sdd-implement

sdd-implement is a command for coding agents from niels-emmer/myace. It costs 28 tokens per session (429 once invoked), scanned A, original, MIT.

A command that carries out an ordered software task list, writing each test before implementing its corresponding change.

In plain words
What is it for?
Use it to implement grouped tasks in dependency order, update task status as work finishes, and prepare the project for final verification.
Why use it?
It keeps work traceable and stops the process when a required task fails instead of hiding problems behind later progress.

Command

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 commands/niels-emmer/myace/sdd-implement
Clone the repo
git clone --depth 1 https://github.com/niels-emmer/myace

Wrote 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.

agentmods badge for sdd-implement

README.md
[![agentmods](https://agentmods.dev/badge/commands/niels-emmer/myace/sdd-implement.svg)](https://agentmods.dev/commands/niels-emmer/myace/sdd-implement)
Your own site
<a href="https://agentmods.dev/commands/niels-emmer/myace/sdd-implement"><img src="https://agentmods.dev/badge/commands/niels-emmer/myace/sdd-implement.svg" alt="Measured on agentmods" height="20"></a>
Per session 28 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 429 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 $0.00028 $0.00429
Opus 5 $0.00014 $0.00215
Sonnet 5 $0.00006 $0.00086
Haiku 4.5 $0.00003 $0.00043

Measured yesterday against content hash a310a491bd21, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

sdd-implement 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.

collections/additional/spec-driven-dev/commands/sdd-implement.md · 14 lines

What it actually says

  1. Read docs/specs/<slug>/tasks.md and the underlying spec.md/plan.md. If sdd-analyze hasn't been run and the spec or plan changed after sdd-tasks was generated, run it first rather than implementing against a possibly-stale task list.
  2. Work through tasks in the order and grouping sdd-tasks produced. Within a group, tasks marked parallel-safe may be done in any order; tasks with a stated dependency must wait for it.
  3. For each task, write the test that would fail without the change first, then implement until it passes — the same discipline as the test-patterns skill, applied task-by-task rather than once at the end.
  4. Mark each task complete in tasks.md as it finishes, so progress is visible and a resumed session picks up where the last one left off instead of re-deriving what's already done.
  5. On a failure in a non-parallel task, stop and surface it rather than skipping ahead to unblocked-looking later tasks — a later task may implicitly depend on the failed one in a way sdd-tasks didn't capture explicitly.
  6. Once every task is complete, hand off to the base verify command (if composed) for the full pre-merge check — this command's job is to execute the task list correctly, not to duplicate the project's whole test/lint/security/docs gate.
  7. Report which tasks completed, which were skipped and why, and the spec's acceptance criteria status — don't report the feature done until every acceptance criterion in spec.md is demonstrably met, not just every task checked off.
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. yesterday First seen · 14 lines · 28 tokens per session scan A a310a491bd21

Subscribe to this mod's changes

sdd-implement is a command published in the GitHub repository niels-emmer/myace (1 stars, last pushed 3d ago), licensed MIT. It adds 28 tokens to every session and 429 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 2026-09-03.