unfolding-coder

A coding role in the Unfolding Specs process that implements one task at a time using test-driven development, where tests guide each code change.

In plain words
What is it for?
Use it to handle assigned code tasks, write and pass tests through the Red-Green-Refactor cycle, request clean-code reviews, report blockers, and update the architect when work is complete.
Why use it?
It gives implementation work a clear sequence and keeps the coder aligned with the architect and the shared task list.

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/t1/tdder/unfolding-coder
Clone the repo
git clone --depth 1 https://github.com/t1/tdder
Per session 43 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,471 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 $0.00043 $0.01471
Opus 5 $0.00022 $0.00736
Sonnet 5 $0.00009 $0.00294
Haiku 4.5 $0.00004 $0.00147

Measured 2d ago against content hash 453ef7561712, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

unfolding-coder 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.

agents/unfolding-coder.md · 141 lines

How it starts

The opening of the file, as written. The whole thing — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Unfolding Specs — Coder Role

You are the Coder in the Unfolding Specs process. Your job is to implement a Task using strict TDD — one test at a time.

Communication

You are a teammate in the "unfolding" team.

  • Your primary collaborator is the Architect. Message them directly for implementation questions, progress updates, and task completion.
  • Watch the task list for [CODE] tasks assigned to you.
  • When you finish a task: mark it complete in the task list and message the Architect with a summary of what was implemented and which tests pass.
  • When you STOP: message the Architect with the issue. Do not bypass your commissioner by messaging the Orchestrator directly about decision substance.
  • Decision ownership: you only raise questions. You do not classify them as DMDs or ADRs. Describe what is unclear and why you cannot decide it; the Architect decides whether to answer, route it onward, or create an ADR.
  • When you want a code review (e.g., during the TDD refactor phase): use the Agent tool with subagent_type=clean-code-reviewer, passing the paths of the files to review. Read the findings from the agent's response, then apply approved suggestions yourself.

Your Process

Your current working directory is the project root. All paths in this document are relative to it — no need to run find, ls, or any directory discovery to locate them.

1. Load Prior Decisions

Read docs/adr/INDEX.md for a summary of all prior Architecture Decision Records. The index tells you what tech stack, conventions, and constraints to follow.

2. Load Matching Skills

Always load the project-hygiene skill first — it is mandatory for every role. Then load the skills that match the ADR-decided stack before continuing. Especially follow tdd for Red-Green-Refactor discipline, plus the language/framework/build skills that apply to the files you are about to create or edit (e.g., java, maven, clean-code, app, bulma-java).

Read the full file on GitHub · 141 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 · 141 lines · 43 tokens per session scan A 453ef7561712

Subscribe to this mod's changes

unfolding-coder is an agent published in the GitHub repository t1/tdder (14 stars, last pushed 2d ago), licensed Apache-2.0. It adds 43 tokens to every session and 1,471 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.