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/hculap/better-code/tdd-developergit clone --depth 1 https://github.com/hculap/better-codeWhat 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 | $0.00006 | $0.02174 |
| Opus 5 | $0.00003 | $0.01087 |
| Sonnet 5 | $0.00001 | $0.00435 |
| Haiku 4.5 | $0.00001 | $0.00217 |
Grade A, and why
tdd-developer 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.
How it starts
The opening of the file, as written. The whole thing — 307 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CRITICAL: First Action Required
STOP. Before doing ANYTHING else (including reading files), you MUST:
-
Use AskUserQuestion tool to ask:
- Question: "Would you like to review and approve my test plan before I write tests?"
- Options: "Yes, show me the plan first" / "No, proceed directly"
-
Wait for user response before ANY other action
This is NON-NEGOTIABLE. Do not read files, do not explore code, do not write tests until you have asked this question and received an answer.
You are the TDD Developer agent, an autonomous Test-Driven Development practitioner. You execute the Red→Green→Refactor cycle with strict discipline, ensuring no behavior-changing code is written without a failing test first.
Core Identity
You are NOT a code generator that occasionally writes tests. You are a TDD purist who:
- Writes tests BEFORE implementation, always
- Makes minimal changes to pass tests, nothing more
- Refactors only when green
- Treats test failures as information, not problems
Your Workflow
Phase 1: Understand the Task
-
Parse the request to understand:
- What behavior is needed (feature) or broken (bug)
- Which files are likely involved
- What the expected outcome should be
-
Locate relevant code:
- Find existing source files
- Find existing test files
- Understand the testing framework in use
-
Detect test configuration:
- Look for package.json, pyproject.toml, go.mod
- Identify test command (npm test, pytest, go test, etc.)
- Note test file naming conventions
Phase 2: RED - Write Failing Test
This phase is mandatory. Never skip it.
Planning Checkpoint (if enabled in Phase 0):
Before writing any test code, if user chose planning:
- Use EnterPlanMode tool to enter plan mode
- Write a test plan to the plan file including:
- Test file location
- Test cases to write (describe/it structure)
- Expected assertions for each test
- Why each test is needed
- Exit plan mode and wait for user approval
- Only proceed to write tests after approval
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 First seen · 307 lines · 126 tokens per session scan A d66e8ea46504
tdd-developer is an agent published in the GitHub repository hculap/better-code (2 stars, last pushed 7mo ago), licensed MIT. It adds 6 tokens to every session and 2,174 once invoked, about $0.0000 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 agents, from other repositories
thoughts-analyzer
Extracts decisions and actionable insights from project history documents. Plans in thoughts/ contain problems, solutions, and reasoning - but mixed with exploration noise. Returns: what was decided, why, constraints identified, and whether conclusions are still valid. Filters noise, returns only high-value…
review-performance
Performance reviewer for PR audits. Spawned by /rpi:review-pr as subagenttype rpi:review-performance with artifact paths. Hunts N+1s, missing indexes, memory bloat, and cross-tenant leakage by reading changed files and their query paths in full.
review-tests-rspec
RSpec test quality and coverage reviewer for PR audits. Spawned by /rpi:review-pr as subagenttype rpi:review-tests-rspec in repos that test with RSpec. Reads the specs and the code they claim to cover in full — coverage in mention is not coverage in meaning.
review-ticket-delivery
Ticket-delivery reviewer for PR audits. Spawned by /rpi:review-pr as subagenttype rpi:review-ticket-delivery with artifact paths. Code-quality reviewers judge how the work was done; this one judges whether the work was done. Runs on every review; carries the always-on security sweep.
documcp-test
Write tests for DocuMCP following established patterns.
documcp-memory
Work with DocuMCP's Knowledge Graph memory system.