impl-orchestration

impl-orchestration is a skill for Claude Code from Aimeerrhythm/enterprise-change-workflow. It costs 24 tokens per session (1,744 once invoked), scanned A, original, MIT.

A workflow for carrying out an implementation plan by splitting it into separate tasks and assigning independent tasks to separate coding agents. It organizes those tasks by dependencies and includes review steps.

In plain words
What is it for?
Use it when an existing implementation plan contains mostly independent tasks that can be worked on in parallel, then merged and reviewed.
Why use it?
It helps coordinate several pieces of planned development without losing track of which tasks depend on others. Reviews at task and project level help check the work before it is considered complete.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions subagents.

Part of the ecw plugin — 15 skills, 3 commands, 7 agents shipped together

Good fit Use it when an existing implementation plan contains mostly independent tasks that can be worked on in parallel, then merged and reviewed.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/aimeerrhythm/enterprise-change-workflow/impl-orchestration
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 Aimeerrhythm/enterprise-change-workflow --skill impl-orchestration
Clone the repo
git clone --depth 1 https://github.com/Aimeerrhythm/enterprise-change-workflow

Made for: Claude Code.

Or install ecw, the plugin that ships this one along with the rest of its 15 skills, 3 commands, 7 agents.

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 impl-orchestration

README.md
[![agentmods](https://agentmods.dev/badge/skills/aimeerrhythm/enterprise-change-workflow/impl-orchestration.svg)](https://agentmods.dev/skills/aimeerrhythm/enterprise-change-workflow/impl-orchestration)
Your own site
<a href="https://agentmods.dev/skills/aimeerrhythm/enterprise-change-workflow/impl-orchestration"><img src="https://agentmods.dev/badge/skills/aimeerrhythm/enterprise-change-workflow/impl-orchestration.svg" alt="Measured on agentmods" height="20"></a>
Per session 24 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,744 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 $0.00024 $0.01744
Opus 5 $0.00012 $0.00872
Sonnet 5 $0.00005 $0.00349
Haiku 4.5 $0.00002 $0.00174

Measured 7d ago against content hash c921a04cb5e0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

impl-orchestration 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 7d 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/impl-orchestration/SKILL.md · 157 lines

How it starts

The opening of the file, as written. The whole thing — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Implementation Orchestration

Execute plan by dispatching subagents per task in dependency-aware parallel layers, with risk-aware review gates.

Core principle: Dependency graph → parallel layers → worktree-isolated dispatch → merge → review = high quality, fast execution.

Announce at start: "Using ecw:impl-orchestration to execute the plan with parallel layer dispatch."

When to Use

Use when:

  • You have an implementation plan (from ecw:writing-plans)
  • Tasks are mostly independent
  • Auto-continue hook routes here based on impl_strategy conditions in workflow-routes.yml, OR Task count x risk level matches subagent-driven criteria

Don't use when:

  • No plan exists (write one first)
  • Tasks are tightly coupled (implement directly)
  • P2 / P3 / simple changes (implement directly)

Risk-Aware Review Depth

Read .claude/ecw/session-data/{workflow-id}/session-state.json for risk level. If unavailable (standalone invocation), default to P0 (full review depth).

Risk Level Per-task Spec Review Per-task Code Quality Review Post-impl
P0 Mandatory Mandatory (simplified inline) ecw:impl-verify (full 4 Rounds)
P1 Mandatory Skip (impl-verify Round 4 covers this) ecw:impl-verify (full 4 Rounds)

Why P0 keeps code quality review: Error cost at P0 is extreme. Catching issues per-task is cheaper than finding them across the full implementation.

Process Overview

For a visual overview, see ./process-diagram.md.

Setup

  1. Read plan file once — extract all tasks with full text
  2. Pre-flight check — Read ./dep-graph-usage.md § Pre-flight Check. Controlled by ecw.yml impl_orchestration.pre_check (default: true). Timeout 120s compile / 600s test. On failure: auto-fix → retry → ask user
  3. Build dependency graph — Read ./dep-graph-usage.md § Steps 1-3. Extract task metadata → call dep_graph.py → get parallel layers (Layer 0, Layer 1, ...)
  4. Create Tasks — one TaskCreate per plan task, with dependency chain
  5. Display execution layers — show user the parallel execution plan before starting

Read the full file on GitHub · 157 lines

Files

What ships with it

7 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.

  1. 7d ago First seen · 157 lines · 24 tokens per session scan A c921a04cb5e0

Subscribe to this mod's changes

impl-orchestration is a skill published in the GitHub repository Aimeerrhythm/enterprise-change-workflow (1 stars, last pushed 3mo ago), licensed MIT. It adds 24 tokens to every session and 1,744 once invoked, about $0.0001 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.