A workflow for starting a new software project or adding its basic toolchain. It covers package management, formatting, linting, type checking, tests, coverage, continuous integration (automated checks run by the repository), and the repository structure.

Use it to plan and approve the project type, language, framework, deployment assumptions, quality checks, files, and baseline commands before writing feature code.

It establishes a repeatable baseline so a clean copy of the project can install, check, test, and run without relying on one developer's machine.

scaffolding — Skill for Codex by kreek

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.

Any agent

npx skills add kreek/consult --skill scaffolding

Clone the repo

git clone --depth 1 https://github.com/kreek/consult

Made for: Codex.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/kreek/consult/scaffolding.svg)](https://agentmods.dev/skills/kreek/consult/scaffolding)

Your own site

<a href="https://agentmods.dev/skills/kreek/consult/scaffolding"><img src="https://agentmods.dev/badge/skills/kreek/consult/scaffolding.svg" alt="Measured on agentmods" height="20"></a>

Per session 23 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,014 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00023	$0.01014
Opus 5	$0.00012	$0.00507
Sonnet 5	$0.00005	$0.00203
Haiku 4.5	$0.00002	$0.00101

Measured 3d ago against content hash 7de7f20792a4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

scaffolding 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.

agents/.agents/skills/scaffolding/SKILL.md · 90 lines

How it starts

The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Scaffolding

Iron Law

NO FEATURE CODE BEFORE THE TOOLCHAIN PROVES IT CAN FAIL AND PASS.

A scaffold is done only when a clean clone can install, check, test, and run the baseline without local knowledge.

When to Use

Starting a new repo or app, or adding missing package management, linting, formatting, typechecking, testing, coverage, or CI.

When NOT to Use

Adding a feature to a healthy project; use the domain skill plus proof.
Release pipeline beyond baseline CI; use release.
UI design choices after the framework is chosen; use ui-design.

Rules

The user owns scaffold choices. Before creating files, installing packages, or running generators, present a Scaffold Decision Gate (project intent and kind, language/runtime, deployment assumption, framework/template, quality baseline, files and commands) with this menu, and wait:
1. Approve: create files, install packages, run generators
2. Refine: change the scaffold plan
3. Cancel: stop scaffolding
Research is free. Audit candidate dependencies without asking, then get approval before selecting or installing a structural runtime dependency (framework, database, ORM, auth client, SDK, state library, job queue), unless the user or the selected stack already named it.
Recommend one option per choice in priority order (language/runtime, deployment assumption, framework/template, framework-local choices) and name the tradeoff. Fresh web apps default to a mature framework unless the user asks for smaller.
Requested artifact names are literal. Create tsconfig.json, package.json, pyproject.toml, CI, or README by name; substitute a nearby config only with approval.
Commands are the contract: test, lint, format, typecheck, and coverage where applicable, and CI runs the same checks developers run. Every added config is consumed by a standard command.
typecheck runs a real type checker using the config added for it. A syntax check such as node --check is lint, not typecheck.
Fresh scaffolds get git and .gitignore before feature code, one package manager with a committed lockfile, one smoke test that can fail and pass, secret hygiene with .env.example placeholders, and a README with purpose, install, run, and test.
Prototypes keep the same command names even when checks are lightweight, and are promoted to the full checklist before production or collaboration.

Read the full file on GitHub · 90 lines

Files

What ships with it

29 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

3d ago Changed · -39 lines 7de7f20792a4
7d ago First seen · 129 lines · 23 tokens per session scan A 0e1e6f7bbbdc

Subscribe to this mod's changes

scaffolding is a skill published in the GitHub repository kreek/consult (1 stars, last pushed 4d ago), licensed MIT. It adds 23 tokens to every session and 1,014 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 2026-08-31.

CI and CD Claude Code DevOps and cloud Planning agentic ai-agents claude-code-plugin claude-skills codex-plugin

ci-workflow

Design and maintain .NET CI workflows for F#, C#, and mixed solutions with SDK setup, restore, build, test, format checks, package checks, caching, and matrix decisions.

gaelic-ghost/socket · 41 tokens

dockerized-service-release-deployment-workflow

Create a Dockerized-service release contract with clean GitHub Actions builds, main-anchored tags, immutable digest manifests, published-release deployments, production approval, health checks, and exact-digest rollback.

gaelic-ghost/socket · 49 tokens

pr-watch

Local PR watcher. Monitors CI status, automatically fixes failing checks by reading failure logs and applying targeted fixes, then optionally merges when all checks pass. Local CLI analog to Claude Code's cloud auto-fix feature.

SethGammon/Citadel · 46 tokens

rust-tooling-cicd

Use when structuring a Cargo workspace or building a Rust CI pipeline — fmt, clippy, cargo-deny/audit, nextest, coverage, MSRV. Not for writing the tests themselves (rust-testing-quality).

fusengine/agents · 51 tokens

clarify

Lightweight spec clarification scan for jig projects — a six-category ambiguity audit that asks up to five prioritized questions and appends them to the spec's ## Clarifications section. Auto-triggers when you say clarify this spec, audit this spec for ambiguities, is this spec ready for review, find unknowns in this…

ramboz/jig · 153 tokens

explain

Explain jig vocabulary and artifacts in plain language. Three modes: term mode defines one lexicon term; artifact mode walks through a spec or ADR and its linked references; passage mode explains pasted jig output. Output is ephemeral (chat-only). Auto-triggers when you say explain this term, walk me through this…

ramboz/jig · 173 tokens