Borrowing it
Nothing to install: this file belongs to ahonn/dotfiles. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/ahonn/dotfiles/master/.claude/skills/codebase-design/SKILL.mdgit clone --depth 1 https://github.com/ahonn/dotfilesWrote 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.
[](https://agentmods.dev/skills/ahonn/dotfiles/codebase-design)<a href="https://agentmods.dev/skills/ahonn/dotfiles/codebase-design"><img src="https://agentmods.dev/badge/skills/ahonn/dotfiles/codebase-design/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/ahonn/dotfiles/codebase-design"><img src="https://agentmods.dev/badge/skills/ahonn/dotfiles/codebase-design.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00591 |
| Opus 5.5 | $0.00009 | $0.00236 |
| Sonnet 5.5 | $0.00005 | $0.00118 |
| Haiku 4.5 | $0.00002 | $0.00059 |
Grade A, and why
codebase-design 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 20d 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.
This is a copy
100% identical to codebase-design — 122 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codebase Design
Design modules that hide substantial behavior behind interfaces callers can understand. Judge a design by the knowledge and coordination it removes from callers, not by file counts or implementation length.
Use the project's established domain language. The vocabulary below supports reasoning; it does not forbid terms such as component, service, API, or boundary.
Working vocabulary
- Module: Code with an interface and an implementation, from a function to a package or feature.
- Interface: Everything callers must know: inputs, outputs, invariants, ordering, errors, configuration, and relevant performance constraints.
- Depth: Useful behavior exposed relative to the complexity callers must understand.
- Seam: A place where behavior can be substituted without editing its consumers.
- Adapter: A concrete implementation that connects a dependency at a seam.
- Locality: Related decisions and changes stay together instead of spreading across callers.
Design from the actual problem
Inspect callers, implementation, and dependencies before proposing a new interface. Identify the concrete cost: repeated policy, change amplification, unclear ownership, or difficult verification. Keep the existing design when a new abstraction would add more navigation or coordination than it removes.
- Hide implementation decisions and maintain invariants inside the module that owns them.
- Keep callers' common operations straightforward. Fewer methods are useful only when they reduce the contract callers must learn.
- Keep related behavior together. Do not split a coherent function or file merely to satisfy size targets.
- Introduce dependency injection where substitution, side-effect control, or an existing architectural boundary provides a concrete benefit. Do not invent a second adapter to justify an interface.
- Keep internal dependencies private unless callers need to supply or configure them.
- Prefer pure computation for domain decisions and explicit ownership for effects. An orchestration module may legitimately perform I/O.
- Consider removing a pass-through layer when it contributes no policy, isolation, or stable contract. A thin adapter may still be valuable for an external dependency.
What ships with it
3 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.
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.
- 20d ago Changed · -72 lines · -34 tokens per session 88e911797609
- 1mo ago First seen · 115 lines · 57 tokens per session scan A a8d50abac5a4
codebase-design is a skill published in the GitHub repository ahonn/dotfiles (63 stars, last pushed 6d ago), licensed MIT. It adds 23 tokens to every session and 591 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to codebase-design, differing in 122 lines, and is treated as a copy.
Other skills, from other repositories
pr-review
Intelligent PR code review with dynamic agent allocation based on change types. Analyzes PR changes and generates targeted review tasks.
analyze-pr
Analyze a GitHub/GitLab Pull Request by fetching its diff, reading its web description, and generating a comprehensive document. Use when the user provides a PR link and wants to understand what changes the PR introduces, or asks to review/analyze/summarize a pull request.
assess-quality
Foundational quality framework: the five questions (readable, easy to start, expands without bloat, consistent, intentional) every other dev skill is judged against, plus the dual-audience and workshop principles. Use when onboarding to a project, defining a quality bar, setting an assessment checklist, or arbitrating…
merge-ready
Drive an existing pull request to a mergeable state: get CI green, resolve merge conflicts with the base branch, address and resolve review comments, trigger required bot reviews/approvals (e.g. commenting '@claude review'), link associated issues, and clean up the PR title and description. Ends with a readiness…
check-project
Validate project structure against scaffold conventions -- check for required files, CI consistency, documentation completeness, sub-package/workspace members, and optional directory usage, reporting PASS/WARN/FAIL with fix suggestions. Use to audit an existing project or verify a scaffold was applied correctly. Do…
review-diff
Standardized review of the CURRENT working-tree changes -- staged, unstaged, and untracked -- against an explicit five-dimension rubric (correctness, security, tests, scope-creep, conventions). Emits a prioritized findings list, each with file:line, severity, and a suggested fix. Read-only: it reviews and reports, it…