recursive-tdd

A rule set for implementing recursive-mode code with TDD, meaning tests are written and shown to fail before production code is added.

In plain words
What is it for?
Use it for recursive-mode features, bug fixes, refactoring, and behavior changes, including documenting any justified exception to test-first work.
Why use it?
It prevents changes from being written without a test that first demonstrates the missing or broken behavior.

Skill for Claude CodeCodex

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 skills/try-works/recursive-mode/recursive-tdd
Any agent
npx skills add try-works/recursive-mode --skill recursive-tdd
Clone the repo
git clone --depth 1 https://github.com/try-works/recursive-mode

Made for: Claude Code, Codex.

Per session 66 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,801 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 $0.00066 $0.02801
Opus 5 $0.00033 $0.01401
Sonnet 5 $0.00013 $0.00560
Haiku 4.5 $0.00007 $0.00280

Measured 2d ago against content hash b2365a6d69a8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

recursive-tdd 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

  • rlm-tdd — 88% identical, 113 lines differ
skills/recursive-tdd/SKILL.md · 395 lines

How it starts

The opening of the file, as written. The whole thing — 395 lines — stays where its author put it; the contents beside it link to each section on GitHub.

recursive-tdd

Overview

Test-Driven Development is mandatory for all recursive-mode implementation work. This skill ensures test-first discipline is followed rigorously and recorded in a way recursive-mode tooling can verify.

Core Principle: If you didn't watch the test fail, you don't know if it tests the right thing.

The Iron Law for recursive-mode:

NO PRODUCTION CODE WITHOUT A FAILING TEST FIRST

Trigger examples

  • Implement Phase 3 for run '<run-id>'
  • Add a failing regression test first, then fix the bug
  • I already wrote the code; now add tests (should trigger TDD reset guidance)
  • Follow RED-GREEN-REFACTOR for this change

When to Use

Always in Phase 3 (Implementation):

  • New features
  • Bug fixes
  • Refactoring
  • Behavior changes

Default rule:

  • Not for "simple" changes
  • Not when "under pressure"
  • Not because "tests after achieve same goals"

Explicit exception path only:

  • If strict RED-first flow is genuinely infeasible, declare TDD Mode: pragmatic in the Phase 3 artifact
  • Record a concrete exception reason
  • Record compensating validation evidence under /.recursive/run/<run-id>/evidence/
  • Treat this as an explicit deviation, not a silent shortcut

RED-GREEN-REFACTOR Cycle

digraph tdd_cycle {
    rankdir=LR;
    red [label="RED\nWrite failing test", shape=box, style=filled, fillcolor="#ffcccc"];
    verify_red [label="Verify fails\ncorrectly", shape=diamond];
    green [label="GREEN\nMinimal code", shape=box, style=filled, fillcolor="#ccffcc"];
    verify_green [label="Verify passes\nAll green", shape=diamond];
    refactor [label="REFACTOR\nClean up", shape=box, style=filled, fillcolor="#ccccff"];
    record [label="Record in\nPhase 3 artifact", shape=box];

    red -> verify_red;
    verify_red -> green [label="yes"];
    verify_red -> red [label="wrong\nfailure"];
    green -> verify_green;
    verify_green -> refactor [label="yes"];
    verify_green -> green [label="no"];
    refactor -> verify_green [label="stay\ngreen"];
    verify_green -> record;
}

Read the full file on GitHub · 395 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 395 lines · 66 tokens per session scan A b2365a6d69a8

Subscribe to this mod's changes

recursive-tdd is a skill published in the GitHub repository try-works/recursive-mode (129 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 66 tokens to every session and 2,801 once invoked, about $0.0003 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.

Related

Other skills, from other repositories