Skill Creator
Azure/azqr
Create new skills, modify and improve existing skills, and measure skill performance.
Shared vocabulary for designing deep modules and for naming factory concepts consistently.
Install Codebase Design
$ npx skills add DanMcInerney/architect-loop --skill codebase-design -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install DanMcInerney/architect-loop codebase-design --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/DanMcInerney/architect-loop.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/codebase-design .claude/skills/codebase-design && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "codebase-design" agent skill from https://github.com/DanMcInerney/architect-loop/tree/main/skills/codebase-design into .claude/skills/codebase-design/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "codebase-design", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/DanMcInerney/architect-loop/tree/main/skills/codebase-designType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add DanMcInerney/architect-loop --skill codebase-design -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install DanMcInerney/architect-loop codebase-design --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/DanMcInerney/architect-loop.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/codebase-design .agents/skills/codebase-design && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "codebase-design" agent skill from https://github.com/DanMcInerney/architect-loop/tree/main/skills/codebase-design into .agents/skills/codebase-design/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "codebase-design", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add DanMcInerney/architect-loop --skill codebase-design -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install DanMcInerney/architect-loop codebase-design --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/DanMcInerney/architect-loop.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/codebase-design .cursor/skills/codebase-design && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "codebase-design" agent skill from https://github.com/DanMcInerney/architect-loop/tree/main/skills/codebase-design into .cursor/skills/codebase-design/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "codebase-design", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/DanMcInerney/architect-loop.git --path skills/codebase-design--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add DanMcInerney/architect-loop --skill codebase-design -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install DanMcInerney/architect-loop codebase-design --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/DanMcInerney/architect-loop.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/codebase-design .gemini/skills/codebase-design && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "codebase-design" agent skill from https://github.com/DanMcInerney/architect-loop/tree/main/skills/codebase-design into .gemini/skills/codebase-design/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "codebase-design", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install DanMcInerney/architect-loop codebase-designInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add DanMcInerney/architect-loop --skill codebase-design -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/DanMcInerney/architect-loop.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/codebase-design .github/skills/codebase-design && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "codebase-design" agent skill from https://github.com/DanMcInerney/architect-loop/tree/main/skills/codebase-design into .github/skills/codebase-design/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "codebase-design", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add DanMcInerney/architect-loop --skill codebase-design -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install DanMcInerney/architect-loop codebase-design --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/DanMcInerney/architect-loop.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/codebase-design .opencode/skills/codebase-design && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "codebase-design" agent skill from https://github.com/DanMcInerney/architect-loop/tree/main/skills/codebase-design into .opencode/skills/codebase-design/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "codebase-design", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
codebase-design- GitHub stars
- 626
- Token cost
- ~1.5k tokens
- SKILL.md length
- 793 words
- Files
- 3
- Skills in repo
- 11
- Repo updated
- First seen
- Licence
- MIT
At a glance
Shared vocabulary for designing deep modules and for naming factory concepts consistently.
- Tasks that involve Skill authoring
- SKILL.md covers Glossary, Deep vs. shallow, Principles and Designing for testability, plus 1 more section
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Codebase Design is an agent skill from DanMcInerney/architect-loop. Shared vocabulary for designing deep modules and for naming factory concepts consistently. Load before writing a spec, decomposing issues, freezing checks, or reviewing a diff - anywhere "module," "interface," "issue," or "frozen check" need to mean the same thing to every skill, builder, and reviewer. Also covers dependency categories for deepening and the parallel design-it-twice pattern for exploring interfaces before committing to one.
Its SKILL.md is about 1.5k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `DEEPENING.md` and `DESIGN-IT-TWICE.md`).
It sits in Agent Workflows, covering Skill authoring. The repository describes itself as: Super optimized /goal loop. Massive token savings and higher quality. Smart model designs and reviews, cheaper model builds.. The licence is MIT.
When your agent uses it
- Tasks that involve Skill authoring
Example prompts
- “module,”
- “interface,”
- “issue,”
- “/codebase-design”
What it can do on your machine
Read from SKILL.md and the folder at commit 28dca7d. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Codebase Design loads about 1.5k tokens when it runs. Until then it costs about 115 tokens; SKILL.md has 793 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from DanMcInerney/architect-loop at commit 28dca7d, republished under its MIT licence (© DanMcInerney). 793 words, ~1,523 tokens.
Download SKILL.mdSave it as
.claude/skills/codebase-design/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.- name
- codebase-design
- description
- Shared vocabulary for designing deep modules and for naming factory concepts consistently. Load before writing a spec, decomposing issues, freezing checks, or reviewing a diff - anywhere "module," "interface," "issue," or "frozen check" need to mean the same thing to every skill, builder, and reviewer. Also covers dependency categories for deepening and the parallel design-it-twice pattern for exploring interfaces before committing to one.
<!-- Adapted from mattpocock/skills (MIT). -->Codebase Design
Design deep modules: a lot of behavior behind a small interface, placed at a clean seam, testable through that interface. Use this language wherever code or a factory issue is being designed. The aim is leverage for callers, locality for maintainers, and testability for everyone.
Glossary
Use these terms exactly — don't substitute component, service, boundary, or API when you mean module or interface; don't say task or ticket for issue, or test file for frozen check. Consistent language is the whole point.
Design (Pocock, adapted):
- Module - anything with an interface and an implementation, at any scale: a function, a package, or a whole vertical slice.
- Interface - everything a caller must know to use a module correctly: types, invariants, ordering, error modes, config, performance - not just a signature.
- Implementation - the body of code behind the interface; distinct from adapter, which names role at a seam, not substance.
- Depth - leverage at the interface: behavior reached per unit of interface learned. Deep means a small interface over a big implementation; shallow is the opposite, and to avoid.
- Seam (Feathers) - the place a module's interface lives; where behavior can change without editing there.
- Adapter - a concrete thing satisfying an interface at a seam. One adapter is a hypothetical seam; two make it real.
- Leverage - what callers get from depth: one implementation pays off across many call sites and tests.
- Locality - what maintainers get from depth: change and bugs concentrate in one place instead of spreading.
Factory (one line each; matches docs/spec/skill-library.md Target flow):
- Run - one factory build from intake to the closing PR, on its own factory branch.
- Tracking issue - the run's parent issue: dashboard, digest, preflight record.
- Issue - one vertical-slice unit of work: one builder job, one disjoint file set, one change-skeleton.
- Slice - the vertical cut an issue implements; slice names the cut, issue names its tracker record - same unit, two angles.
- Frozen check - the committed, read-only acceptance check a builder's work is graded against.
- Check-runner - the deterministic script that grades a frozen check's RUN items and exits typed (0/2/5).
- Strategist - the fresh high-judgment subagent that drafts specs, cuts issues, stress-tests plans, and runs full-lane reviews.
- Builder - the fresh, worktree-isolated agent that implements one issue and never commits.
- Orchestrator - the one session that grounds, dispatches strategist and builder work, freezes, and integrates; never writes implementation code; in the fast lane (/architect-fast) it also runs the closing test pass whose output feeds the builder review - a recorded relaxation.
- Factory branch - the run's integration branch (
factory/<run>) that job branches merge into. - Worktree - the isolated git checkout a builder or reviewer works in, verified against the freeze commit.
- Job report - a builder's raw-evidence artifact, ending in one STATUS line.
- Verdict - the grading record posted on an issue at close: checkrun summary plus typed exit, postflight result, slice call, decisive reason; the closing review's run-level verdict goes on the tracking issue.
- Ruling - an orchestrator decision recorded post-freeze: a PHASE-0 execution conflict, boundary amendment, or respawn answer.
- Digest - the shipped-issues, diffstat, rulings, and domain-language summary handed to the integrate subagent's docs pass.
- Hard stop - an irreversible or destructive action the loop refuses without a human ruling.
Show full SKILL.md (273 more words)Show less
Deep vs. shallow
A deep module hides a lot of implementation behind a small interface: few methods, simple params, most of the complexity out of sight. A shallow module is the opposite - an interface almost as complex as what it wraps, often a near-passthrough. When shaping an interface, ask whether the method count and params can shrink, and whether more logic can move inside.
Principles
- Depth is a property of the interface, not the implementation - a deep module can be built from small internal seams its own tests use, without exposing them at the external interface.
- The deletion test: imagine deleting the module. If complexity vanishes, it was a pass-through; if it reappears across N callers, it was earning its keep.
- The interface is the test surface - callers and tests cross the same seam. If you want to test past the interface, the module is probably the wrong shape.
- One adapter means a hypothetical seam; two adapters means a real one. Don't introduce a seam unless something actually varies across it.
Designing for testability
- Accept dependencies, don't create them - a function that takes its
gateway is testable; one that builds a
StripeGateway()internally is not. - Return results, don't produce side effects - a function that returns a computed discount is testable; one that mutates a cart in place is not.
- Small surface area: fewer methods = fewer tests needed; fewer params = simpler test setup.
Going deeper
- Deepening a cluster given its dependencies - see
DEEPENING.md: dependency categories, seam discipline, and replace-don't-layer testing. - Exploring alternative interfaces - see
DESIGN-IT-TWICE.md: dispatch parallel subagents to design the interface several radically different ways, then compare on depth, locality, and seam placement.
© DanMcInerney, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 2 other files in skills/codebase-design of DanMcInerney/architect-loop.
- SKILL.md
- DEEPENING.md
- DESIGN-IT-TWICE.md
Open the folder on GitHubat commit 28dca7d
Compare with similar skills
Codebase Design next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Codebase Design this skillDanMcInerney/architect-loop | 626 | — | ~1.5k | Automated safety check: Pass | MIT | |
| Skill CreatorAzure/azqr | 795 | 89 repos | ~8.2k | Automated safety check: Pass | Apache-2.0 | |
| Claude Code Skill Developer Guidediet103/claude-code-infrastructure-showcase | 10k | 11 repos | ~3.5k | Automated safety check: Pass | MIT | |
| Darwin Skill Optimizeralchaincyf/darwin-skill | 6.2k | 1 repos | ~4.7k | Automated safety check: Pass | MIT | |
| Claude Code Command Developmentanthropics/claude-plugins-official | 38k | 10 repos | ~4.8k | Automated safety check: Pass | Apache-2.0 | |
| Claude Code Plugin Structureanthropics/claude-plugins-official | 38k | 10 repos | ~3.4k | Automated safety check: Pass | Apache-2.0 |
Similar skills
- Official
Claude Code Skill Developer Guide
diet103/claude-code-infrastructure-showcase
A guide to creating and managing Claude Code skills with auto-activation: skill-rules.json triggers, hooks, enforcement levels, YAML frontmatter and progressive disclosure.
Darwin Skill Optimizer
alchaincyf/darwin-skill
Scores SKILL.md files on a nine-dimension rubric, then improves them in a keep-or-revert loop with independent judge agents, test prompts, git history and human checkpoints.
- Official
Claude Code Command Development
anthropics/claude-plugins-official
Explains how to write Claude Code slash commands: Markdown files with YAML frontmatter, arguments, file references, bash context and interactive prompts.
- Official
Claude Code Plugin Structure
anthropics/claude-plugins-official
Explains the directory layout, plugin.json manifest and component organization of a Claude Code plugin, including auto-discovery and portable paths.
Skill Release Gate
rohitg00/ai-engineering-from-scratch
Evaluates an Agent Skill bundle before release for structure, trigger quality, artifact improvement, script correctness, safety, installed-tree integrity and host portability.
More from DanMcInerney/architect-loop
All 11 skills in this repoArchitect Research
DanMcInerney/architect-loop
A skill your agent uses when the user asks for discovery-scale research that informs a decision: brainstorming a project or feature, choosing a technology, or requests like "research X", "what's the…
Adversarial Review
DanMcInerney/architect-loop
A skill your agent uses when the architect factory orchestrator dispatches a fresh strategist subagent to harden a draft spec: falsify it with file:line evidence, fold the surviving findings into a…
Architect
DanMcInerney/architect-loop
A skill your agent uses when the user asks to architect, run or continue the autonomous software factory, turn a goal into a hardened tracker issue plan, dispatch builder jobs, grade finished work…
Architect Fast
DanMcInerney/architect-loop
A skill your agent uses when the user asks to architect-fast a change, run the light factory lane, or factory-build a small goal — a few files, roughly one sitting, at most ~3 parallel issues — into…
Final Review
DanMcInerney/architect-loop
A skill your agent uses for the closing whole-run review in the architect factory — the only model review in the loop: dispatched by the orchestrator, at finish, to one fresh strategist subagent…
Frozen Checks
DanMcInerney/architect-loop
A skill your agent uses when the strategist drafts per-issue graded checks after decomposition and before builder dispatch.
Related
Categories
Questions about Codebase Design
What does Codebase Design do?
Shared vocabulary for designing deep modules and for naming factory concepts consistently. Codebase Design is an agent skill from DanMcInerney/architect-loop. Shared vocabulary for designing deep modules and for naming factory concepts consistently.
When should I use Codebase Design?
Codebase Design fits situations like: tasks that involve Skill authoring.
How do I install Codebase Design in Claude Code?
Run `npx skills add DanMcInerney/architect-loop --skill codebase-design -a claude-code`. Or copy the skill folder (skills/codebase-design in DanMcInerney/architect-loop) into .claude/skills/codebase-design in your project. Claude Code loads it when a task matches its description.
How do I install Codebase Design in Codex?
Run `npx skills add DanMcInerney/architect-loop --skill codebase-design -a codex`. Or copy the skill folder (skills/codebase-design in DanMcInerney/architect-loop) into .agents/skills/codebase-design in your project. Codex loads it when a task matches its description.
Can I use Codebase Design in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add DanMcInerney/architect-loop --skill codebase-design -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/codebase-design, .gemini/skills/codebase-design, .github/skills/codebase-design and .opencode/skills/codebase-design in your project.
What does Codebase Design need to run?
SKILL.md names no scripts, command-line tools or credentials: Codebase Design is instructions for the agent only.
Does Codebase Design access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Codebase Design safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Codebase Design use?
Codebase Design is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Codebase Design use?
About 1.5k tokens (SKILL.md is roughly 6.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Codebase Design?
Skills that share tags, products or a category with Codebase Design: Skill Creator (Azure/azqr, 795 stars), Claude Code Skill Developer Guide (diet103/claude-code-infrastructure-showcase, 10k stars), Darwin Skill Optimizer (alchaincyf/darwin-skill, 6.2k stars) and Claude Code Command Development (anthropics/claude-plugins-official, 38k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Codebase Design?
DanMcInerney (a GitHub user) maintains it in DanMcInerney/architect-loop, which has 626 GitHub stars. The repository holds 11 skills in this directory. The repository was last updated on September 13, 2026.
Source: DanMcInerney/architect-loop on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.