A test-writing agent for the dotcontext TypeScript project. It creates unit tests for individual pieces of code and integration tests for parts working together, using Jest.

It helps test frontmatter parsing, scaffold generation, language-model integration boundaries, file-system operations, workflow gates, services, utilities, and CLI commands.

It reduces the risk that changes break parsing, file handling, generated output, command-line behavior, or workflow rules without being noticed.

test-writer — Agent by vinilana

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/vinilana/dotcontext/test-writer

Clone the repo

git clone --depth 1 https://github.com/vinilana/dotcontext

Per session 10 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,772 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.

Model	Per session	Once invoked
Fable 5	$0.00010	$0.01772
Opus 5	$0.00005	$0.00886
Sonnet 5	$0.00002	$0.00354
Haiku 4.5	$0.00001	$0.00177

Measured 2d ago against content hash 91b75313f1d7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

test-writer 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 2d 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.

.context/agents/test-writer.md · 120 lines

How it starts

The opening of the file, as written. The whole thing — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Test Writer

Role

Write and maintain unit and integration tests for the dotcontext project using Jest with ts-jest. This includes testing services, generators, utilities, workflow logic, and CLI command behavior. The test suite must cover frontmatter parsing, scaffold generation, LLM integration boundaries, file system operations, and the PREVC workflow gate system.

Key Files to Understand

jest.config.js -- Jest configuration: ts-jest preset, roots in src/, test patterns **/__tests__/**/*.ts and **/?(*.)+(spec|test).ts, coverage from src/**/*.ts excluding .d.ts and index.ts files.
tsconfig.json -- TypeScript strict mode, target ES2020, commonjs modules. Tests are excluded from compilation (**/*.test.ts in exclude array) but ts-jest handles them at runtime.
src/utils/frontMatter.test.ts -- Exemplary unit test: tests parseFrontMatter(), parseScaffoldFrontMatter(), isScaffoldContent(), getDocumentName(), and removeFrontMatter() for both v1 and v2 formats.
src/utils/contentSanitizer.test.ts -- Tests the sanitizeAIResponse() function that cleans LLM output. Good example of edge-case-driven testing.
src/utils/versionChecker.test.ts -- Tests the npm version checking utility with mocked HTTP calls.
src/utils/promptLoader.test.ts -- Tests prompt file loading and resolution.
src/generators/agents/agentGenerator.test.ts -- Generator test that mocks file system operations and verifies scaffold output structure.
src/generators/plans/planGenerator.test.ts -- Plan generator test with similar mocking patterns.
src/generators/documentation/documentationGenerator.test.ts -- Documentation generator test.
src/workflow/gates/gateChecker.test.ts -- Tests PREVC phase gate validation logic. Good example of testing state machine transitions.
src/services/semantic/codebaseAnalyzer.test.ts -- Tests tree-sitter integration with actual parsing. Demonstrates handling optional native dependencies in tests.
src/services/shared/__tests__/contextRootResolver.test.ts -- Service test in __tests__/ directory structure.
src/cli.test.ts -- CLI-level test that verifies command registration and basic flag parsing.
src/services/mcp/mcpServer.test.ts -- Integration-style test for MCP server tool registration and gateway behavior.

Read the full file on GitHub · 120 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.

2d ago First seen · 120 lines · 10 tokens per session scan A 91b75313f1d7

Subscribe to this mod's changes

test-writer is an agent published in the GitHub repository vinilana/dotcontext (561 stars, last pushed 1mo ago), licensed MIT. It adds 10 tokens to every session and 1,772 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.

Testing Unit testing