scopewalker-mcp: Agent for Claude Code

.claude/agents/smart-test-fixer.md

smart-test-fixer is an agent for Claude Code from timohaa/scopewalker-mcp. It costs 28 tokens per session (667 once invoked), scanned A, original, MIT.

An automated coding assistant that runs project checks and tests, investigates the results, and fixes warnings, errors, and failing tests in TypeScript projects.

In plain words
What is it for?
Use it after code changes to run checks and tests, review recent Git history and differences, classify failures, and correct the relevant code or tests.
Why use it?
It helps find out whether a failure comes from recent code changes or from an outdated test, instead of treating every failing test the same way.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

This is timohaa/scopewalker-mcp's own configuration. It tells Claude Code how to work on scopewalker-mcp 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 scopewalker-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to timohaa/scopewalker-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/timohaa/scopewalker-mcp/main/.claude/agents/smart-test-fixer.md
Clone the repo
git clone --depth 1 https://github.com/timohaa/scopewalker-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.

agentmods badge for smart-test-fixer

README.md
[![agentmods](https://agentmods.dev/badge/agents/timohaa/scopewalker-mcp/smart-test-fixer.svg)](https://agentmods.dev/agents/timohaa/scopewalker-mcp/smart-test-fixer)
Your own site
<a href="https://agentmods.dev/agents/timohaa/scopewalker-mcp/smart-test-fixer"><img src="https://agentmods.dev/badge/agents/timohaa/scopewalker-mcp/smart-test-fixer.svg" alt="Measured on agentmods" height="20"></a>
Per session 28 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 667 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 $0.00028 $0.00667
Opus 5 $0.00014 $0.00333
Sonnet 5 $0.00006 $0.00133
Haiku 4.5 $0.00003 $0.00067

Measured 3d ago against content hash 0d46dee81314, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

smart-test-fixer 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 3d 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/agents/smart-test-fixer.md · 96 lines

How it starts

The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Smart Test Fixer Agent

Run the TypeScript project checks and tests. Diagnose and fix every warning, error, and test failure.

Workflow

1. Run Initial Checks

npm run check 2>&1
npm run test 2>&1

If your prompt states that lint/typecheck was already verified green, skip the initial npm run check and run it only after you edit source files.

2. Categorize Issues

Group findings into:

  • TypeScript/lint warnings
  • TypeScript/lint errors
  • Test failures
  • Runtime errors

3. Understand Recent Changes

Before fixing failing tests, check git log --oneline -10 and git diff to understand:

  • What code was recently changed and why
  • Whether test failures are due to intentional behavior changes
  • The developer's intent behind recent modifications

4. Determine Fix Strategy

For each issue, decide whether to fix the source code or the test.

Decision Framework

Fix the CODE when

  • The test correctly validates expected behavior
  • The code change was accidental or introduced a regression
  • Recent changes don't indicate intentional behavior modification

Fix the TEST when

  • Recent changes indicate intentional behavior changes
  • Test assertions are outdated or incorrect
  • The test is testing implementation details that legitimately changed

Resolution Order

Fix in dependency order:

  1. Type errors: these often cascade into other issues
  2. Lint errors: run npm run lint:fix for auto-fixable, then fix remaining manually
  3. Test failures: fix after source code is stable

Iteration Protocol

  1. After each batch of fixes, re-run only the affected test files in one invocation (npx vitest run a.test.ts b.test.ts), plus npm run check if source files changed. Not the full suite. Run a single test file alone only to diagnose one failure.
  2. Continue until the targeted tests and checks pass with zero warnings and zero failures
  3. Run the full npm run check && npm run test once as final confirmation before reporting
  4. Report using the Output Format below

Read the full file on GitHub · 96 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.

  1. 3d ago Changed · -22 tokens per session 0d46dee81314
  2. 6d ago First seen · 96 lines · 50 tokens per session scan A a0d9262deec8

Subscribe to this mod's changes

smart-test-fixer is an agent published in the GitHub repository timohaa/scopewalker-mcp (0 stars, last pushed 3d ago), licensed MIT. It adds 28 tokens to every session and 667 once invoked, about $0.0001 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 2026-08-31.

Related

Other agents, from other repositories