A bug-fixing workflow based on test-driven development (TDD), where you write a test that exposes the bug before changing the code. It then guides the test-and-fix cycle and can refactor the result afterward.

Use it to fix a named bug, create its regression test first, run the project's tests, and optionally plan or refactor the change.

The regression test proves the bug is reproduced and helps prevent it from returning. Planning and strictness options let you control how much process the fix requires.

tdd-bug — Command by hculap

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 commands/hculap/better-code/tdd-bug

Clone the repo

git clone --depth 1 https://github.com/hculap/better-code

Per session 7 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,547 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	$0.00007	$0.01547
Opus 5	$0.00003	$0.00773
Sonnet 5	$0.00001	$0.00309
Haiku 4.5	$0.00001	$0.00155

Measured yesterday against content hash 364e5123bae6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

tdd-bug 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.

plugins/tdd-dev/commands/tdd-bug.md · 221 lines

How it starts

The opening of the file, as written. The whole thing — 221 lines — stays where its author put it; the contents beside it link to each section on GitHub.

TDD Bug Fix

Fix a bug using Test-Driven Development - regression test first: $ARGUMENTS

Parse Arguments

Extract from arguments:

Bug description: The bug to fix (required)
--strict / --standard / --relaxed: Override strictness mode (optional)
--no-refactor: Skip refactor phase after green (optional)
--file : Target specific file (optional)
--plan: Force planning mode (require approval before test and fix)
--skip-plan: Skip planning entirely, execute directly

Pre-Flight Checks

Load settings: Read .claude/tdd-dev.local.md if exists
Determine strictness: Use flag override > settings > default (strict)
Detect test command: From settings or auto-detect
Locate bug: Find the code responsible for the bug
Reset TDD cycle state: Create/update .claude/.tdd-cycle-state to start fresh RED phase:
```
{"phase": "red", "testFilesWritten": [], "testsRan": false, "testsFailed": false}
```
This ensures hooks enforce "write regression test first" for this bug fix.

Plan Mode Decision

Determine planning behavior based on flags:

If --skip-plan flag: Skip all planning, proceed directly to TDD loop
If --plan flag: Force planning before both RED and GREEN phases
If neither flag (default): Ask user using AskUserQuestion:
- "Would you like to review and approve the regression test plan before I write tests?"
- Options: "Yes, show me the plan" / "No, proceed directly"
- Store response for consistent behavior in GREEN phase

Regression Test Planning Phase (unless --skip-plan)

If planning is enabled (via --plan flag or user choice):

Enter plan mode: Use EnterPlanMode tool
Analyze the bug:
- What is the incorrect behavior?
- How can we reproduce it in a test?
- What should the correct behavior be?
Write regression test plan to plan file including:
- Test file location
- Test case that reproduces the bug
- Expected vs actual behavior
- Assertions that will fail due to bug
Exit plan mode: Wait for user approval via ExitPlanMode
Proceed to RED phase only after approval

Read the full file on GitHub · 221 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.

yesterday First seen · 221 lines · 0 tokens per session scan A 364e5123bae6

Subscribe to this mod's changes

tdd-bug is a command published in the GitHub repository hculap/better-code (2 stars, last pushed 7mo ago), licensed MIT. It adds 7 tokens to every session and 1,547 once invoked, about $0.0000 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 2026-08-31.

Code review Debugging Testing ai-tools claude-code code-quality dev-tools documentation plugins

tdd-bug

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

TDD Bug Fix

Parse Arguments

Pre-Flight Checks

Plan Mode Decision

Regression Test Planning Phase (unless --skip-plan)

What this file has done since we first saw it

Other commands, from other repositories

create-skill

sync-config

create_plan

review-pr

research_codebase

iterate_plan