agentic-workflow-builder

agentic-workflow-builder is a skill for Claude Code, Codex from vignesh2027/Claude-Agentic-Skills2.0-version. It costs 79 tokens per session (758 once invoked), scanned A, original, MIT.

A guide for designing multi-step systems in which AI agents use tools, coordinate tasks, recover from errors, and sometimes request human approval.

In plain words
What is it for?
Design agent loops, plan-and-execute pipelines, parallel agents, human approval gates, and error-recovery flows for AI-powered automation.
Why use it?
It helps turn a broad automation idea into a defined workflow with clear steps, decision points, parallel work, and safeguards for irreversible actions.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Design agent loops, plan-and-execute pipelines, parallel agents, human approval gates, and error-recovery flows for AI-powered automation.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/vignesh2027/claude-agentic-skills2.0-version/agentic-workflow-builder
Install

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.

Any agent
npx skills add vignesh2027/Claude-Agentic-Skills2.0-version --skill agentic-workflow-builder
Clone the repo
git clone --depth 1 https://github.com/vignesh2027/Claude-Agentic-Skills2.0-version

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for agentic-workflow-builder

README.md
[![agentmods](https://agentmods.dev/badge/skills/vignesh2027/claude-agentic-skills2.0-version/agentic-workflow-builder/github.svg)](https://agentmods.dev/skills/vignesh2027/claude-agentic-skills2.0-version/agentic-workflow-builder)
Your own site
<a href="https://agentmods.dev/skills/vignesh2027/claude-agentic-skills2.0-version/agentic-workflow-builder"><img src="https://agentmods.dev/badge/skills/vignesh2027/claude-agentic-skills2.0-version/agentic-workflow-builder/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for agentic-workflow-builder

Your own site · 80×15
<a href="https://agentmods.dev/skills/vignesh2027/claude-agentic-skills2.0-version/agentic-workflow-builder"><img src="https://agentmods.dev/badge/skills/vignesh2027/claude-agentic-skills2.0-version/agentic-workflow-builder.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 79 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 758 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00079 $0.00758
Opus 5 $0.00039 $0.00379
Sonnet 5 $0.00016 $0.00152
Haiku 4.5 $0.00008 $0.00076

Measured 10d ago against content hash dc0a133e7836, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

agentic-workflow-builder 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 10d 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.

agentic-workflow-builder/SKILL.md · 99 lines

How it starts

The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AgenticWorkflowBuilder Agent

You are AgenticWorkflowBuilder — a specialist in designing production-ready agentic systems that combine LLMs with tools, APIs, and human oversight.

Agentic System Design Patterns

ReAct Loop (Reason + Act)

while not done:
    thought = llm.think(goal, history, available_tools)
    action = llm.select_tool(thought)
    observation = execute_tool(action)
    history.append(thought, action, observation)
    done = llm.check_completion(goal, history)

Best for: open-ended research, multi-step problem solving

Plan + Execute

plan = llm.create_plan(goal)          # step list
for step in plan:
    result = execute_step(step)
    plan = llm.revise_if_needed(plan, result)  # optional replanning

Best for: well-defined tasks with clear sub-steps

Parallel Agents

results = await asyncio.gather(
    agent_a.run(subtask_1),
    agent_b.run(subtask_2),
    agent_c.run(subtask_3)
)
final = synthesizer.merge(results)

Best for: independent sub-tasks (research + coding + writing simultaneously)

Human-in-the-Loop Design

Approval Gates

Insert human approval before:

  • Irreversible actions (send email, delete record, execute payment)
  • High-stakes decisions (deploy to production, cancel contract)
  • Low-confidence completions (agent confidence < threshold)
  • Expensive operations (actions costing > $X)

Approval Interface Pattern

async def execute_with_approval(action, context):
    if requires_approval(action):
        approval = await request_human_approval(
            action=action,
            context=context,
            timeout=300  # 5 min before auto-reject
        )
        if not approval.granted:
            return ActionResult(status='rejected', reason=approval.reason)
    return await execute(action)

Error Recovery Strategies

  1. Retry with backoff: transient errors (network, rate limit)
  2. Alternative tool: if tool A fails, try tool B for same goal
  3. Decompose: if step fails, break it into smaller steps
  4. Escalate to human: if 3 retries fail, hand off to human with full context
  5. Graceful degradation: complete partial result with clear notation of what failed

Read the full file on GitHub · 99 lines

Changes

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.

  1. 10d ago First seen · 99 lines · 79 tokens per session scan A dc0a133e7836

Subscribe to this mod's changes

agentic-workflow-builder is a skill published in the GitHub repository vignesh2027/Claude-Agentic-Skills2.0-version (6 stars, last pushed 11d ago), licensed MIT. It adds 79 tokens to every session and 758 once invoked, about $0.0004 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 2026-08-31.