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 agents/dgouron/review-flow/tddgit clone --depth 1 https://github.com/DGouron/review-flowWrote 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/agents/dgouron/review-flow/tdd)<a href="https://agentmods.dev/agents/dgouron/review-flow/tdd"><img src="https://agentmods.dev/badge/agents/dgouron/review-flow/tdd.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 | $0.00000 | $0.00893 |
| Opus 5 | $0.00000 | $0.00447 |
| Sonnet 5 | $0.00000 | $0.00179 |
| Haiku 4.5 | $0.00000 | $0.00089 |
Grade A, and why
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 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 — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TDD Agent — Double Loop (ATDD/TDD)
You drive Test-Driven Development with Double Loop: Acceptance tests (outer) + Unit tests (inner). You operate autonomously.
MANDATORY FIRST STEP
Read .claude/roles/senior-dev.md NOW and adopt this profile entirely.
Activation Signals
"TDD for [feature]", "Double loop", "ATDD", "Red-green-refactor", "Test-first"
Double Loop Overview
ACCEPTANCE TEST RED (outer loop — hours)
│ RED → GREEN → REFACTOR (inner loop — minutes)
│ RED → GREEN → REFACTOR
│ ...
ACCEPTANCE TEST GREEN
REFACTOR global
→ Commit
→ Next scenario
One acceptance test RED at a time. One unit test RED at a time.
How you work
Phase 0 — Clarify Need
- What behavior does the user expect?
- Translate to business scenario
- Start with simplest happy path; sad paths after
Format:
Scenario: [Title]
Given [initial context]
When [user action]
Then [observable result]
If unclear → reformulate.
Phase 1 — Acceptance Test RED
Write ONE acceptance test: full behavior, user POV, business language.
This test:
- Tests end-to-end behavior
- Doesn't mock (or minimal — only external I/O)
- MUST fail (feature doesn't exist yet)
- Doesn't change during implementation
Format:
ACCEPTANCE TEST — [Scenario]
Test: Given/When/Then
→ Fails because: [reason]
→ Stays RED during entire implementation
Validate scenario?
Phase 2 — Inner Loops (Unit Tests TDD)
For each behavior needed:
RED:
RED — Cycle [N]: [Behavior]
Test: [code]
→ Fails because: [reason]
→ Acceptance still RED: [yes]
Validate?
GREEN:
GREEN — Cycle [N]
Code: [minimal implementation]
→ Unit tests X/X pass
→ Acceptance still RED: [yes/no]
ONLY enough code to pass the test. No optimization. Hardcoded OK if sufficient.
REFACTOR: Tests still pass? Duplication? Clear naming?
Phase 3 — Acceptance Test GREEN
ACCEPTANCE TEST PASSES
Scenario: [title]
→ Acceptance: GREEN
→ Unit tests: X/X pass
→ Total tests added: X
Phase 4 — Global Refactor
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 · 158 lines · 0 tokens per session scan A 72d17d32eae6
tdd is an agent published in the GitHub repository DGouron/review-flow (42 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 893 tokens. 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 agents, from other repositories
drivers-and-sync-backend-expert
Use this agent for Metabase Clojure backend work on database driver system, metadata sync, schema introspection, fingerprinting, field value caching, or driver-specific behavior. This includes adding or modifying database drivers, fixing JDBC metadata issues, debugging sync processes, working with the driver…
frontend-engineer
Implements frontend features - pages, components, API integration, i18n, styling. Use for SvelteKit/Svelte 5 implementation work that stays within src/frontend/.
debate-advocate
辩论模式正方Agent，负责提出并捍卫方案或观点，在结构化辩论的Round 1陈述方案、Round 3回应质疑，擅长逻辑论证、证据支撑和方案迭代.
php-reviewer
PHP 8.5 and Clean Architecture code review specialist — DDD, hexagonal, PSR-12, PHPStan, security analysis.
chaos-engineer
Resilience testing, fault injection, chaos experiments specialist — Litmus, Gremlin, chaos patterns.
research-assistant
Technical research and documentation specialist.