red-test-writer

red-test-writer is an agent for Claude Code from navapbc/digital-service-orchestra. It costs 20 tokens per session (5,596 once invoked), scanned A, original, Apache-2.0.

An agent that writes behavioral failing tests for test-driven development, or TDD, where tests are written before the implementation. It rejects tests that merely detect the current code instead of describing the intended behavior.

In plain words
What is it for?
Use it in TDD bug-fix workflows to create RED tests and update the project’s test index.
Why use it?
It helps ensure a bug fix begins with a test that fails for the right reason. This reduces the risk of writing a test that passes without proving the behavior changed.

Agent for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: model in frontmatter; mentions subagents; mentions Claude Code.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the dso plugin — 37 skills, 4 commands, 53 agents shipped together

Good fit Use it in TDD bug-fix workflows to create RED tests and update the project’s test index.

Compare 6 agents from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add navapbc/digital-service-orchestra
Claude Code
/plugin install dso

Made for: Claude Code.

Or install dso, the plugin that ships this one along with the rest of its 37 skills, 4 commands, 53 agents.

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 red-test-writer

README.md
[![agentmods](https://agentmods.dev/badge/agents/navapbc/digital-service-orchestra/red-test-writer/github.svg)](https://agentmods.dev/agents/navapbc/digital-service-orchestra/red-test-writer)
Your own site
<a href="https://agentmods.dev/agents/navapbc/digital-service-orchestra/red-test-writer"><img src="https://agentmods.dev/badge/agents/navapbc/digital-service-orchestra/red-test-writer/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.

agentmods 80×15 button for red-test-writer

Your own site · 80×15
<a href="https://agentmods.dev/agents/navapbc/digital-service-orchestra/red-test-writer"><img src="https://agentmods.dev/badge/agents/navapbc/digital-service-orchestra/red-test-writer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 5,596 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00020 $0.05596
Opus 5 $0.00010 $0.02798
Sonnet 5 $0.00004 $0.01119
Haiku 4.5 $0.00002 $0.00560

Measured 11d ago against content hash 9e77da5e29b6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

red-test-writer scanned grade A with 1 finding 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 11d 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.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

| Real subprocess spawning (`subprocess.run`, `os.system`) | Mock `subprocess.run` / `subprocess.check_output` to return a fixture response |
plugins/dso/agents/red-test-writer.md · 441 lines

How it starts

The opening of the file, as written. The whole thing — 441 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Red Test Writer

Startup: Session HEAD Sync (worktree isolation fix)

When dispatched with isolation: "worktree", the Agent runtime creates your worktree branched from origin/main — NOT from the orchestrator's session HEAD. If the orchestrator injected SESSION_BRANCH and SESSION_HEAD into your prompt, sync to the session HEAD as your FIRST action before reading any source files. Bug a951-d6f2-0c21-443f tracks this.

if [[ -n "${SESSION_BRANCH:-}" && -n "${SESSION_HEAD:-}" ]]; then
    bash "${CLAUDE_PLUGIN_ROOT}/scripts/worktree-session-head-sync.sh"  # shim-exempt: internal orchestration script
    if [[ $? -ne 0 ]]; then
        echo "ERROR: worktree-session-head-sync.sh failed — aborting" >&2
        exit 1
    fi
elif [[ -n "${SESSION_BRANCH:-}" || -n "${SESSION_HEAD:-}" ]]; then
    echo "WARNING: SESSION_BRANCH/SESSION_HEAD partially set — skipping worktree sync" >&2
fi

When both are unset (orchestrator on main, no session in flight), do nothing — your default origin/main worktree is correct.

Worktree Retention (isolation mode)

After writing the RED test file(s) and updating .test-index, and BEFORE emitting your TEST_RESULT: output, stage all changes so the working tree is non-clean. The Claude Code harness reaps isolated worktrees that have a clean working tree before the orchestrator can harvest them — staging keeps the worktree alive until the orchestrator reviews, commits, and harvests your written files.

Read the full file on GitHub · 441 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. 11d ago First seen · 441 lines · 20 tokens per session scan A 9e77da5e29b6

Subscribe to this mod's changes

red-test-writer is an agent published in the GitHub repository navapbc/digital-service-orchestra (6 stars, last pushed today), licensed Apache-2.0. It adds 20 tokens to every session and 5,596 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.