Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add TheBeardedBearSAS/claude-craft --skill dynamic-workflowsgit clone --depth 1 https://github.com/TheBeardedBearSAS/claude-craftWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/thebeardedbearsas/claude-craft/dynamic-workflows)<a href="https://agentmods.dev/skills/thebeardedbearsas/claude-craft/dynamic-workflows"><img src="https://agentmods.dev/badge/skills/thebeardedbearsas/claude-craft/dynamic-workflows.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00090 | $0.01447 |
| Opus 5 | $0.00045 | $0.00724 |
| Sonnet 5 | $0.00018 | $0.00289 |
| Haiku 4.5 | $0.00009 | $0.00145 |
Grade A, and why
dynamic-workflows scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
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
| Palier | Outil | Concurrence | Quand |
|---|---|---|---|
| 1 | Sub-agent simple (Task/Agent) | 1 | Une investigation isolée, garder le contexte principal propre |
| 2 | Agent Teams (/team:audit, /team:sprint, /team:security) |
1 leader + ~3 workers | Travail parallèle borné, synchrone, qui tient en un round |
| 3 | Dynamic 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).
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 3d ago First seen · 88 lines · 90 tokens per session scan A a29d2590026c
dynamic-workflows is a skill published in the GitHub repository TheBeardedBearSAS/claude-craft (105 stars, last pushed 4d ago), licensed MIT. It adds 90 tokens to every session and 1,447 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
ai-ml-development
AI and machine learning development with PyTorch, TensorFlow, and LLM integration. Use when building ML models, training pipelines, fine-tuning LLMs, or implementing AI features.
leadership
Executive leadership expertise for decision-making, change management, crisis management, stakeholder management, team building, and organizational leadership. Use when leading teams, managing change, navigating crises, or developing leadership skills.
debug-systematic
Systematic 4-phase debugging methodology for complex, intermittent, or mysterious issues. Use when investigating bugs, race conditions, or unexplained failures.
embedded-iot
Embedded systems firmware, microcontrollers (ESP32, STM32, Arduino, Raspberry Pi), RTOS (FreeRTOS, Zephyr), IoT protocols (MQTT, CoAP, BLE), bare-metal C/C++, and hardware peripheral interfaces (I2C, SPI, UART, GPIO). Use when developing firmware, working with microcontrollers, or building IoT devices.
querying-json
Use when querying JSON files, filtering or transforming JSON data, or extracting specific fields from large JSON files without loading entire file contents (saves 80-95% context).
finding-files
Use when searching for files by name, pattern, or type in large directories, or building file lists for pipelines with other tools.