agent-architecture
Skill0 starsChanged 2 months agoMITView on GitHub
Design role decomposition, message passing, shared state and failure isolation across agents. Use when designing autonomous agent state machines, memory, or loops.
12 other projects use a version of this.
Adopted by
Most recently taken up by
- taixuann/development-spacetheir own version, first seen Nov 8, 2026
- github/awesome-copilottheir own version, first seen Oct 25, 2026
- eshwarvijay/agent-architecturetheir own version, first seen Oct 25, 2026
- ruvnet/ruflotheir own version, first seen Oct 21, 2026
- ruvnet/claude-flowtheir own version, first seen Oct 8, 2026
- Sathvikar01/Agent-engineering-skillstheir own version, first seen Oct 5, 2026
Other versions12 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 12
- ruvnet/claude-flow★ 80ksame name
- ruvnet/ruflo★ 79ksame name
- github/awesome-copilot★ 41ksame name
- eshwarvijay/agent-architecture★ 9same name
- Sathvikar01/Agent-engineering-skills★ 3same name
- mattstruble/skills★ 2same name
- Zekiog/ruflo★ 2same name
- fidgetcoding/fidgetflo★ 1same name
- jpoindexter/theft-kit★ 1same name
- Soulcynics404/AgentForge★ 1same name
2 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.
- agent-identitySkill
- agent-orchestrationSkill
- agent-safetySkill
- automation-reviewSkill
- composioSkill
- create-skillSkill
- document-generationSkill
- mcp-builderSkill
- n8nSkill
- prompt-engineeringSkill
- prompt-librarySkill
- rag-systemsSkill
- report-automationSkill
- skill-linterSkill
- trigger-devSkill
- workflow-mappingSkill
The file
We split this skill into the rules it gives an agent
4 rules. 0 are common, 4 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 12 edited versions we read keep these.
4
Distinctive
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 20
Make the trace reconstructable: When output is wrong, you need to see which agent decided what, with what input.
- Distinctive: line 38
NEVER weaken or skip a failing test to make a change land.
- Distinctive: line 39
NEVER swallow errors silently or leave unhandled rejections in production paths.
- Distinctive: line 40
NEVER introduce a breaking API change without a version bump and migration path.
“Common” is measured: kept by at least 6 in 10 of the 12 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
Agent Architecture
Design multi-agent systems where coordination does not become the failure mode.
Process
- Justify the second agent. Most tasks that look multi-agent are one agent with better tools. Split only when roles need genuinely different context or run concurrently.
- Decompose by context boundary, not by job title. An agent exists to hold a distinct working set, not to mirror an org chart.
- Define the contract between agents — the exact shape of what is passed, and what is guaranteed about it. Free-text handoff is where multi-agent systems lose information.
- Decide where state lives. Shared mutable state between agents needs the same care as between threads.
- Isolate failure. One agent failing or looping must not stall the others; set timeouts and a supervisor that can terminate.
- Make the trace reconstructable. When output is wrong, you need to see which agent decided what, with what input.
- Bound the total cost. Agents that can spawn agents need a hard ceiling.
Deliverables
- Role decomposition with the context boundary justifying each agent
- Message contracts between agents
- Failure isolation, timeouts and supervision model
- Trace format and cost ceiling
Verification & Quality Checklist
- Code compiles and all automated tests and typechecks pass without new warnings.
- Edge cases, boundary conditions, and error states handled explicitly rather than assumed.
- No hardcoded secrets, credentials, or insecure defaults introduced.
- Changes are covered by a test that fails without them.
Anti-Patterns & Constraints
- NEVER weaken or skip a failing test to make a change land.
- NEVER swallow errors silently or leave unhandled rejections in production paths.
- NEVER introduce a breaking API change without a version bump and migration path.
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.