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 Aimeerrhythm/enterprise-change-workflow --skill impl-orchestrationgit clone --depth 1 https://github.com/Aimeerrhythm/enterprise-change-workflowWrote 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/aimeerrhythm/enterprise-change-workflow/impl-orchestration)<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>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 | $0.00024 | $0.01744 |
| Opus 5 | $0.00012 | $0.00872 |
| Sonnet 5 | $0.00005 | $0.00349 |
| Haiku 4.5 | $0.00002 | $0.00174 |
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.
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_strategyconditions inworkflow-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
- Read plan file once — extract all tasks with full text
- Pre-flight check — Read
./dep-graph-usage.md§ Pre-flight Check. Controlled by ecw.ymlimpl_orchestration.pre_check(default: true). Timeout 120s compile / 600s test. On failure: auto-fix → retry → ask user - Build dependency graph — Read
./dep-graph-usage.md§ Steps 1-3. Extract task metadata → calldep_graph.py→ get parallel layers (Layer 0, Layer 1, ...) - Create Tasks — one TaskCreate per plan task, with dependency chain
- Display execution layers — show user the parallel execution plan before starting
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.
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.
- 7d ago First seen · 157 lines · 24 tokens per session scan A c921a04cb5e0
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.
Other skills, from other repositories
import
Import a tasks.md into the coco tracker as an epic with dependencies, and create matching issues in the configured issue tracker.
cyxj-transcript
A workflow that turns a video or audio transcript into a structured article draft in Obsidian Markdown.
cyxj-blog-pub
A publishing workflow for adding a finished article to an Astro blog, a website built with the Astro framework.
document
Generate minimal documentation through parallel agents.
cyxj-jingxuan
A writing assistant for applying to have a finished video selected for 抖音精选, a curated feature on the Douyin video platform. It reads the video's actual subtitles or transcript and writes a 150–250 character Chinese application in four sections.
prd-gen
A guide for turning a feature idea into a product requirements document (PRD), a structured plan that explains what to build and how success will be judged.