What is workflow-engine?

A development workflow controller that chooses the process and approval checks for each coding task. It uses tracks from trivial changes to significant changes and can require security, architecture, or design approval.

It is for classifying work, enforcing approval gates, and controlling whether agents may start or hand off development work.

It prevents teams from using the same heavy process for every change or skipping important checks for changes involving secrets, external input, new services, or public interfaces.

workflow-engine — Skill for Claude Code by olehsvyrydov

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 olehsvyrydov/AI-development-team --skill workflow-engine

Clone the repo

git clone --depth 1 https://github.com/olehsvyrydov/AI-development-team

Made for: Claude Code.

Or install ai-dev-team, the plugin that ships this one along with the rest of its 43 skills, 50 commands.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/olehsvyrydov/ai-development-team/workflow-engine/github.svg)](https://agentmods.dev/skills/olehsvyrydov/ai-development-team/workflow-engine)

Your own site

<a href="https://agentmods.dev/skills/olehsvyrydov/ai-development-team/workflow-engine"><img src="https://agentmods.dev/badge/skills/olehsvyrydov/ai-development-team/workflow-engine/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/olehsvyrydov/ai-development-team/workflow-engine"><img src="https://agentmods.dev/badge/skills/olehsvyrydov/ai-development-team/workflow-engine.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 140 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,227 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.

Model	Per session	Once invoked
Fable 5.1	$0.00140	$0.01227
Opus 5.5	$0.00056	$0.00491
Sonnet 5.5	$0.00028	$0.00245
Haiku 4.5	$0.00014	$0.00123

Measured today against content hash 0177965dce56, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

workflow-engine 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 today.

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.

claude/skills/workflow-engine/SKILL.md · 47 lines

How it starts

The opening of the file, as written. The whole thing — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Workflow Engine — how the team works

You enforce the team's workflow. The authoritative definition lives in workflow.yaml (resolved first-found: ./.aidevteam/workflow.yaml → ~/.aidevteam/workflow.yaml → the framework default in this repo's claude/workflow/workflow.yaml). Load that file when a task starts — do not paraphrase the process from memory.

Do this at the start of every task and before every handoff

Load workflow.yaml. Note the active preset and its always_required gates.
Classify the change → pick the matching track. Right-size it:
- trivial (typo/comment/rename) → floor_min; small (one file, no new deps) → floor; standard (a feature/story) → standard; significant (new service/dependency/schema/boundary, or anything security-sensitive) → full.
Detect gate triggers from the change and require those gates even on a small change:
- auth/secrets/PII/upload/external-input/network/crypto → SECOPS_APPROVED; new dep/schema/service/boundary/public API → ARCH_APPROVED; visual change/new screen → DESIGN_APPROVED; etc.
- Security is a safety override: never skip SECOPS for being a "small" change.
Check the ledger for gates already passed on this ticket (.workflow-state.json → Backlog.md → workflow MCP → Jira; first available wins — see references/ledger.md).
Enforce. Before crossing a gate it must be passed:
- refusal: hard + unmet → STOP. Do not proceed. Name the gate and invoke its owner: e.g. "Blocked: SECOPS_APPROVED required — handing to /secops."
- refusal: soft + unmet → warn, record the skip + reason, may proceed.
Record every gate result and status transition to the ledger (and a ticket note) as you go.

Proportionality (why the workflow stops getting ignored)

The default preset: solo forces nothing — gates fire only on trigger or change-class, so a solo dev gets a light path and won't route a typo through architecture + security. small-team adds always-on code review; regulated runs the full gauntlet and uses Jira/Confluence. Switch by editing preset: in workflow.yaml.

Read the full file on GitHub · 47 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

today First seen · 47 lines · 140 tokens per session scan A 0177965dce56

Subscribe to this mod's changes

workflow-engine is a skill published in the GitHub repository olehsvyrydov/AI-development-team (17 stars, last pushed today), licensed MIT. It adds 140 tokens to every session and 1,227 once invoked, about $0.0006 per session on Opus 5.5. 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 2026-10-19.

Building agents Planning agentic-workflow ai-agents ai-dev-tools anthropic

workflow-engine

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Workflow Engine — how the team works

Do this at the start of every task and before every handoff

Proportionality (why the workflow stops getting ignored)

What ships with it

What this file has done since we first saw it

Other skills, from other repositories

bf-clarify

bf-rebuild-plan

bf-ui

loop

bf-blueprint

debug