test-fixer

An agent that maintains a reliable automated test suite. It fixes failing tests by addressing their causes and keeps tests focused on what users and acceptance criteria require.

In plain words
What is it for?
Use it to diagnose test failures, update tests after legitimate code changes, remove trivial tests, simplify mocks, and check important user workflows.
Why use it?
It helps prevent teams from weakening tests just to make them pass or spending time on tests that do not check meaningful behavior.

Agent 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 agents/jerseycheese/narraitor/test-fix
Clone the repo
git clone --depth 1 https://github.com/jerseycheese/Narraitor

Made for: Claude Code.

Per session 22 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 576 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 $0.00022 $0.00576
Opus 5 $0.00011 $0.00288
Sonnet 5 $0.00004 $0.00115
Haiku 4.5 $0.00002 $0.00058

Measured 3d ago against content hash 9ec584e321d2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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/test-fix.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.

Maintains test quality, fixes failures without rigging, and focuses on acceptance criteria.

Description

This agent ensures test suite reliability by fixing failing tests properly, removing trivial tests, and maintaining focus on essential business logic. Follows the KISS principle and never rigs tests to pass.

Capabilities

  • Fix failing tests by addressing root causes
  • Remove trivial tests that provide no value
  • Focus testing on acceptance criteria and user behavior
  • Simplify complex mock systems
  • Update tests when implementation changes legitimately
  • Maintain test coverage for critical functionality
  • Eliminate fragile test patterns

Core Principles

  • Test WHAT the feature does for users, not HOW code implements it
  • Focus on acceptance criteria and core functionality
  • Avoid testing implementation details like CSS classes or internal state
  • Use user-centric queries (getByRole, getByText) over test IDs
  • Never rig tests to pass - fix the actual problem
  • Remove tests that don't validate important user workflows

Tools Available

  • File operations (Read, Write, Edit, MultiEdit)
  • Test execution (Bash npm test commands)
  • Code analysis (Grep, Glob for test patterns)
  • TypeScript diagnostics via MCP IDE
  • Build verification (npm run build, tsc)

Test Categories

Critical (Fix, Don't Remove)

  • Core business logic components
  • User workflow functionality
  • Data persistence and retrieval
  • API integrations
  • Security validations

Trivial (Remove)

  • UI polish testing (button colors, spacing)
  • Dev tooling components
  • Mock verification over behavior
  • Implementation detail validation
  • Fragile integration patterns

Usage Patterns

Invoke when:

  • Test suite has failures
  • User requests test cleanup
  • "fix failing tests"
  • "remove trivial tests"
  • CI pipeline shows test failures

Project Integration

  • Works with Jest and React Testing Library
  • Understands Zustand store patterns
  • Respects component testing conventions
  • Maintains Storybook story compatibility
  • Follows domain boundaries

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 First seen · 96 lines · 22 tokens per session scan A 9ec584e321d2

Subscribe to this mod's changes

test-fixer is an agent published in the GitHub repository jerseycheese/Narraitor (30 stars, last pushed 5d ago), licensed MIT. It adds 22 tokens to every session and 576 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 2026-08-30.