Skip to content

yeaight7/agent-powerups / plugins/dev-vitals/skills/agent-runtime-patterns

agent-runtime-patterns

Verified

Use when optimizing agent runtime loops, card packs, MCP session lifecycle, tool-call count, or multi-agent orchestration patterns.

FileKindSize
SKILL.mdskill md3.1 KB
references/runtime-patterns.mdmarkdown1.2 KB

references/runtime-patterns.md

View on GitHub
# Runtime Patterns

## Pattern Selection

| Problem | Pattern |
| --- | --- |
| repeated broad search | bounded search subagent/card |
| long system prompt | compact card pack |
| specialist subtasks | agents-as-tools |
| sequential multi-step workflow | chain |
| ambiguous routing | router |
| independent subtasks | orchestrator-worker |
| server state needed | explicit MCP session lifecycle |

## Measurement

Track before/after:

- tool calls
- LLM calls
- elapsed time
- prompt/context size
- failure rate
- number of user clarifications

## Card Rules

- Card is high-signal operating guidance, not full docs.
- One card owns one behavior.
- Include trigger, constraints, and done criteria.
- Avoid putting secrets or local machine paths in cards.

## MCP Session Lifecycle

1. Create session.
2. Attach session id via request metadata.
3. Verify stateful tool behavior.
4. Handle "session not found" by recreating or stopping.
5. Delete session or document intentional persistence.

## Anti-Patterns

- Adding orchestration to avoid clarifying requirements.
- Hiding slow tools behind more agents.
- Persisting state with no cleanup rule.
- Measuring token reduction only, ignoring task quality.
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 468kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 321kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 321kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 321kUpdated Claude CodeCodexVerifiedInstall