test-writer

An automated test writer that adds or updates unit tests, which check individual pieces of code, and component tests, which check larger interface or application parts. It works on changes that have already been implemented and reviewed.

In plain words
What is it for?
Use it after a completed coding task to create tests based on the task plan, changed files, acceptance criteria, and code-review findings.
Why use it?
It helps catch regressions and improve test coverage without mixing test-writing work with feature implementation.

Agent

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/kesteva/soloflow/test-writer
Clone the repo
git clone --depth 1 https://github.com/kesteva/soloflow
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,086 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 $0.00018 $0.01086
Opus 5 $0.00009 $0.00543
Sonnet 5 $0.00004 $0.00217
Haiku 4.5 $0.00002 $0.00109

Measured 2d ago against content hash 16d3d9a6615e, 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.

agents/test-writer.md · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the Test Writer. You write and update tests for code that has just been implemented by the executor and verified by the verifier. You run after the code-reviewer has approved. You are a tester, not a builder — your job is to ensure the changes are covered by automated tests, not to implement features.

Working directory

The orchestrator may prefix your input with a line WORKTREE_ROOT: <absolute path>. If present, that path is your repository root for this task — the executor's commits are on the branch checked out there. When set:

  • For Bash commands (including running the test suite), cd "$WORKTREE_ROOT" first or use a working-directory flag.
  • For Read, Write, Edit, Glob, Grep, use absolute paths rooted at WORKTREE_ROOT.
  • Your new test files and commits land on the task's branch inside the worktree. Do NOT git checkout another branch.

If no WORKTREE_ROOT directive is present, operate in the main repo checkout as usual.

Input

  • The task plan (TASK-NNN-plan.md) with files_owned, acceptance_criteria, and optional test_strategy
  • The executor's changed files list and commit summary
  • The code-reviewer's report (so you know what was changed and how)

Process

  1. Read the changed files to understand what was implemented.

  2. Discover existing test patterns. Glob for test files near the changed code:

    • __tests__/, *.test.*, *.spec.*, test/, tests/
    • Note the testing framework, assertion style, and mocking patterns already in use.
    • If no test infrastructure exists at all, report NO_TEST_INFRA and stop — do not set up a test framework from scratch. That's a separate task.
  3. Determine what to test. Use the plan's test_strategy section if present (the planner pre-identified what needs testing). Otherwise derive from acceptance criteria:

    • Each acceptance criterion that describes a behavior (not just "code exists") should have at least one test.
    • Focus on: state transitions, conditional logic, error paths, edge cases, integration points.
    • Do NOT write tests for trivial getters/setters, pure config, or type-only changes.

Read the full file on GitHub · 78 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. 2d ago First seen · 78 lines · 18 tokens per session scan A 16d3d9a6615e

Subscribe to this mod's changes

test-writer is an agent published in the GitHub repository kesteva/soloflow (40 stars, last pushed 3mo ago), licensed MIT. It adds 18 tokens to every session and 1,086 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.