project-architecture
Skill119 starsChanged 5 months agoMITView on GitHub
Foundational rules and layout for the declarative agent platform. Read this before any change, regardless of area; it anchors every other skill.
7 other projects use a version of this.
Adopted by
Most recently taken up by
- luigi-dv/react-ts-vitetheir own version, first seen Oct 20, 2026
- BidingCC/BuildingAItheir own version, first seen Oct 8, 2026
- marwan562/agents-skillstheir own version, first seen Sep 19, 2026
- sebas8824/sdd-harnesstheir own version, first seen Aug 24, 2026
- Jithnkn/project-architecturetheir own version, first seen Aug 20, 2026
- fqmyysjjd/agent-feedtheir own version, first seen May 9, 2026
Other versions7 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 7
- BidingCC/BuildingAI★ 1.9ksame name
- Jithnkn/project-architecture★ 8same name
- marwan562/agents-skills★ 8same name
- fqmyysjjd/agent-feed★ 4same name
- luigi-dv/react-ts-vite★ 1same name
- sebas8824/sdd-harness★ 1same name
- thetruong1099/android-mvi-base-code★ 0same 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 repository16 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- architecture-reviewSkill
- code-reviewSkill
- documentationSkill
- git-workflowSkill
- mcp-toolsSkill
- prompt-renderingSkill
- refactoringSkill
- runtime-engineSkill
- senior-python-engineeringSkill
- sidecar-auth-contextSkill
- skill-authoringSkill
- testingSkill
- vercel-react-best-practicesSkill
- yaml-schemaSkill
The file
We split this skill into the rules it gives an agent
6 rules. 0 are common, 4 are distinctive, and 2 are very specific to this project.
0
Common
Most of the 6 edited versions we read keep these.
4
Distinctive
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 10
Do not edit this file directly.
- Distinctive: line 18
Always. Read this before any change, regardless of area.
- Very specific: line 44
Follow the planned package layout in AGENTS.md (src/agentplatform/<layer>).
- Distinctive: line 45
No giant single-file modules.
- Distinctive: line 46
Keep each module to one architectural responsibility.
- Distinctive: line 49
Do not change public contracts (YAML schema, plugin contracts, API shape) without an ADR and approval.
“Common” is measured: kept by at least 6 in 10 of the 6 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.
Files
<!--
This file is generated by tools/skills.
Do not edit this file directly.
Edit .ai/skills/project-architecture.md and run `make generate-ai`.
-->Skill: Project Architecture
When to use this skill
Always. Read this before any change, regardless of area. It anchors every other skill in the project's non-negotiable rules and layout.
Files to read first
AGENTS.mddocs/ARCHITECTURE.mddocs/ROADMAP.mddocs/adr/
Architecture rules
- The pipeline is one-directional:
config.yml → validate → compile → CompiledAgentGraph → RuntimeEngine → ExecutionContext (per request) → execution → response + trace. - YAML is declarative specification, never executable business logic.
- Validate before compile; compile before run. The runtime sees only compiled, typed models — never raw YAML dicts.
RuntimeEngineis created once at startup;ExecutionContextis per request.- Client-specific auth/business logic lives in customer plugins, not the runtime.
- Prompts are templates rendered per request; security is enforced at the tool/data layer, not via prompt text.
- Secrets never live in YAML or prompts.
Implementation rules
- Follow the planned package layout in
AGENTS.md(src/agentplatform/<layer>). No giant single-file modules. - Keep each module to one architectural responsibility.
- Respect layer boundaries: a layer depends only on the typed outputs of the layers before it.
- Do not change public contracts (YAML schema, plugin contracts, API shape) without an ADR and approval.
- Stay within the current task's scope; propose new tasks for discovered work.
Validation checklist
- Change fits the layered architecture and the planned layout.
- No architecture rule from
AGENTS.md§3 is violated. - No contract changed without an ADR.
- Tests added for new behavior.
make checkpasses.
Common mistakes to avoid
- Reading raw YAML in the runtime instead of compiled models.
- Adding request state to
RuntimeEngineor the compiled graph. - Putting customer auth/business logic in the runtime.
- Expanding scope beyond the current task or doing large uncontrolled rewrites.
- Relying on prompt wording for security.
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.