cdd-quick-create

A guided command that creates a small, standalone deliverable: a script and a README, without setting up a full project.

In plain words
What is it for?
Use it from a CDD repository to make a focused script and document how to use it.
Why use it?
It helps when you need a one-off tool but do not want the files and process of a complete CDD project. A few questions clarify the task before the code is created.

Command 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 commands/drabaioli/cdd/cdd-quick-create
Clone the repo
git clone --depth 1 https://github.com/drabaioli/cdd

Made for: Claude Code.

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 1,637 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 $0.00000 $0.01637
Opus 5 $0.00000 $0.00818
Sonnet 5 $0.00000 $0.00327
Haiku 4.5 $0.00000 $0.00164

Measured 2d ago against content hash 3ef983936f12, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cdd-quick-create 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/commands/cdd-quick-create.md · 93 lines

How it starts

The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Produce a small, self-contained deliverable — a script plus a README, not a full CDD project: /cdd-quick-create (takes an optional one-line description of what to build).

Run this command from a CDD-repo session. It is the third sibling of /cdd-bootstrap and /cdd-retrofit: /cdd-bootstrap creates a new CDD project, /cdd-retrofit adapts an existing one, and /cdd-quick-create creates a lightweight deliverable — a one-off artifact with none of the project substrate (no roadmap, no doc/ tree, no .claude/commands/, no worktree helper, no baseline marker, no /cdd-pre-pr lifecycle). Like its siblings it exists only in the CDD repo and has no counterpart in template/.claude/commands/; unlike them it needs neither template/ nor the bootstrap script, because a one-off has no template — it writes plain files directly (see doc/features/template.md).

This is a guided command, but deliberately lighter than /cdd-bootstrap: a few natural questions, not the seven discovery headings. What it keeps from CDD is the part that pays off even for a one-off — a little guided discovery, clean single-purpose code, and a README so future-you can use it. What it drops is everything a single artifact doesn't need.

Checkpoint discipline: confirm the scope (step 1), then the captured definition (step 2), then the name and target (step 3) — each before moving on. The deliverable is written files-first (step 4), before any version control. The two outward-facing actions — a local commit (step 6) and a GitHub repo (step 7) — are offered separately, confirmed individually, and never done silently or by default.

1. Scope check (the gate)

Before discovery, confirm this is actually a deliverable and not a project. Apply the shared scope-triage heuristic (doc/features/template.md, "Deliverable or project?"): a task is a project (→ /cdd-bootstrap) when any of these hold — it is expected to evolve across many sessions and needs a roadmap; it has more than one cooperating component or an architecture worth documenting; it involves multiple collaborators or handoffs; it is long-lived and will accrete features. It is a deliverable (→ /cdd-quick-create) when none hold: a single self-contained artifact, finished in essentially one sitting, used as-is by future-you.

If, from the description ($ARGUMENTS) or an opening exchange, project-signals trip, surface them and offer to switch to /cdd-bootstrap rather than proceeding. The human decides.

Checkpoint: if any project-signal is present, name it and get an explicit "stay lightweight" or "switch to /cdd-bootstrap" before continuing.

Read the full file on GitHub · 93 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 · 93 lines · 0 tokens per session scan A 3ef983936f12

Subscribe to this mod's changes

cdd-quick-create is a command published in the GitHub repository drabaioli/cdd (2 stars, last pushed 7d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,637 tokens. 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 2026-08-31.