dynamic-workflows
Skill1 starsChanged 30 days agoMITView on GitHub
Instructions for the upstream workflow: Orchestration patterns for efficient agents — classify and act, fan out and synthesize, adversarial verification, generate and filter, tournament — each addressing one of three failure modes: agent laziness (declares more than it does), self-preference (judging its own work) and goal drift (losing the objective in a long session). Use when designing or debugging a multi-agent workflow rather than a single call. Not for the retroactive-loop controller — use loop-optimizer; not for the parallel review of one diff — use simplify-code; not for delegating a task — use the agent delegation surface.
5 other projects use a version of this.
Adopted by
Most recently taken up by
- TheBeardedBearSAS/claude-crafttheir own version, first seen Oct 29, 2026
- cubetribe/ClaudeCode_GodMode-Ontheir own version, first seen Oct 13, 2026
- tharanee-bit/Codex-Dynamic-Workflowstheir own version, first seen Jul 16, 2026
- donovan-yohan/hermes-plugin-dynamic-workflowstheir own version, first seen Jul 3, 2026
- cs50victor/dynamic_workflows_mcptheir own version, first seen Jun 7, 2026
Other versions5 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 5
- TheBeardedBearSAS/claude-craft★ 108same name
- cubetribe/ClaudeCode_GodMode-On★ 53same name
- donovan-yohan/hermes-plugin-dynamic-workflows★ 2same name
- tharanee-bit/Codex-Dynamic-Workflows★ 1same name
- cs50victor/dynamic_workflows_mcp★ 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 repository114 other files it gives its agents.
- agent-cacheSkill
- agent-compressionSkill
- agent-intelSkill
- agent-overlapSkill
- agent-stateSkill
- ambient-hudSkill
- app-testSkill
- audit-dagSkill
- auto-distillSkill
- auto-memorySkill
- auto-routerSkill
- benchSkill
- bootstrapSkill
- botte-learnSkill
- botte-nnSkill
- botte-proxySkill
- botte-wrapSkill
- cacheSkill
- call-chainsSkill
- capabilitiesSkill
- cardinalSkill
- checkupSkill
- clarificationSkill
- clusterSkill
- code-complexitySkill
- code-duplicationSkill
- code-fingerprintSkill
- code-rulesSkill
- code-stateSkill
- code-wrappersSkill
- comfyuiSkill
- completion-proofSkill
- conductorSkill
- context-budgetSkill
- context-compressorSkill
- context-profilerSkill
- context-slicerSkill
- context-windowsSkill
- control-loopSkill
- cost-estimatorSkill
- dag-optimizerSkill
- dashboardSkill
- decision-ladderSkill
- demoSkill
- diff-languageSkill
- directives-auditSkill
- docgenSkill
- docs-stewardSkill
- efficiencySkill
- eventsSkill
- fallow-likeSkill
- fallowSkill
- fast-contextSkill
- fixSkill
- fleetSkill
- hailo-visionSkill
- harness-deltaSkill
- harvestSkill
- hermes-bridgeSkill
- hermes-second-brainSkill
- The first 60 shown.
The file
Files
Dynamic Workflows — patterns for efficient agents
Package scope and prerequisites
This catalog ships instructions, not the executable runtime. Python modules, scripts, local services and optional tools named below must be installed separately from the upstream project. Check their availability before running commands; if they are missing, explain the prerequisite instead of claiming execution or results. The host agent may use model tokens while following these instructions.
Purpose
A catalogue of composition patterns, each mapped to the failure mode it fixes. The underlying idea is a harness per task: the shape of the orchestration should match the task, not be fixed for everything.
The full upstream pattern catalog is in PATTERNS.md, which is not included here. Obtain it from the upstream project before claiming to apply its complete procedure; if absent, explain that limitation.
When NOT to use
- You need the loop controller and its stop reasons — use loop_optimizer.
- You need one diff reviewed by several narrow reviewers — use simplify-code.
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.