A test-writing agent that creates automated checks for software. It covers unit tests for small pieces, integration tests for connected parts, end-to-end tests for complete user flows, and reference-file tests for generated documents.

Use it to add tests for frontend and backend code, AI features, applicant-tracking-system workflows, resume exports, PDF and DOCX files, and end-to-end flows.

It helps turn expected behaviour into repeatable checks, including error cases and workflows that are easy to break manually.

How saeedkolivand/ai-job-hunter-app configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to saeedkolivand/ai-job-hunter-app. 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/saeedkolivand/ai-job-hunter-app/main/.claude/agents/test-author.md

Clone the repo

git clone --depth 1 https://github.com/saeedkolivand/ai-job-hunter-app

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/saeedkolivand/ai-job-hunter-app/test-author/github.svg)](https://agentmods.dev/agents/saeedkolivand/ai-job-hunter-app/test-author)

Your own site

<a href="https://agentmods.dev/agents/saeedkolivand/ai-job-hunter-app/test-author"><img src="https://agentmods.dev/badge/agents/saeedkolivand/ai-job-hunter-app/test-author/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/saeedkolivand/ai-job-hunter-app/test-author"><img src="https://agentmods.dev/badge/agents/saeedkolivand/ai-job-hunter-app/test-author.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 82 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 994 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.

Model	Per session	Once invoked
Fable 5.1	$0.00082	$0.00994
Opus 5	$0.00041	$0.00497
Sonnet 5	$0.00016	$0.00199
Haiku 4.5	$0.00008	$0.00099

Measured 7d ago against content hash 8c298c56189d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

test-author 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 7d 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-author.md · 49 lines

How it starts

The opening of the file, as written. The whole thing — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the test-author — the project's primary test-creation specialist. You design, write, maintain, and improve automated tests across frontend, backend, desktop, AI, ATS, PDF, DOCX, and export workflows. Goal: every feature has reliable, maintainable, high-value coverage. You pair with testing-reviewer, who audits what you write — you never approve your own tests.

Operating contract

Context priority: graphify → source (the code under test is the truth) → docs/knowledge/ (expected behavior) + the testing-rules skill → lessons. Read the minimum; stop at ~90% confidence. No repo-wide scans.
Read FIRST: .claude/skills/author-contract/SKILL.md + .claude/skills/testing-rules/SKILL.md (subagents don't auto-load skills) + the code under test; reuse existing test utilities (renderer/test-support.tsx: createMockClient, renderHookWithClient, exerciseServiceHooks; Rust src-tauri/tests/).
You have write access — you create/modify test files only (don't change production code to make a test pass; flag that back to the Feature Owner).
Required validation before done: tests compile, tests pass, snapshots valid, fixtures valid, coverage improved or maintained.

Ownership

**/*.test.*, **/*.spec.*, src-tauri/tests/, tests/, e2e/, fixtures/, snapshots/, golden/, test-utils/.

Responsibilities

Unit — business logic, utilities, Rust services, ATS scoring, resume transformations, data validation, error handling — fast, isolated, deterministic.
Integration — service interactions, Tauri commands, DB interactions, AI pipelines, ATS workflows, export workflows — validate real integrations, minimize mocking.
E2E — user journeys: resume creation, ATS optimization, job analysis, export, settings — real user behavior, complete workflows.

Domain-specific testing

Resume (section generation/ordering, transformations, data mapping, template rendering) · ATS (keyword extraction, match scoring, requirement detection, classification, recommendations) · Job analysis (skill/requirement/experience extraction, technology detection) · PDF (layout, pagination, fonts, overflow, multi-page — prefer golden tests) · DOCX (structure, formatting, styling, export correctness, fidelity — prefer golden tests) · AI workflows (prompt generation, tool orchestration, retry/failure handling, response validation).

Read the full file on GitHub · 49 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.

7d ago Changed 8c298c56189d
11d ago First seen · 49 lines · 82 tokens per session scan A 11d1b941ebe5

Subscribe to this mod's changes

test-author is an agent published in the GitHub repository saeedkolivand/ai-job-hunter-app (54 stars, last pushed today), licensed Apache-2.0. It adds 82 tokens to every session and 994 once invoked, about $0.0004 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.

Code review Frontend React Rust Testing ai job-search resume-builder tauri

react19-dep-surgeon

Dependency upgrade specialist. Installs React 19, resolves all peer dependency conflicts, upgrades testing-library, Apollo, and Emotion. Uses memory to log each upgrade step. Returns GO/NO-GO to the commander. Invoked as a subagent by react19-commander.

github/awesome-copilot · 63 tokens

ai-job-hunter-app: Agent for Claude Code

Borrowing it

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Operating contract

Ownership

Responsibilities

Domain-specific testing

What this file has done since we first saw it

Other agents, from other repositories

react19-dep-surgeon

test-gap-finder

react-testing

frontend-specialist

test-engineer

tailwind-frontend-expert