codebase-design
Skill133 starsChanged 3 months agoAGPL-3.0View on GitHub
Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable or AI-navigable, or when another skill needs the deep-module vocabulary.
250 other projects use a version of this, 99 of them edited; 23 of 95 edited versions we compared changed its rules; 21 new projects in the last 4 weeks, against 18 the 4 before.
How people change it
23 of 95 edited versions changed its rules, and some changes recur.
Of the 95 edited versions we compared: 72 keep every rule, 23 made changes of their own.
Rules people drop
- Use these terms exactly: don't substitute "component," "service," "API," or "boundary." Consistent language is the whole point.dropped by 11 of 23
- When designing an interface, ask:dropped by 7 of 23
Rules people add
- Don't introduce a seam unless something actually varies across it.added by 2 of 23
- Use these terms consistently where their distinctions matter.added by 2 of 23
- Prefer returning results to side effects when that keeps the interface simpler.added by 2 of 23
- Keep the surface small: fewer methods and parameters mean fewer, simpler tests.added by 2 of 23
- Agents copy existing patterns, including bad ones. Write golden principles as opinionated, mechanical rules in the repository. Correct drift against them continuously with small, targeted refactors. …added by 2 of 23
- Do not prompt harder.added by 2 of 23
- Give one command family one default mode. Do not let some commands write by default while others only check. State the default mode, the paths written, and the side effects in help text.added by 2 of 23
- When applying this vocabulary to a design or review, report the recommended module, interface, and seam. In that design or review, explain how the result improves depth, leverage, locality, or testability. …added by 2 of 23
We split this file and each edited version into the rules they give an agent and match them by wording. A version that adds no rule of its own and has not changed since this file last did reads as an older text, so what it lacks is not counted as dropped. We keep no past texts of a file, so that is inferred, and an edited version that started from an older text still counts its gaps as drops.
Adopted by
Rising: 21 new projects took it in the last 4 weeks, 1.2× the 4 weeks before.
Most recently taken up by
- bepaldes/heimdall-agentword for word, first seen Nov 16, 2026
- philoserf/claude-code-configedited, first seen Nov 15, 2026
- Binbin-miao/workbuddy-expert-teamtheir own version, first seen Nov 15, 2026
- adelrodriguez/skillstheir own version, first seen Nov 15, 2026
- theishandubey/dotclaudeword for word, first seen Nov 15, 2026
- geoffbremner/skillsword for word, first seen Nov 15, 2026
Used with
Projects with it also use setup-ts-deep-modules, decision-mapping and 10 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
liufeng1976Skillsetup-ts-deep-modules
Wire dependency-cruiser into a TypeScript repo so each package is a deep module — implementation hidden in subfolders, reachable only through its entry-point files. User-invoked.
Also in 43 projects that use this
FabienDehopreSkilldecision-mapping
Turn a loose idea into a sequenced map of investigation tickets, then drive them to resolution one at a time.
Also in 8 projects that use this
RoentekSkillloop-me
Grill me about specs for the workflows I want to build, within this workspace.
Also in 55 projects that use this
LesaniSkillwriting-beats
Shape an article as a journey of beats, choose-your-own-adventure style. The user picks a starting beat from the raw material, you write only that beat, then offer options for where to pivot next, beat by beat, until the article reaches a natural end. Use when the user has raw material and wants to assemble it as a narrative rather than an argument.
Also in 58 projects that use this
AWSSkillto-questionnaire
Turn a decision you can't fully answer into a questionnaire for someone else to fill in.
Also in 90 projects that use this
LesaniSkillwriting-shape
Take a markdown file of raw material and shape it into an article through a conversational session — drafting candidate openings, growing the piece paragraph by paragraph, arguing about format (lists, tables, callouts, quotes) at each step. Use when the user has a pile of notes, fragments, or a rough draft and wants help turning it into something publishable.
Also in 58 projects that use this
- +1 more from Lesani
Other versions250 projects use a version of this.
Word for word · 126
- mattpocock/skills★ 325k100% same
- QuivrHQ/quivr★ 40k100% same
- The-Vibe-Company/quivr★ 40k100% same
- MODSetter/SurfSense★ 17k100% same
- formbricks/formbricks★ 13k100% same
- ArcReel/ArcReel★ 6.6k100% same
- withcoral/coral★ 4.9k100% same
- epam/ketcher★ 932100% same
- moeru-ai/xsai★ 667100% same
- mxyhi/ok-skills★ 511100% same
116 more not listed
Edited · 99
- danny-avila/LibreChat★ 47k100% same
- LibreChat-AI/LibreChat★ 47k100% same
- windmill-labs/windmill★ 19k96% same
- GreyDGL/PentestGPT★ 16k100% same
- humanlayer/humanlayer★ 13k100% same
- openstatusHQ/openstatus★ 9.3k100% same
- vinvcn/mattpocock-skills-zh-CN★ 5.8k16% same
- bestofjs/bestofjs★ 3.1k100% same
- mdiri-ai/SoduWork★ 93094% same
- nodetool-ai/nodetool★ 63797% same
89 more not listed
Wrote their own version · 25
- stevesolun/ctx★ 583same name
- devcxl/mattpocock-skills-zh★ 543same name
- OyadotAI/oya-browser★ 349same name
- ahonn/dotfiles★ 62same name
- sgaabdu4/building-flutter-apps★ 25same name
- kriscard/Skills★ 15same name
- eralmansouri/skills★ 9same name
- imMamdouhaboammar/matts-skills-into-chatgpt★ 8same name
- Boom-Vitt/skills-thai★ 5same name
- KroxiDev/engineering-skills★ 4same name
15 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository16 other files it gives its agents.
- AGENTS.mdAGENTS.md
- adversarial-reviewerSkill
- architecture-blueprint-generatorSkill
- code-reviewSkill
- domain-modelingSkill
- electronSkill
- grillingSkill
- grill-with-docsSkill
- handoffSkill
- implementSkill
- pr-review-handlerSkill
- svelte5-best-practicesSkill
- sveltekit-svelte5-tailwind-skillSkill
- tddSkill
- to-specSkill
- to-ticketsSkill
The file
We split this skill into the rules it gives an agent
2 rules. 2 are common, 0 are distinctive, and 0 are very specific to this project.
2
Common
Most of the 111 edited versions we read keep these.
0
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
Licensed with conditions — read it at the source. We count its rules but don't quote them. Read them on GitHub.
“Common” is measured: kept by at least 6 in 10 of the 111 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

