team-management-tdd-discipline

team-management-tdd-discipline is a skill for Claude Code, Codex from TeamManagementPlugin/claude-plugin. It costs 96 tokens per session (1,054 once invoked), scanned A, original, MIT.

A guide to test-driven development, a method of writing a test first, seeing it fail, then writing the smallest code change that makes it pass and improving the code.

In plain words
What is it for?
Use it for bug fixes, behavior changes, features with clear inputs and outputs, and refactoring code that already has tests.
Why use it?
It helps prove that a test checks the intended behavior and leaves a safeguard against the same bug returning. It also explains when writing the test first would be unnecessary, such as exploratory work or basic configuration.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it for bug fixes, behavior changes, features with clear inputs and outputs, and refactoring code that already has tests.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/teammanagementplugin/claude-plugin/team-management-tdd-discipline
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.

Any agent
npx skills add TeamManagementPlugin/claude-plugin --skill team-management-tdd-discipline
Clone the repo
git clone --depth 1 https://github.com/TeamManagementPlugin/claude-plugin

Made for: Claude Code, Codex.

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 team-management-tdd-discipline

README.md
[![agentmods](https://agentmods.dev/badge/skills/teammanagementplugin/claude-plugin/team-management-tdd-discipline/github.svg)](https://agentmods.dev/skills/teammanagementplugin/claude-plugin/team-management-tdd-discipline)
Your own site
<a href="https://agentmods.dev/skills/teammanagementplugin/claude-plugin/team-management-tdd-discipline"><img src="https://agentmods.dev/badge/skills/teammanagementplugin/claude-plugin/team-management-tdd-discipline/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 team-management-tdd-discipline

Your own site · 80×15
<a href="https://agentmods.dev/skills/teammanagementplugin/claude-plugin/team-management-tdd-discipline"><img src="https://agentmods.dev/badge/skills/teammanagementplugin/claude-plugin/team-management-tdd-discipline.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 96 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,054 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00096 $0.01054
Opus 5 $0.00048 $0.00527
Sonnet 5 $0.00019 $0.00211
Haiku 4.5 $0.00010 $0.00105

Measured 8d ago against content hash ef3518d84a42, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

team-management-tdd-discipline 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 8d 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.

skills/team-management-tdd-discipline/SKILL.md · 105 lines

How it starts

The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.

TDD When Applicable

Core Principle

Write the test first. Watch it fail. Write minimal code to pass.

If you didn't watch the test fail, you don't know it tests the right thing. Tests written after the code pass immediately — and passing immediately proves nothing: the test might assert the wrong behaviour, might test the implementation instead of the contract, might miss the cases you already forgot. Only a test you saw fail, for the reason you expected, is evidence of anything.

Applicability Matrix

TDD is a tool, not a loyalty oath. Forcing it where it does not fit produces ceremonial tests that assert nothing.

Applies to:

  • Bug fixes — the failing test reproduces the bug, then the fix makes it pass. This proves the fix and leaves a regression guard behind.
  • Behaviour changes — new required output, new validation, a changed contract.
  • Feature work with clear inputs and outputs.
  • Refactoring of already-tested code — the existing tests are the safety net.

Does not apply (do not force it):

  • Exploratory spikes where the goal is learning, not shipping.
  • Framework or config scaffolding (setup.py, CI YAML, .gitignore, Dockerfile boilerplate).
  • One-off migration or analysis scripts, run once and discarded.
  • Documentation-only changes.
  • Pure refactoring with zero behaviour change where the existing suite already covers the surface — that suite is the oracle.

When uncertain which category applies, default to writing the test. The thirty seconds it takes to find out is almost always cheaper than the debugging session it replaces.

RED-GREEN-REFACTOR

RED — write the failing test

One test, one behaviour, a clear name, exercising real code. Be suspicious of a test that exercises mocks rather than the production path — it will pass forever regardless of the code.

Verify RED — watch it fail

Run it. Confirm three things:

  • It fails, rather than erroring out from a typo or a bad import.
  • The failure message is the one you expected.
  • It fails because the behaviour is missing — not because of an unrelated bug elsewhere.

Read the full file on GitHub · 105 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. 8d ago First seen · 105 lines · 96 tokens per session scan A ef3518d84a42

Subscribe to this mod's changes

team-management-tdd-discipline is a skill published in the GitHub repository TeamManagementPlugin/claude-plugin (5 stars, last pushed 1mo ago), licensed MIT. It adds 96 tokens to every session and 1,054 once invoked, about $0.0005 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.