agent-workflow-orchestrator

agent-workflow-orchestrator is a skill for Claude Code, Codex from avksp/agent-lifecycle-kit. It costs 33 tokens per session (1,711 once invoked), scanned A, original, Apache-2.0.

A workflow skill that coordinates a coding task from clarification and planning through approval, execution, testing, and final proof.

In plain words
What is it for?
Use it to resume saved work, review and freeze plans, assign ready tasks, launch workers, validate results, and route defects for correction.
Why use it?
It keeps decisions, ownership, dependencies, reviews, and evidence organized across the whole task.

Skill for Claude CodeCodex

Part of the agent-lifecycle-kit plugin — 7 skills shipped together

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.

agentmods
npx agentmods add skills/avksp/agent-lifecycle-kit/agent-workflow-orchestrator
Any agent
npx skills add avksp/agent-lifecycle-kit --skill agent-workflow-orchestrator
Clone the repo
git clone --depth 1 https://github.com/avksp/agent-lifecycle-kit

Made for: Claude Code, Codex.

Or install agent-lifecycle-kit, the plugin that ships this one along with the rest of its 7 skills.

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 agent-workflow-orchestrator

README.md
[![agentmods](https://agentmods.dev/badge/skills/avksp/agent-lifecycle-kit/agent-workflow-orchestrator.svg)](https://agentmods.dev/skills/avksp/agent-lifecycle-kit/agent-workflow-orchestrator)
Your own site
<a href="https://agentmods.dev/skills/avksp/agent-lifecycle-kit/agent-workflow-orchestrator"><img src="https://agentmods.dev/badge/skills/avksp/agent-lifecycle-kit/agent-workflow-orchestrator.svg" alt="Measured on agentmods" height="20"></a>
Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,711 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00033 $0.01711
Opus 5 $0.00016 $0.00856
Sonnet 5 $0.00007 $0.00342
Haiku 4.5 $0.00003 $0.00171

Measured 2d ago against content hash b3ec79e0280c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

agent-workflow-orchestrator 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 2d 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.

skills/agent-workflow-orchestrator/SKILL.md · 160 lines

How it starts

The opening of the file, as written. The whole thing — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent workflow orchestrator

Drive the complete lifecycle with this skill. The controller is host-neutral: skills define semantics; adapters own native questions, approvals, tools, launch, waiting, cancellation and telemetry.

Lifecycle

  1. Load existing durable state when present. Do not reconstruct authority from chat.
  2. Clarify only decisions that materially change behavior, scope, safety, architecture, ownership, evidence, or external authority.
  3. Route planning to agent-first-planning.
  4. Route every candidate specification or plan to independent review through audit-agent-plan; refine until the freeze verdict passes or blocks.
  5. Freeze only reviewed matching inputs.
  6. Compile packets with agent-plan-to-workers.
  7. Respect execution mode: plan-only, approval-required, or auto-after-freeze.
  8. Launch only dependency-ready packets within frozen parallelism.
  9. Run controller-owned validation before launch and after attempts when the plan requires it.
  10. Audit every task attempt with audit-plan-implementation before acceptance.
  11. Route implementation/test/evidence defects to bounded remediation. Route plan gaps, write-set gaps, architecture changes, or contract changes to reopen and refreeze.
  12. After all required tasks are accepted, run final implementation audit and publish completion only from a reproducible proof.

For remediation require a frozen retry budget, independent REWORK evidence and open finding IDs; in v4 use workflow task-review-apply (with task-rework as compatibility wrapper). Never edit state manually. Before each task-result, put a current workflow task-snapshot claim in the result. Later code changes require a new claim and result.

workflow continue applies one projected revision and action digest. For sequences add --until-blocked --apply, bundle, lock, caps and --out. It replaces no validator or transition; stop at external authority.

For adapter-backed work, prefer agent-lifecycle start --adapter <id>. It requires one task source or --resume <session-id>. Raw input in auto, research, plan or review creates draft intake only; it cannot claim lifecycle coverage or start implementation. Review recommendations are advice until confirmed by the operator or reviewed plan. Only --mode implement may consume a fully bound frozen request. --resume accepts stored ALK session identity, never a guessed host conversation id. Lower-level atomic commands are adapter task start, adapter run and adapter session resume; adapter session start only records WAITING_FOR_TASK. Native launch remains descriptor-driven and host-owned.

Read the full file on GitHub · 160 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. 2d ago Changed · -1 lines b3ec79e0280c
  2. 5d ago First seen · 161 lines · 33 tokens per session scan A 229647720e31

Subscribe to this mod's changes

agent-workflow-orchestrator is a skill published in the GitHub repository avksp/agent-lifecycle-kit (18 stars, last pushed today), licensed Apache-2.0. It adds 33 tokens to every session and 1,711 once invoked, about $0.0002 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 2026-08-30.

Related

Other skills, from other repositories

edgeone skill scanner

Scan any agent skill for security risks before you install or use it. Powered by Tencent Zhuque Lab A.I.G (AI-Infra-Guard). 100% local static analysis — no file contents or credentials leave your device. Compatible with CodeBuddy, Cursor, Windsurf, Claude Code, OpenClaw and more. Triggers on: 这个 skill 安全吗, skill 安全扫描…

Tencent/AI-Infra-Guard · 148 tokens

happiness-skill

当用户问「怎么才能更幸福/为什么得到了还不满足/怎么减少焦虑」时调用。 核心理念: 幸福是缺憾感清空的默认状态, 是可训练的技能; 欲望是与自己的契约(得到前不快乐), 同时只留一个重大欲望; 活在当下。 不适用于: 临床抑郁等需要专业治疗的场景(本书方法不能替代医疗)。 Triggers: 幸福/不快乐/欲望/焦虑/知足/活在当下/happiness/desire/anxiety.

kangarooking/cangjie-skill · 136 tokens

agent-review

Critically review a Stencila agent and suggest improvements. Use when asked to review, audit, critique, evaluate, or improve an agent directory or AGENT.md file. Covers frontmatter validation, system instruction quality, configuration correctness, and adherence to the Agent schema.

stencila/stencila · 57 tokens

performing-cryptographic-audit-of-application

A cryptographic audit systematically reviews an application's use of cryptographic primitives, protocols, and key management to identify vulnerabilities such as weak algorithms, insecure modes, hardco.

xalgorix/xalgorix · 43 tokens

aws-security-audit

AWS security auditing — IAM users/roles/policies, CloudTrail API events, security posture analysis. Use when auditing IAM permissions, investigating security incidents, checking MFA compliance, or tracing API activity in CloudTrail.

automateyournetwork/netclaw · 47 tokens

Website Audit

Comprehensive website auditing skill using Lighthouse, PageSpeed Insights, and web performance APIs to audit performance, accessibility, SEO, best practices, and security.

PramodDutta/qaskills · 33 tokens