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.
npx agentmods add skills/moberghr/mtk-agent-toolkit/test-driven-developmentnpx skills add moberghr/mtk-agent-toolkit --skill test-driven-developmentgit clone --depth 1 https://github.com/moberghr/mtk-agent-toolkitWhat 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 | $0.00028 | $0.00598 |
| Opus 5 | $0.00014 | $0.00299 |
| Sonnet 5 | $0.00006 | $0.00120 |
| Haiku 4.5 | $0.00003 | $0.00060 |
Grade A, and why
test-driven-development 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 3d 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.
How it starts
The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Test-Driven Development
Overview
Use tests as proof of intent, not cleanup after coding. The test should define the behavior change before the implementation makes it pass.
When To Use
- New behavior in handlers, services, endpoints, routes, or validators
- Bug fixes that need regression protection
- Refactors where behavior must stay stable
When NOT To Use
- Pure renames with no behavioral impact
- Mechanical formatting-only changes
Workflow
- Identify the behavioral contract that is changing.
- Write the smallest failing test that proves the missing or broken behavior.
- Choose the correct test level:
- unit for pure logic
- integration for behavior that depends on framework infrastructure (see the active tech stack skill's
## Test Level Guidancefor stack-specific rules)
- Use the project-standard test provider. See the active tech stack skill's
## ORM & Data Layer Guidancefor stack-specific data layer testing rules. - Implement the minimum production code needed to make the test pass.
- Strengthen the test if it only proves "does not throw" or "does not raise".
- Run the relevant tests, then broader tests as the task requires.
Rules
- Bug fixes get regression tests.
- New public behavior gets at least one meaningful test.
- Prefer behavior assertions over implementation-detail assertions.
- Match local test naming and fixture patterns.
Common Rationalizations
See .claude/skills/context-engineering/SKILL.md for the shared table. TDD-specific traps: "I'll add the test after the code works" (then the test proves your implementation, not the intended behavior — write it failing first), "a unit test is enough for this query" (not if the risk lives in translation, provider behavior, or relational semantics — check the tech stack's ORM guidance), and "this assertion is good enough" (if it wouldn't fail on a real regression, it is not good enough).
Red Flags
- Behavior changed with no new or updated test
- Assertions only prove no exception or no error
- In-memory or mock provider used for behavior that depends on real database semantics
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.
- 3d ago First seen · 67 lines · 28 tokens per session scan A 6cbc0959f240
test-driven-development is a skill published in the GitHub repository moberghr/mtk-agent-toolkit (6 stars, last pushed 8d ago), licensed MIT. It adds 28 tokens to every session and 598 once invoked, about $0.0001 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.
Other skills, from other repositories
agent-integration
Run all three agent integration phases sequentially: research, write-tests, and implement using E2E-first TDD (unit tests written last). For individual phases, use /agent-integration:research, /agent-integration:write-tests, or /agent-integration:implement. Use when the user says "integrate agent", "add agent…
engram-testing-coverage
TDD and coverage standards for Engram. Trigger: When implementing behavior changes in any package.
code-assist
Guides implementation of code tasks using test-driven development in an Explore, Plan, Code, Commit workflow. Acts as a Technical Implementation Partner and TDD Coach — following existing patterns, avoiding over-engineering, and producing idiomatic, modern code.
tdd
Test-driven development. Use when the user wants to build features or fix bugs test-first, mentions "red-green-refactor", or wants integration tests.
css-design-tdd
Test-driven CSS design system modifications. Run checks before/after CSS changes to verify token usage, variable definitions, fallbacks, and consistency. Use when modifying CSS tokens, fixing design inconsistencies, or auditing CSS architecture.
mobiai-mobile-tdd
You MUST use this before writing any implementation code for a mobile feature, bug fix, refactor, or behavior change. Tests come before implementation — no exceptions.