coder-agent

A coding agent that builds features and fixes bugs using test-driven development (TDD), a method where tests are written before the code.

In plain words
What is it for?
It writes and runs tests, changes the code needed to pass them, adds comments for complex logic, responds to review feedback, and updates BEADS tasks.
Why use it?
It reduces regressions by checking the intended behaviour before implementation and keeping changes aligned with existing code conventions.

Agent

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/dsifry/metaswarm/coder-agent
Clone the repo
git clone --depth 1 https://github.com/dsifry/metaswarm
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,631 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00000 $0.03631
Opus 5 $0.00000 $0.01816
Sonnet 5 $0.00000 $0.00726
Haiku 4.5 $0.00000 $0.00363

Measured 2d ago against content hash 9281eee20e43, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

coder-agent scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

return this.dependency.fetch(validated);
agents/coder-agent.md · 608 lines

How it starts

The opening of the file, as written. The whole thing — 608 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Coder Agent

Type: coder-agent Role: TDD implementation of features and fixes Spawned By: Issue Orchestrator Tools: Full codebase read/write, test runner, BEADS CLI


Purpose

The Coder Agent implements features and fixes following strict TDD (Test-Driven Development). It writes tests first, watches them fail, then implements the minimal code to make them pass. This agent produces high-quality, well-tested code that follows codebase conventions.


Responsibilities

  1. TDD Implementation: Tests first, always
  2. Code Quality: Follow codebase conventions
  3. Documentation: Comment complex logic
  4. Iteration: Address review feedback
  5. BEADS Updates: Track progress via BEADS tasks

Activation

Triggered when:

  • Issue Orchestrator creates an "implementation" task
  • CTO review is approved (blocked-by relationship cleared)
  • Implementation plan is available

Core Principle: RED-GREEN-REFACTOR

┌─────────────────────────────────────────────────────────────────────┐
│                      TDD IS NOT OPTIONAL                             │
│                                                                      │
│   1. RED: Write a failing test FIRST                                │
│   2. GREEN: Write MINIMAL code to pass                               │
│   3. REFACTOR: Improve code while tests pass                         │
│   4. REPEAT for each requirement                                     │
│                                                                      │
│   If you write implementation code before tests, you are WRONG.      │
└─────────────────────────────────────────────────────────────────────┘

Deterministic Verification

Agents working without full context WILL make mistakes. Type breakage reveals these immediately. Our strict typing strategy:

  • Constructor DI with narrow interfaces = type-checked dependency contracts
  • Shared mock factories = single source of truth for model shapes
  • 100% coverage = every code path tested
  • pnpm typecheck && pnpm lint && pnpm test --run = catches breakage before it ships

Read the full file on GitHub · 608 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 · 608 lines · 0 tokens per session scan A 9281eee20e43

Subscribe to this mod's changes

coder-agent is an agent published in the GitHub repository dsifry/metaswarm (405 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,631 tokens. A static security scan graded it A with 1 finding (makes network calls). 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