A plugin entry describing TokenWise, a Claude Code add-on that routes mechanical, execution, review, and planning tasks to different AI models. It records token usage and estimates the money saved per session.

Use it as the catalogue listing for the TokenWise plugin and its model-routing and session-cost tracking purpose.

It helps avoid using the same model for every task and provides data for checking whether the routing is saving money. The description does not provide further implementation details.

How reuvenaor/israel-statistics-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to reuvenaor/israel-statistics-mcp. 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/reuvenaor/israel-statistics-mcp/main/.claude/agents/mcp-tester.md

Clone the repo

git clone --depth 1 https://github.com/reuvenaor/israel-statistics-mcp

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/reuvenaor/israel-statistics-mcp/mcp-tester/github.svg)](https://agentmods.dev/agents/reuvenaor/israel-statistics-mcp/mcp-tester)

Your own site

<a href="https://agentmods.dev/agents/reuvenaor/israel-statistics-mcp/mcp-tester"><img src="https://agentmods.dev/badge/agents/reuvenaor/israel-statistics-mcp/mcp-tester/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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/reuvenaor/israel-statistics-mcp/mcp-tester"><img src="https://agentmods.dev/badge/agents/reuvenaor/israel-statistics-mcp/mcp-tester.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 54 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 640 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 1 finding. 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.

Model	Per session	Once invoked
Fable 5.1	$0.00054	$0.00640
Opus 5	$0.00027	$0.00320
Sonnet 5	$0.00011	$0.00128
Haiku 4.5	$0.00005	$0.00064

Measured 11d ago against content hash 17eb291604b3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

mcp-tester scanned grade A with 1 finding 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 11d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

4. If ALL tools fail with timeouts/5xx, verify CBS availability before reporting (curl the catalog endpoint) — report "CBS outage" separately from regressions.

.claude/agents/mcp-tester.md · 32 lines

How it starts

The opening of the file, as written. The whole thing — 32 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You test the israel-statistics-mcp stdio server. You never modify source code — you build, run, probe, and report.

Procedure

pnpm build. If it fails, report and stop.
Offline gate: node scripts/smoke.mjs — Inspector must connect (connect failure ⇒ capabilities regression), tools/list must return exactly 9 tools with title, annotations.readOnlyHint, and outputSchema present on each; the invalid-args call must return a clean, human-readable error.
Per-tool live matrix (network permitting) — call each tool once via npx -y @modelcontextprotocol/inspector --cli node dist/index.js --method tools/call --tool-name <name> --tool-arg ...:
- get_catalog_chapters {lang:"en"} → 11 chapters
- get_index_topics {lang:"en", pagesize:5} and once with {lang:"he"} (expect Hebrew text)
- get_chapter_topics {chapterId:"aa"} → summary contains a housing warning
- get_subject_codes with a subjectId discovered from the previous call
- get_index_data {code:"120010", last:3} → ≤3 finite data points; and an empty range (e.g. 01-1900→02-1900) → clean "0 results", not a validation error
- get_index_calculator {indexCode:120010, value:1000, fromDate:"2020-01-01", toDate:"2025-06-01"} → numeric linkage; regression case {indexCode:110050, ...same} → must SUCCEED (null coefficients tolerated); a dd-mm-yyyy-looking date with day>12 → normalized, echoed dates match
- get_main_indices {} and get_main_indices_by_period {startDate:"202401", endDate:"202403"} → 3 date groups
- get_all_indices {chapter:"a", lang:"en"} For each call assert: isError !== true, content[0].text parses as JSON, structuredContent present and consistent with the text.
If ALL tools fail with timeouts/5xx, verify CBS availability before reporting (curl the catalog endpoint) — report "CBS outage" separately from regressions.

Reporting

Output a matrix: tool → case → PASS/FAIL → one-line evidence (key numbers, error text). End with a verdict: SHIP / FIX FIRST (list blockers). Record recurring CBS quirks you discover in your memory directory so future runs anticipate them.

Read the full file on GitHub · 32 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.

11d ago First seen · 32 lines · 54 tokens per session scan A 17eb291604b3

Subscribe to this mod's changes

mcp-tester is an agent published in the GitHub repository reuvenaor/israel-statistics-mcp (4 stars, last pushed 1mo ago), licensed MIT. It adds 54 tokens to every session and 640 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

E2E testing Testing

integration-testing-orchestrator

Use this agent when you need to coordinate end-to-end testing across multiple components, optimize build systems, validate deployments, or ensure proper integration between eBPF programs, Rust collector, and frontend components. Examples: Context: User has made changes to both eBPF programs and Rust collector and…

eunomia-bpf/agentsight · 0 tokens

test-engineer

Expert in testing, TDD, and test automation. Use for writing tests, improving coverage, debugging test failures. Triggers on test, spec, coverage, jest, pytest, playwright, e2e, unit test.

ashrafmusa/agenticana · 49 tokens

e2e-tester

Use for end-to-end and smoke testing of critical user paths across viewports. Pairs with a browser-automation MCP (for example Playwright) when one is available.

mnzralee/claude-multi-agent-architecture · 41 tokens

qa-tester

Use when the task is a verifiable browser interaction with a binary pass/fail outcome — login flow, submit form, attach file, verify message appears. Returns a verdict + evidence. Do NOT use for tasks needing user decisions mid-flow (region selection, domain pick, etc.).

DevZonayed/Mochi · 60 tokens

visual-diagram-verifier

Use this agent when the architecture-designer:design or architecture-designer:review skill has opened the browser preview (Step 8 / step 4d) and wants to check whether diagrams actually render without visually overlapping elements — a real, rendered-geometry check using the chrome-devtools-mcp or firefox-devtools-mcp…

sembraniteam/claude-plugins · 112 tokens

qa-engineer

Converts Excel test case reports into verified Playwright E2E scripts with real selectors.

odarino/haren · 21 tokens

israel-statistics-mcp: Agent for Claude Code