sdd

sdd is a command for coding agents from fockus/skill-memory-bank. It costs 20 tokens per session (4,830 once invoked), scanned A, original, MIT.

A command that creates three connected planning files for a software feature: requirements, design, and tasks.

In plain words
What is it for?
It helps document user stories, acceptance criteria, architecture decisions, interfaces, evaluation checks, and numbered work items.
Why use it?
It turns a discussion into testable requirements and an ordered implementation plan instead of leaving the work as an empty template.

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/fockus/skill-memory-bank/sdd
Clone the repo
git clone --depth 1 https://github.com/fockus/skill-memory-bank
Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,830 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 $0.00020 $0.04830
Opus 5 $0.00010 $0.02415
Sonnet 5 $0.00004 $0.00966
Haiku 4.5 $0.00002 $0.00483

Measured 3d ago against content hash 027cd1f93c23, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

sdd 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 3d 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.

commands/sdd.md · 223 lines

How it starts

The opening of the file, as written. The whole thing — 223 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/mb sdd

Generate a Kiro/Kilo-compatible spec triple under .memory-bank/specs/<topic>/. Each file has a single concern: requirements (Kiro User Stories + EARS acceptance criteria — hybrid format), design (architecture + interfaces + decisions + Eval declarations), tasks (numbered <!-- mb-task:N --> work items with **Eval:** / **Scope:** / **Budget:**).

/mb sdd is a generation pipeline, not a blank scaffolder: it reads the discuss/self-interview transcript, generates full content, gates the size, publishes the triple as draft, and runs the deterministic C8 self-check battery before anything is called ready. The raw scaffold writer still exists for direct use (see Scaffold boundary).

Hybrid requirements format

requirements.md pairs the two industry conventions instead of choosing one:

  • Kiro User Story per requirement — ### Requirement N + **User Story:** As a <role>, I want <feature>, so that <benefit>. (the "who / why").
  • EARS acceptance criteria under each — a #### Acceptance Criteria heading with - **REQ-NNN**: WHEN ... THE SYSTEM SHALL ... bullets in the 5 EARS patterns, uppercase keywords (the testable "what"). mb-ears-validate.sh is case-insensitive and validates only these bullets; User-Story lines are ignored, so the two layers coexist with zero tooling conflict.

REQ-IDs stay unique and traceable; mb-traceability-gen.sh and **Covers:** REQ-NNN in tasks.md are unaffected by the grouping.

Why split into three?

  • Parallel work — requirements / design / tasks evolve at different speeds.
  • requirements.md stays self-contained and exportable to Kiro.
  • tasks.md is checkbox-compatible with downstream tools.
  • mb-traceability-gen.sh automatically picks up REQ-IDs from specs/*/requirements.md for the REQ → Plan → Test matrix.

When to use

After /mb discuss <topic> (or a self-interview) produced a transcript and an EARS-validated context/<topic>.md, when the work is large enough to need a dedicated spec triple. For small fixes, /mb plan alone is enough.

Read the full file on GitHub · 223 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. 3d ago First seen · 223 lines · 20 tokens per session scan A 027cd1f93c23

Subscribe to this mod's changes

sdd is a command published in the GitHub repository fockus/skill-memory-bank (25 stars, last pushed 1mo ago), licensed MIT. It adds 20 tokens to every session and 4,830 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.