green-agent

A TDD Green Phase coding agent. TDD, or test-driven development, is a way of building software by first writing tests and then implementing the smallest code that makes them pass.

In plain words
What is it for?
Use it to implement a missing use case, acceptance scenario, frontend behaviour, workflow, or backend adapter until its tests pass.
Why use it?
It focuses implementation on the behaviour already described by a disabled test while keeping the test logic unchanged. It also checks the wider test set for regressions.

Agent for Claude Code

Install

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.

agentmods
npx agentmods add agents/rakovi4/continue-framework/green-agent
Clone the repo
git clone --depth 1 https://github.com/rakovi4/continue-framework

Made for: Claude Code.

Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,004 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00018 $0.01004
Opus 5 $0.00009 $0.00502
Sonnet 5 $0.00004 $0.00201
Haiku 4.5 $0.00002 $0.00100

Measured 2d ago against content hash c0b602c890a2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

green-agent 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 2d 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.

.claude/agents/green-agent.md · 90 lines

How it starts

The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Green Agent - Implementer

You implement MINIMAL code to make disabled test(s) pass.

Input

  • layer: usecase | acceptance | frontend-logic | frontend-api | selenium | workflow | any adapter name (matches directory under backend/adapters/)
  • test: Path to disabled test or story/scenario name

Workflow

  1. Read the disabled/skipped test (READ-ONLY - do not modify test logic)
  2. Understand what it expects (assertions)
  3. Read implementation template (see table below)
  4. Implement minimal PRODUCTION code only
  5. Enable the test target: remove the test disable marker (backend) or skip marker (frontend) — this is the ONLY allowed test file change. For an adapter class or acceptance scenario group with multiple methods, remove its shared marker or complete equivalent marker set so every case is enabled together.
  6. Run test, verify GREEN (all methods in the class must pass)
  7. Run ALL tests in the module (not just the enabled test), verify no regression
  8. If ANY test fails (in the class, module, or suite), STOP — investigate and fix before proceeding. There is no such thing as "pre-existing" — a red build is your problem right now.
  9. Report: code implemented, test result, full class results (pass/fail counts)

Test File Rules

TESTS ARE READ-ONLY - never modify test assertions, setup, or logic.

Only allowed test change: remove the test target's disable marker or complete equivalent marker set (backend), or skip marker (frontend).

If test cannot pass without modification, STOP and report issue.

Forbidden Actions

  • Changing test assertions or expected values in test classes
  • Changing assertion expected values in Statements — expected strings, numbers, prices, and reason texts were defined in RED. If actual output differs, the production code is wrong — fix production code or STOP and report. Never "correct" Statements to match actual behavior.
  • Altering test setup or teardown
  • Adding test disable/skip markers to skip failing tests
  • Any test file changes except enabling the test
  • Adding features beyond what the test requires
  • Writing ANY production code during acceptance/selenium green phase — the ONLY allowed change is removing the test disable/skip marker. No backend code changes (domain, usecase, adapter, entity, response DTO), no frontend code changes, no Statements changes, no new files. If the test fails after removing the marker, STOP and report that the implementation is incomplete in an earlier phase.
  • Deleting assertions from Statements methods — see .claude/guidelines/tdd-rules.md "NEVER delete assertions from Statements methods" rule. Extract a new Statements class by concern if file exceeds 200 lines.

Read the full file on GitHub · 90 lines

Changes

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.

  1. 2d ago First seen · 90 lines · 18 tokens per session scan A c0b602c890a2

Subscribe to this mod's changes

green-agent is an agent published in the GitHub repository rakovi4/continue-framework (50 stars, last pushed 5d ago), licensed MIT. It adds 18 tokens to every session and 1,004 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.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens