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/mountainunicorn/add/tdd-cyclenpx skills add MountainUnicorn/add --skill tdd-cyclegit clone --depth 1 https://github.com/MountainUnicorn/addWrote 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.
[](https://agentmods.dev/skills/mountainunicorn/add/tdd-cycle)<a href="https://agentmods.dev/skills/mountainunicorn/add/tdd-cycle"><img src="https://agentmods.dev/badge/skills/mountainunicorn/add/tdd-cycle.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00025 | $0.02961 |
| Opus 5 | $0.00013 | $0.01481 |
| Sonnet 5 | $0.00005 | $0.00592 |
| Haiku 4.5 | $0.00003 | $0.00296 |
Grade A, and why
tdd-cycle 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 4d 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 — 309 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ADD TDD Cycle Skill v{{VERSION}}
Execute a complete Test-Driven Development cycle for a feature from the specification through production-quality code.
Overview
The TDD Cycle is the primary "do the work" skill in Agent Driven Development. It orchestrates the full lifecycle:
- RED — Write failing tests from spec acceptance criteria
- GREEN — Implement minimal code to pass those tests
- REFACTOR — Improve code quality while keeping tests green
- VERIFY — Run all quality gates to ensure production readiness
This skill coordinates sub-agents (test-writer, implementer, reviewer, verify) and maintains traceability between specs, tests, and implementation.
Sub-Agent Dispatch Prompt Template
Every Task-tool dispatch from this skill (test-writer, implementer, reviewer,
verify) MUST emit a prompt body laid out per rules/cache-discipline.md.
Construct the prompt as follows — the STABLE block is byte-identical across
every dispatch in a session; only the VOLATILE block changes per role.
- Active autoload:true rule bodies, in stable order
- Tier-1 knowledge active view (
knowledge/global.md) - Tier-2 active view (
~/.claude/add/library-active.md) if present - Project identity summary from
.add/config.json - Active learnings view (
.add/learnings-active.md) - Full body of the current spec under work
- Role (test-writer | implementer | reviewer | verify)
- MODEL: capability tier per role — test-writer: editor, implementer: editor,
reviewer: architect, verify: editor (tiers per
rules/model-roles.md, never hardcoded model names) - BUDGET: max tokens for this dispatch — per the maturity Resource Budgets
table in
${CLAUDE_PLUGIN_ROOT}/references/swarm-protocol.md(overridable via.add/config.json→swarm.budgets) - Per-call TASK / SCOPE / SPEC REFERENCE / SUCCESS CRITERIA / RESTRICTIONS
- AC subset for this dispatch
- Per-call hints — recent edits, tool outputs, working-set diffs
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.
- 4d ago First seen · 309 lines · 25 tokens per session scan A 292ba947bbcd
tdd-cycle is a skill published in the GitHub repository MountainUnicorn/add (11 stars, last pushed 1mo ago), licensed MIT. It adds 25 tokens to every session and 2,961 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 2026-08-30.
Other skills, from other repositories
bugfix
Fixing bugs using a test-first disciplined loop. Use when a bug is reported or discovered and needs a verified fix with minimal blast radius.
test-driven-development
Use when implementing any feature or bugfix, before writing implementation code.
taiyi-dev
TaiyiForge 第6阶段 — TDD开发执行。四端通用。.
maestro-work
Drive one accepted implementation unit test-first - smallest falsifiable behavior, minimum edits, evidence that names the real falsifier.
red-green-refactor
Guides the red-green-refactor TDD workflow: write a failing test first, implement the minimum code to make it pass, then refactor while keeping tests green. Use when a user asks to practice TDD, write tests first, follow red-green-refactor, do test-driven development, write failing tests before code, or phrases like…
superpowers-zh
Use when constraining AI coding with Chinese TDD methodology, systematic debugging, code review, and verification workflows. Superpowers-zh: Chinese adaptation of the Superpowers AI-assisted programming skills and methodologies.