Skip to main content
skill CX Codex

token-report — Claude Code skill: what it does, how to install

The token-report skill for Claude Code reports how many tokens the Roslyn Navigator MCP server has saved and tracks adoption rate.

MIT 749 installs ★ 845 updated 2026-08-07

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add codewithmukesh/dotnet-claude-kit --skill token-report -a claude-code
Open on GitHub

What token-report does

The skill reports measurable token savings across one repository or an aggregate of all repositories, complete with a per-tool leaderboard and adoption rate. Collection is opt-in and requires starting the server with CWM_ROSLYN_TELEMETRY=on, storing records outside the repository in %LOCALAPPDATA%/cwm-roslyn-navigator/. Adoption rate reads directly from transcripts without requiring opt-in.

Metrics include methodological notes such as uncalibrated divisors and baselines that only count answered files. Aggregate reports run via the CWM.RoslynNavigator.Stats CLI using dotnet run commands. Calibration requires an Anthropic API key passed via $ANTHROPIC_API_KEY alongside a sample path.

Uncalled tools highlight potential description issues or redundant features. Deleting the telemetry directory erases all stored metrics.

What it helps with

  • measure actual token savings from the MCP server
  • generate a per-tool leaderboard with execution counts
  • calculate tool adoption rate in C# development
  • identify tools with zero calls to refine descriptions

Example prompts for the agent

  • Run a token report for this session
  • Show the token savings leaderboard and adoption rate
  • Display aggregate token statistics across all repositories

How to install token-report

1Skills CLI (Vercel)

npx skills add codewithmukesh/dotnet-claude-kit --skill token-report -a claude-code

2Manually: put the files in place

~/.claude/skills/token-report/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/token-report/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about token-report

How to install token-report in Claude Code?

Run npx skills add codewithmukesh/dotnet-claude-kit --skill token-report -a claude-code followed by ~/.claude/skills/token-report/SKILL.md.

What does token-report do?

It reports token savings achieved by the Roslyn Navigator MCP server, providing leaderboards, adoption rates, and methodology notes.

What is needed to run token-report?

Telemetry must be enabled with CWM_ROSLYN_TELEMETRY=on when starting the server, and divisor calibration requires an $ANTHROPIC_API_KEY.

Source text

SKILL.md · MIT
---
name: token-report
description: >
  Report how many tokens the Roslyn Navigator MCP server has saved, across one
  repository or all of them, with a per-tool leaderboard, adoption rate, and the
  methodology behind the number. Use when: "token report", "token savings", "how
  many tokens saved", "is the MCP worth it", "MCP usage", "tool leaderboard",
  "adoption rate", "which MCP tools are used", "prove the savings".
---

# /token-report — Roslyn Navigator token savings

## What

Reports what the Roslyn MCP server has actually saved, measured rather than asserted.
Two surfaces:

| Scope | Surface | Use when |
|---|---|---|
| This repository, mid-session | `get_token_savings` MCP tool | "how are we doing here?" |
| All repositories, aggregate | `CWM.RoslynNavigator.Stats` CLI | producing a public number |

## When

- Deciding whether the MCP server earns its context cost
- Finding tools nobody calls — a description problem, or a tool that should not exist
- Backing a claim about token efficiency with something checkable

## Prerequisite

**Collection is opt-in and off by default.** Nothing was recorded unless the server was
started with it enabled:

```bash
CWM_ROSLYN_TELEMETRY=on cwm-roslyn-navigator --solution MySolution.sln
```

Nothing is transmitted. Records are written under `%LOCALAPPDATA%/cwm-roslyn-navigator/`
(or the XDG equivalent), outside the repository. Delete that directory to erase everything.

Adoption rate is read from Claude Code transcripts and needs no opt-in, so it is available
even when telemetry was never enabled.

## How

**1 — This repository, mid-session.** Call the `get_token_savings` MCP tool. Returns
totals, a per-tool leaderboard, separate zero-result / not-ready / error counts, and the
methodology. If it reports `Enabled: false`, telemetry was never turned on — say so rather
than reporting zero as if it were a measurement.

**2 — All repositories.**

```bash
cd mcp/CWM.RoslynNavigator
dotnet run --project stats/CWM.RoslynNavigator.Stats.csproj            # table
dotnet run --project stats/CWM.RoslynNavigator.Stats.csproj -- --markdown
dotnet run --project stats/CWM.RoslynNavigator.Stats.csproj -- --json
dotnet run --project stats/CWM.RoslynNavigator.Stats.csproj -- --repo myapp
```

**3 — Interpret it honestly.** Three things must be said whenever a number is quoted:

- **The divisor is uncalibrated.** 3.5 bytes/token is an estimate, and it scales every
  figure linearly. If `DivisorCalibrated` is false, the number is indicative, not precise.
- **The baseline understates.** It counts only the files an answer came from, ignoring the
  wrong files a text search would have opened first.
- **Adoption is biased upward.** Its denominator counts only Read/Grep/Glob calls that
  demonstrably targeted C#; ambiguous searches are excluded.

**4 — Act on the leaderboard.** A tool with no calls is the actionable finding. Low
adoption in a configured repository usually means a tool description is not attracting the
work it should — more useful than the savings figure itself.

## Calibrating the divisor

Turns the one estimated input into a measurement. Free, manual, and never run by the
server:

```bash
dotnet run --project stats/CWM.RoslynNavigator.Stats.csproj -- calibrate \
  --api-key $ANTHROPIC_API_KEY --path /path/to/dotnet/repo --sample 200
```

Samples C# files, gets exact counts from the Anthropic `count_tokens` endpoint, and
regresses bytes against tokens. Apply the result to `TokenEstimator` in the server and
record the sample size and R² next to the constant so the figure stays checkable.

## Example

```
  Repositories        3  (1 with telemetry)
  Tool calls          412
  Tokens saved        1,284,000
  Adoption            68%

  Tool leaderboard
  tool                  calls      saved   p50 ms  0-result
  find_references         180    612,000       84        4%
  find_symbol             150    431,000       22        2%

  Never called (2): get_nuget_packages, resolve_stack_trace
  Divisor: 3.5 bytes/token — UNCALIBRATED estimate.
```

When the server was never invoked, the report says so plainly instead of printing zeros —
"no calls" and "no savings" are different findings.

## Related

- `/verify` — quality gates before a PR
- `/health-check` — codebase health grades

© codewithmukesh · MIT · codewithmukesh/dotnet-claude-kit

Similar skills

All skills for Agent setup: memory, context, orchestration →

From the same set52

The whole set →

Project sponsors

Companies that keep this analytics open