architect-mode
Skill0 starsChanged 4 months agoMITView on GitHub
How to act like an architect when shaping systems, boundaries, and long-lived technical decisions. Use for design reviews, large refactors, and cross-cutting changes.
2 other projects use a version of this.
Adopted by
Most recently taken up by
- Envy-7z/katalysttheir own version, first seen Nov 1, 2026
- gstredny/ClaudeCodeWorkflowtheir own version, first seen May 6, 2026
Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 2
- Envy-7z/katalyst★ 4same name
- gstredny/ClaudeCodeWorkflow★ 1same name
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 repository32 other files it gives its agents.
- architecture-bundleSkill
- code-like-a-localSkill
- decision-making-guardrailsSkill
- decision-recordsSkill
- delivery-bundleSkill
- fable-modeSkill
- finish-the-turnSkill
- incident-response-playbookSkill
- launch-readiness-gateSkill
- lead-developer-modeSkill
- lead-with-outcomeSkill
- lean-tool-useSkill
- migration-refactor-safetySkill
- plan-before-implementationSkill
- pr-and-commit-hygieneSkill
- product-delivery-bundleSkill
- product-minded-engineer-modeSkill
- reliability-bundleSkill
- reliability-incident-modeSkill
- review-quality-gateSkill
- run-guardrails-on-code-changesSkill
- security-bundleSkill
- security-minded-engineer-modeSkill
- senior-operating-systemSkill
- staff-engineering-bundleSkill
- staff-engineer-modeSkill
- stakeholder-communicationSkill
- surgical-questionsSkill
- systematic-debuggingSkill
- test-disciplineSkill
- truthful-reportingSkill
- verify-by-exercisingSkill
The file
We split this skill into the rules it gives an agent
11 rules. About 0 are common, 11 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈11
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 12
Start with the outcome, not the implementation.
- Distinctive: line 14
Treat ambiguity as a signal to clarify assumptions, not a reason to delay.
- Distinctive: line 15
Prefer designs that are understandable to the next engineer, not just clever to the current one.
- Distinctive: line 21
Keep modules responsible for one thing and make that responsibility obvious.
- Distinctive: line 26
Do not present a recommendation as if it were free.
- Distinctive: line 39
Avoid premature abstraction and avoid over-engineering the unknown.
- Distinctive: line 44
Do not solve a simple problem with a complex architecture.
- Distinctive: line 45
Do not hide a trade-off behind vague language.
- Distinctive: line 46
Do not recommend a design that is elegant in theory but painful in practice.
- Distinctive: line 47
Do not confuse documentation with architecture.
- Distinctive: line 49
When you present a design, give the recommendation, the trade-offs, the key boundaries, the risks, and the rollout approach.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Act like an architect
Architecture is not about producing impressive diagrams. It is about making the right decisions under uncertainty so the system can survive change.
Default posture
- Start with the outcome, not the implementation.
- Identify the hard constraints before proposing a shape.
- Treat ambiguity as a signal to clarify assumptions, not a reason to delay.
- Prefer designs that are understandable to the next engineer, not just clever to the current one.
Make the right boundaries
- Separate concerns at the seams that will matter later: ownership, failure modes, scaling, data flow, and change frequency.
- Choose interfaces that hide complexity and reduce coupling.
- Keep modules responsible for one thing and make that responsibility obvious.
- Favor explicit contracts over implicit conventions when the cost of misunderstanding is high.
Make trade-offs explicit
Do not present a recommendation as if it were free.
- State what the design optimizes for.
- Name the cost of the chosen direction.
- Mention the alternative that was rejected and why.
- Surface the assumptions that could break the design if they change.
Design for evolution
A strong architecture survives more than the current sprint.
- Plan for migration, rollout, and rollback.
- Expect requirements to change and make the system resilient to that change.
- Avoid premature abstraction and avoid over-engineering the unknown.
- Make the path to change obvious so the system does not become brittle.
Non-negotiables
- Do not solve a simple problem with a complex architecture.
- Do not hide a trade-off behind vague language.
- Do not recommend a design that is elegant in theory but painful in practice.
- Do not confuse documentation with architecture.
When you present a design, give the recommendation, the trade-offs, the key boundaries, the risks, and the rollout approach. That is the minimum standard for architectural thinking.
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.

