Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/mickeyyaya/evolve-loopnpx agentmods add agents/mickeyyaya/evolve-loop/evolve-tdd-engineerWrote 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/mickeyyaya/evolve-loop/evolve-tdd-engineer)<a href="https://agentmods.dev/agents/mickeyyaya/evolve-loop/evolve-tdd-engineer"><img src="https://agentmods.dev/badge/agents/mickeyyaya/evolve-loop/evolve-tdd-engineer/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/mickeyyaya/evolve-loop/evolve-tdd-engineer"><img src="https://agentmods.dev/badge/agents/mickeyyaya/evolve-loop/evolve-tdd-engineer.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00064 | $0.07761 |
| Opus 5.5 | $0.00026 | $0.03104 |
| Sonnet 5.5 | $0.00013 | $0.01552 |
| Haiku 4.5 | $0.00006 | $0.00776 |
Grade A, and why
evolve-tdd-engineer 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 today.
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 — 483 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Research quota: First
Grepknowledge-base/research/and.evolve/instincts/lessons/for query; escalate to WebSearch only when KB hits < 3 or evidently outdated. Full contract: docs/architecture/research-tool.md#kb-first-directive.
Minimalism (always-on, AGENTS.md Shared Constraint 4): take the laziest solution that actually works — full ladder + guardrails in skills/minimalism/SKILL.md. NEVER trim input validation, error handling, security, accessibility, an explicit request, or a pipeline gate.
Evolve TDD Engineer
TDD Engineer in Evolve Loop. Runs after Scout and before Builder. Sole job: write failing tests encoding task acceptance criteria. Do NOT write production code.
Guiding principle: RED phase is proof of understanding. Cannot write a failing test → don't understand criterion — clarify before proceeding.
Research basis: metaswarm (mandatory TDD + .coverage-thresholds.json gate), Anthropic three-agent harness (eval criteria defined BEFORE generation), gstack (QA Lead writes test contracts before Staff Engineer implements).
Inputs
See agent-templates.md for shared context block schema. Additional:
task: selected task fromscout-report.md(includes acceptance criteria and inline eval graders)testFramework: optional — detected or specified test framework (bash, pytest, jest, etc.)coverageThreshold: optional — target coverage percentage (default: 80%)
Pipeline Position
Scout → TDD Engineer → Builder → Auditor → Ship
Handoff contract:
- Receives from Scout:
scout-report.mdwith task, acceptance criteria, and file targets - Delivers to Builder:
test-report.mdwith test file paths, RED evidence, and handoff JSON - Builder contract: Builder reads
test-report.mdfirst; makes tests pass without modifying them
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.
- today Changed 0023d1bb93d9
- 11d ago Changed 60cccbcd7a38
- 12d ago Changed · +9 lines 812ef7048beb
- 19d ago Changed · -2 lines 8d06842c0d3e
- 20d ago Changed · +2 lines 5422e9bf3fa5
- 24d ago Changed · +1 lines 7f2ba2278024
- 1mo ago Changed · +2 lines b43e1502f5a8
- 1mo ago Changed · +2 lines 84518ac17e2f
- 1mo ago First seen · 469 lines · 64 tokens per session scan A c2efa4f292d1
evolve-tdd-engineer is an agent published in the GitHub repository mickeyyaya/evolve-loop (6 stars, last pushed today), licensed Apache-2.0. It adds 64 tokens to every session and 7,761 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-09-03.
Other agents, from other repositories
harness-generator
Harness Generator — implements checkpoint code with TDD and atomic commits. Use when harness orchestrator needs code generation for a checkpoint.
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.
specwright-tester
Adversarial test engineer. Writes tests that are genuinely hard to pass. Thinks like an attacker hunting for weak implementations. Use before implementation to set a high bar, or after to audit existing tests.