Agent skill

Dynamic Workflows

by TheBeardedBearSAS in TheBeardedBearSAS/claude-craft

Orchestrate dozens-to-hundreds of subagents from a script Claude writes (Claude Code Dynamic Workflows, trigger ultracode).

MITAuto-check passedAgent Workflows

Install Dynamic Workflows

skills CLI
$ npx skills add TheBeardedBearSAS/claude-craft --skill dynamic-workflows -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install TheBeardedBearSAS/claude-craft dynamic-workflows --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/TheBeardedBearSAS/claude-craft.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/dynamic-workflows .claude/skills/dynamic-workflows && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
dynamic-workflows
GitHub stars
107
Token cost
~1.4k tokens
SKILL.md length
554 words
Files
1
Skills in repo
12
Repo updated
First seen
Licence
MIT

At a glance

Orchestrate dozens-to-hundreds of subagents from a script Claude writes (Claude Code Dynamic Workflows, trigger ultracode).

  • A task exceeds a single agents context
  • SKILL.md covers Quand l'utiliser — les 3…, Patterns composables (prompts…, Squelette type (review → verify) and Monitoring, plus 2 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
  • Needs more than ~4 concurrent workers — large audits

What it does

Dynamic Workflows is an agent skill from TheBeardedBearSAS/claude-craft. Orchestrate dozens-to-hundreds of subagents from a script Claude writes (Claude Code Dynamic Workflows, trigger ultracode). Use when a task exceeds a single agent's context or needs more than ~4 concurrent workers — large audits, migrations, multi-source research, fan-out reviews. Distinct from Agent Teams (synchronous, ≤4 workers) and ralph-run (sequential single-context loop).

Its SKILL.md is about 1.4k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Agent Workflows, covering Subagents and Deep research. The repository describes itself as: Supercharge Claude Code with Expert Knowledge A comprehensive framework for AI-assisted development. Install standardized rules, agents, and commands for your projects across… The licence is MIT.

When your agent uses it

  • A task exceeds a single agents context
  • Needs more than ~4 concurrent workers — large audits
  • Multi-source research
  • Fan-out reviews

Example prompts

  • “/dynamic-workflows”

What it can do on your machine

Read from SKILL.md and the folder at commit 99c1ee3. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are javascript).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Links to these hosts (documentation or services it may open):

    • code.claude.com

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Dynamic Workflows loads about 1.4k tokens when it runs. Until then it costs about 100 tokens; SKILL.md has 554 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~100
When it runs · the whole SKILL.md, loaded when a task matches
~1.4k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from TheBeardedBearSAS/claude-craft at commit 99c1ee3, republished under its MIT licence (© TheBeardedBearSAS). 554 words, ~1,365 tokens.

Download SKILL.mdSave it as .claude/skills/dynamic-workflows/SKILL.md (or your agent's skills folder).
name
dynamic-workflows
description
Orchestrate dozens-to-hundreds of subagents from a script Claude writes (Claude Code Dynamic Workflows, trigger `ultracode`). Use when a task exceeds a single agent's context or needs more than ~4 concurrent workers — large audits, migrations, multi-source research, fan-out reviews. Distinct from Agent Teams (synchronous, ≤4 workers) and ralph-run (sequential single-context loop).
context
fork

Dynamic Workflows — orchestration multi-agents scriptée

Dynamic Workflows (Claude Code 2.1.154+, mot-clé déclencheur ultracode) laissent Claude écrire un script JavaScript qui orchestre des sous-agents de façon déterministe (boucles, conditions, fan-out). Le script tourne en arrière-plan ; on suit l'exécution via /workflows.

⚠️ Opt-in coûteux : un workflow peut lancer des dizaines à centaines de sous-agents. Ne l'utiliser que sur demande explicite (mot « ultracode », « use a workflow », « fan out agents ») ou quand le palier de complexité ci-dessous est franchi.

Quand l'utiliser — les 3 paliers d'orchestration

PalierOutilConcurrenceQuand
1Sub-agent simple (Task/Agent)1Une investigation isolée, garder le contexte principal propre
2Agent Teams (/team:audit, /team:sprint, /team:security)1 leader + ~3 workersTravail parallèle borné, synchrone, qui tient en un round
3Dynamic Workflows (ultracode)jusqu'à ~1000 sous-agents (cap concurrent ~16)La tâche dépasse le contexte d'un agent OU exige >4 workers OU une boucle/pipeline déterministe

Heuristique break-even : dès que tu écrirais « lance N agents, puis pour chacun fais X, puis agrège » — c'est un workflow. Si N ≤ 4 et une seule passe suffit, reste sur Agent Teams.

Patterns composables (prompts minimaux)

  • Fan-out & synthesize — N lecteurs en parallèle sur des sous-systèmes disjoints → un agent synthétise. (audit, cartographie de code)
  • Adversarial verification — chaque finding passé à ≥1 sceptique chargé de le réfuter ; ne garder que les CONFIRMED. Le pattern qualité le plus important pour la génération autonome.
  • Generate-and-filter — générer large (idées, candidats), puis filtrer par un juge.
  • Classify-and-act — un classifieur route chaque item vers le traitement adapté.
  • Pipeline — chaque item traverse toutes les étapes sans barrière (latence = pire chaîne, pas somme des étapes). C'est le défaut multi-étapes.
  • Loop-until-done / loop-until-dry — relancer des chercheurs jusqu'à K rounds sans nouveauté (découverte de taille inconnue : bugs, edge cases).

Squelette type (review → verify)

js
const results = await pipeline(
  DIMENSIONS,
  d => agent(d.prompt, { phase: 'Review', schema: FINDINGS }),
  review => parallel(review.findings.map(f => () =>
    agent(`Adversarially verify: ${f.title}. Default refuted=true if unsure.`,
          { phase: 'Verify', schema: VERDICT }).then(v => ({ ...f, verdict: v }))))
)
const confirmed = results.flat().filter(Boolean).filter(f => f.verdict?.isReal)

pipeline() par défaut (pas de barrière) ; parallel() seulement quand l'étape N a besoin de TOUS les résultats de N-1 (dédup, early-exit, comparaison croisée). schema force une sortie structurée validée. Pour des éditions concurrentes de fichiers, isolation: 'worktree'.

Show full SKILL.md (236 more words)Show less

Monitoring

  • /workflows : progression live (phases, agents, tokens).
  • Le script revient avec un résultat agrégé ; lire ce résultat, décider la suite (souvent plusieurs workflows en séquence : comprendre → concevoir → implémenter → revoir).

À ne pas confondre

  • ralph-run (/common:ralph-run) : boucle séquentielle mono-contexte jusqu'à une DoD — pas de parallélisme. Pour une tâche qui dépasse ce modèle, basculer sur un Dynamic Workflow.
  • /effort ultracode : palier d'effort CLI (débit code max sur Opus 4.8) — orthogonal au déclencheur ultracode des workflows, même si souvent utilisés ensemble.

Réutilisation & garde-fous (v2.1.166+)

  • Essayer d'abord le workflow intégré /deep-research (recherche multi-sources vérifiée) avant d'en écrire un : beaucoup de besoins « fan-out web + synthèse » y sont déjà couverts.
  • Sauvegarder un run éprouvé : dans /workflows, presser s enregistre le script comme commande réutilisable — projet (.claude/workflows/) ou perso (~/.claude/workflows/). Un paramètre args permet de le rejouer avec une entrée différente (question de recherche, chemin cible…).
  • ⚠️ Sécurité — acceptEdits implicite : les sous-agents lancés par un workflow tournent toujours en mode acceptEdits et héritent de ton allowlist, quel que soit le mode de la session (y compris plan ou default). Les éditions de fichiers sont auto-approuvées. Ne fan-out des agents qui écrivent qu'en zone maîtrisée (worktree isolé, cf. règle 11 sur l'hygiène des permissions).
  • Coupe-circuit & coût : disableWorkflows (settings.json) ou CLAUDE_CODE_DISABLE_WORKFLOWS=1 désactivent la fonctionnalité ; /workflows affiche la consommation de tokens en direct (un workflow coûte significativement plus qu'un contexte unique — piloter avec un budget explicite).

Référence : Claude Code Workflows · voir aussi @.claude/commands/common/sub-agents-patterns.md (tableau comparatif des orchestrations).

© TheBeardedBearSAS, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .claude/skills/dynamic-workflows of TheBeardedBearSAS/claude-craft.

Open the folder on GitHubat commit 99c1ee3

Compare with similar skills

Dynamic Workflows next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Dynamic Workflows compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Dynamic Workflows this skillTheBeardedBearSAS/claude-craft107—~1.4kAutomated safety check: PassMIT
Codebase Research Passbbartling/open-fdd172—~1.4kAutomated safety check: PassCustom licence
Claw Multi AgentLeoYeAI/openclaw-master-skills2.2k—~5.5kAutomated safety check: PassMIT
Research Trackersundial-org/awesome-openclaw-skills663—~1kAutomated safety check: PassNone
Advanced Swarm Orchestrationruvnet/agentic-flow8165 repos~5.9kAutomated safety check: PassNone
Synthesisyologdev/yoyo-evolve1.9k—~3.1kAutomated safety check: PassMIT

Similar skills

  • Codebase Research Pass

    bbartling/open-fdd

    A skill your agent uses for structured research on an unfamiliar or complex codebase before planning, reviewing, or editing.

    172 GitHub stars~1.4k tokensUpdated today
    Agent WorkflowsAuto-check passed
  • Claw Multi Agent

    LeoYeAI/openclaw-master-skills

    Multi-agent parallel orchestration for OpenClaw. An agent skill from LeoYeAI/openclaw-master-skills.

    2.2k GitHub stars~5.5k tokensUpdated 2 mo ago
    Agent WorkflowsAuto-check passed
  • Research Tracker

    sundial-org/awesome-openclaw-skills

    Manage autonomous AI research agents with SQLite-based state tracking.

    663 GitHub stars~1k tokensUpdated 7 mo ago
    Agent WorkflowsAuto-check passed
  • Advanced Swarm Orchestration

    ruvnet/agentic-flow

    Patterns for running multi-agent swarms on research, development and testing work, with four topologies and a four-phase research swarm built on claude-flow MCP tools.

    816 GitHub starsUsed in 5 repos~5.9k tokens
    Agent WorkflowsAuto-check passed
  • Synthesis

    yologdev/yoyo-evolve

    Multi-source research synthesis — aggregate and compare 3+ sources or any source 5KB using sub-agent dispatch and SharedState

    1.9k GitHub stars~3.1k tokensUpdated today
    Agent WorkflowsAuto-check passed
  • Web Research

    Juncai22/spring-ai-agent-learning

    A skill your agent uses for requests related to web research; it provides a structured approach to conducting comprehensive web research

    123 GitHub starsUsed in 3 repos~1.1k tokens
    Research & ScienceAuto-check passed

More from TheBeardedBearSAS/claude-craft

All 12 skills in this repo
  • Architect

    TheBeardedBearSAS/claude-craft

    Phase d'architecture systématique AVANT le code (TDD). An agent skill from TheBeardedBearSAS/claude-craft.

    107 GitHub stars~1.2k tokensUpdated 23 days ago
    Auto-check passed
  • Async

    TheBeardedBearSAS/claude-craft

    Architecture async-first avec messaging et queues (Symfony Messenger, Laravel Queue, Ecotone).

    107 GitHub stars~741 tokensUpdated 23 days ago
    Auto-check passed
  • Atomic Tasks

    TheBeardedBearSAS/claude-craft

    Pattern GSD (Get Shit Done) - découper en tâches atomiques avec contextes subagent frais pour combattre le context rot.

    107 GitHub stars~1.1k tokensUpdated 23 days ago
    Auto-check passed
  • Cqrs

    TheBeardedBearSAS/claude-craft

    CQRS - Command Query Responsibility Segregation. An agent skill from TheBeardedBearSAS/claude-craft.

    107 GitHub stars~833 tokensUpdated 23 days ago
    Auto-check passed
  • Design Md Convention

    TheBeardedBearSAS/claude-craft

    Convention DESIGN.md pour design systems AI-friendly. An agent skill from TheBeardedBearSAS/claude-craft.

    107 GitHub stars~1.1k tokensUpdated 23 days ago
    Auto-check passed
  • Docker Hadolint

    TheBeardedBearSAS/claude-craft

    Docker & Hadolint validation (2026). An agent skill from TheBeardedBearSAS/claude-craft.

    107 GitHub stars~498 tokensUpdated 23 days ago
    Auto-check passed

Categories

Questions about Dynamic Workflows

What does Dynamic Workflows do?

Orchestrate dozens-to-hundreds of subagents from a script Claude writes (Claude Code Dynamic Workflows, trigger ultracode). Dynamic Workflows is an agent skill from TheBeardedBearSAS/claude-craft. Orchestrate dozens-to-hundreds of subagents from a script Claude writes (Claude Code Dynamic Workflows, trigger ultracode).

When should I use Dynamic Workflows?

Dynamic Workflows fits situations like: A task exceeds a single agents context; needs more than ~4 concurrent workers — large audits; multi-source research; fan-out reviews.

How do I install Dynamic Workflows in Claude Code?

Run `npx skills add TheBeardedBearSAS/claude-craft --skill dynamic-workflows -a claude-code`. Or copy the skill folder (.claude/skills/dynamic-workflows in TheBeardedBearSAS/claude-craft) into .claude/skills/dynamic-workflows in your project. Claude Code loads it when a task matches its description.

How do I install Dynamic Workflows in Codex?

Run `npx skills add TheBeardedBearSAS/claude-craft --skill dynamic-workflows -a codex`. Or copy the skill folder (.claude/skills/dynamic-workflows in TheBeardedBearSAS/claude-craft) into .agents/skills/dynamic-workflows in your project. Codex loads it when a task matches its description.

Can I use Dynamic Workflows in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add TheBeardedBearSAS/claude-craft --skill dynamic-workflows -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/dynamic-workflows, .gemini/skills/dynamic-workflows, .github/skills/dynamic-workflows and .opencode/skills/dynamic-workflows in your project.

What does Dynamic Workflows need to run?

SKILL.md names no scripts, command-line tools or credentials: Dynamic Workflows is instructions for the agent only.

Does Dynamic Workflows access the network?

SKILL.md names 1 domain. As links in the text: code.claude.com. This is read from the text; nothing was executed.

Is Dynamic Workflows safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Dynamic Workflows use?

Dynamic Workflows is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Dynamic Workflows use?

About 1.4k tokens (SKILL.md is roughly 5.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Dynamic Workflows?

Skills that share tags, products or a category with Dynamic Workflows: Codebase Research Pass (bbartling/open-fdd, 172 stars), Claw Multi Agent (LeoYeAI/openclaw-master-skills, 2.2k stars), Research Tracker (sundial-org/awesome-openclaw-skills, 663 stars) and Advanced Swarm Orchestration (ruvnet/agentic-flow, 816 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Dynamic Workflows?

TheBeardedBearSAS (a GitHub organization) maintains it in TheBeardedBearSAS/claude-craft, which has 107 GitHub stars. The repository holds 12 skills in this directory. The repository was last updated on September 14, 2026.

Source: TheBeardedBearSAS/claude-craft on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.