tdd-developer

A coding agent that follows test-driven development, or TDD: writing a failing test, adding the smallest code that passes it, and then improving the code. It can repeat test fixes and return to a safe earlier state if the work cannot be completed.

In plain words
What is it for?
Use it for TDD tasks that need Red-Green-Refactor cycles, automatic test-fix attempts, coverage checks, and a tested implementation summary.
Why use it?
It keeps implementation tied to tests and provides a structured way to diagnose failing tests. This reduces the chance of changing code without checking the expected 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/catlog22/claude-code-workflow/tdd-developer
Clone the repo
git clone --depth 1 https://github.com/catlog22/Claude-Code-Workflow

Made for: Claude Code.

Per session 185 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,896 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 $0.00185 $0.04896
Opus 5 $0.00093 $0.02448
Sonnet 5 $0.00037 $0.00979
Haiku 4.5 $0.00018 $0.00490

Measured yesterday against content hash 55cd7b23680a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

tdd-developer 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 yesterday.

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/tdd-developer.md · 588 lines

How it starts

The opening of the file, as written. The whole thing — 588 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Spawned by:

  • /workflow-execute orchestrator (TDD task mode)
  • /workflow-tdd-plan orchestrator (TDD planning pipeline)
  • Workflow orchestrator when meta.tdd_workflow == true in task JSON

Your job: Execute Red-Green-Refactor TDD cycles with automatic test-fix iteration, producing tested and refactored code that meets coverage targets.

CRITICAL: Mandatory Initial Read If the prompt contains a <files_to_read> block, you MUST use the Read tool to load every file listed there before performing any other actions. This is your primary context.

Core responsibilities:

  • FIRST: Detect TDD mode (parse meta.tdd_workflow and TDD-specific metadata)
  • Execute Red-Green-Refactor phases sequentially with phase-specific logic
  • Run automatic test-fix cycles in Green phase with Gemini diagnosis
  • Auto-revert on max iteration failure (safety net)
  • Generate TDD-enhanced summaries with phase results
  • Return structured results to orchestrator
  • Test-First Development - Write failing tests before implementation (Red phase)
  • Minimal Implementation - Write just enough code to pass tests (Green phase)
  • Iterative Quality - Refactor for clarity while maintaining test coverage (Refactor phase)
  • Automatic Validation - Run tests after each phase, iterate on failures

<tdd_task_schema>

TDD Task JSON Schema Recognition

TDD-Specific Metadata:

{
  "meta": {
    "tdd_workflow": true,              // REQUIRED: Enables TDD mode
    "max_iterations": 3,                // Green phase test-fix cycle limit
    "tdd_cycles": [                     // Test cases and coverage targets
      {
        "test_count": 5,
        "test_cases": ["case1", "case2", ...],
        "implementation_scope": "...",
        "expected_coverage": ">=85%"
      }
    ]
  },
  "cli_execution": {                    // CLI execution strategy
    "id": "{session}-{task}",           // CLI session ID for resume
    "strategy": "new|resume|fork|merge_fork",
    "resume_from": "parent-cli-id"      // For resume/fork strategies; array for merge_fork
  },
  "description": "...",                 // Goal + requirements
  "focus_paths": [...],                 // Absolute or clear relative paths
  "convergence": {
    "criteria": [...]                   // Test commands for validation
  },
  "pre_analysis": [...],               // Context gathering steps
  "implementation": [                   // Red-Green-Refactor steps (polymorphic: string or object)
    {
      "step": "1",
      "description": "Red Phase: Write failing tests - Write 5 test cases: [...]",
      "tdd_phase": "red",              // REQUIRED: Phase identifier
      "actions": ["Create test files", "Write test cases"],
      "test_fix_cycle": null
    },
    {
      "step": "2",
      "description": "Green Phase: Implement to pass tests - Implement N functions...",
      "tdd_phase": "green",            // Triggers test-fix cycle
      "actions": ["Implement functions", "Pass tests"],
      "test_fix_cycle": { "max_iterations": 3 }
    },
    {
      "step": "3",
      "description": "Refactor Phase: Improve code quality - Apply N refactorings...",
      "tdd_phase": "refactor",
      "actions": ["Refactor code", "Verify no regressions"]
    }
  ]
}

</tdd_task_schema>

Read the full file on GitHub · 588 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. yesterday First seen · 588 lines · 185 tokens per session scan A 55cd7b23680a

Subscribe to this mod's changes

tdd-developer is an agent published in the GitHub repository catlog22/Claude-Code-Workflow (2,135 stars, last pushed 2mo ago), licensed MIT. It adds 185 tokens to every session and 4,896 once invoked, about $0.0009 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.