d 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.

.claude/commands/tool-stats.md · 74 lines

What it actually says

Tool Usage Statistics

Display statistics about tool usage patterns in the current session.

Usage

/tool-stats

What It Shows

This command analyzes your current session and displays:

  1. Tool Usage Counts

    • MCP tools used
    • Native search tools used
    • File operations
  2. Performance Metrics

    • Average response times
    • Total time saved by using MCP
    • Efficiency rating
  3. MCP Compliance

    • Percentage of searches using MCP
    • Any violations of MCP-first strategy
    • Suggestions for improvement

Example Output

📊 Tool Usage Statistics
========================

Session Duration: 15 minutes
Total Tool Calls: 42

MCP Tools (Recommended):
- symbol_lookup: 8 calls (19%)
- search_code: 12 calls (29%)
- get_status: 2 calls (5%)
Total MCP: 22 calls (52%)

Native Tools:
- Read: 18 calls (43%)
- Grep: 0 calls (0%) ✅
- Find: 0 calls (0%) ✅
- Glob: 2 calls (5%) ⚠️

Performance Impact:
- Time with MCP: 11.5s
- Time without MCP: ~680s
- Efficiency Gain: 59x faster

MCP-First Compliance: 100% ✅
All searches used MCP tools first!

Recommendations:
- Consider using search_code instead of Glob for file discovery
- Excellent MCP adoption rate!

Metrics Explained

  • MCP Usage Rate: Percentage of search operations using MCP
  • Efficiency Gain: How much faster than traditional search
  • Compliance Score: Whether MCP tools are used before native search

Goal Metrics

Aim for:

  • MCP Usage: >80% of searches
  • Zero grep/find for content search
  • Compliance: 100% MCP-first
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. 2d ago First seen · 74 lines · 0 tokens per session scan A b5d6875e417d

Subscribe to this mod's changes

tool-stats is a command published in the GitHub repository Consiliency/Code-Index-MCP (57 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 397 tokens. 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.