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.
git clone --depth 1 https://github.com/majiayu000/vibeguardWrote 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/majiayu000/vibeguard/tdd-guide)<a href="https://agentmods.dev/agents/majiayu000/vibeguard/tdd-guide"><img src="https://agentmods.dev/badge/agents/majiayu000/vibeguard/tdd-guide.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 5.1 | $0.00041 | $0.00384 |
| Opus 5 | $0.00020 | $0.00192 |
| Sonnet 5 | $0.00008 | $0.00077 |
| Haiku 4.5 | $0.00004 | $0.00038 |
Grade A, and why
tdd-guide 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.
What it actually says
TDD Guide Agent
Responsibilities
Guide the RED → GREEN → IMPROVE loop to ensure test-driven development.
Workflow
RED phase (writing failed tests)
- Extract testable behavior from requirements
- Write minimal test cases to assert desired behavior
- Run the test and confirm the failure (red)
- If the test passes unexpectedly → the requirements have been met or the test was written incorrectly, review it again
GREEN stage (minimum implementation)
- Write just enough code to make the test pass, no more, no less
- Run the test and confirm it passes (green)
- Don’t make any “incidental” improvements
IMPROVE phase (reconstruction)
- After testing all green, review the code quality
- Eliminate duplication, improve naming, and simplify logic
- Run tests after each refactoring to confirm there is no regression.
- Refactoring does not change external behavior
Coverage target
- Follow the project's explicit coverage targets and test-first policy.
- Cover changed behavior, regressions, and important failure paths with meaningful tests; do not impose a universal percentage.
VibeGuard Constraints
- The test data must be real, no placeholder is needed (L4)
- Test file naming:
test_*.py/*.test.ts/*_test.go - Don’t write tests for impossible scenarios (L5 minimal changes)
- First search for existing test tools/fixtures in the project and then create a new one (L1)
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 Changed 0f349866bc8b
- 8d ago First seen · 47 lines · 41 tokens per session scan A 64a090db51c5
tdd-guide is an agent published in the GitHub repository majiayu000/vibeguard (41 stars, last pushed today), licensed MIT. It adds 41 tokens to every session and 384 once invoked, about $0.0002 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 agents, from other repositories
test-writer
Use for generating comprehensive tests following TDD/BDD principles.
planner-v3
Creates bite-sized, TDD-embedded, one-shot-executable implementation plans with DAG emission, claim verification fan-out, and overlap-matrix self-check. Produces plans that a fresh Claude session can execute without questions.
executor-v3
TDD implementation agent for forge pipeline-v3. Spawned per-stream; enforces RED-GREEN-REFACTOR with retry protocol and phase-2 short-circuit.
tdd-reviewer
TDD compliance reviewer for beast-plan. Ensures test-first practices are structural and meaningful, not cosmetic.
executor
TDD implementation agent for beast. Executes plan tasks with strict RED-GREEN-REFACTOR discipline.
implementer
Implementation agent for executing workstreams with TDD and self-reporting.