compound-engineering

compound-engineering is a skill for Claude Code, Codex from aegntic/cldcde. It costs 54 tokens per session (1,899 once invoked), scanned A, original, MIT.

A workflow coordinator that runs several code-quality checks in stages, including technical-debt scans, documentation checks, and adversarial review. It can assess individual edits or an entire codebase.

In plain words
What is it for?
Use it to validate file edits, run codebase checks in CI (automated build and test pipelines), manage enhancement workflows, and track engineering metrics.
Why use it?
It brings separate validation steps into one workflow, so problems can be found before code is merged or deployed.

Skill for Claude CodeCodex

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/aegntic/cldcde/compound-engineering
Any agent
npx skills add aegntic/cldcde --skill compound-engineering
Clone the repo
git clone --depth 1 https://github.com/aegntic/cldcde

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 compound-engineering

README.md
[![agentmods](https://agentmods.dev/badge/skills/aegntic/cldcde/compound-engineering.svg)](https://agentmods.dev/skills/aegntic/cldcde/compound-engineering)
Your own site
<a href="https://agentmods.dev/skills/aegntic/cldcde/compound-engineering"><img src="https://agentmods.dev/badge/skills/aegntic/cldcde/compound-engineering.svg" alt="Measured on agentmods" height="20"></a>
Per session 54 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,899 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00054 $0.01899
Opus 5 $0.00027 $0.00949
Sonnet 5 $0.00011 $0.00380
Haiku 4.5 $0.00005 $0.00190

Measured 4d ago against content hash cda41b84348e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

compound-engineering scanned grade A with 1 finding 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 4d 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.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

subprocess.run(..., timeout=120) # Increase from 60
.claude/skills/compound-engineering/SKILL.md · 310 lines

How it starts

The opening of the file, as written. The whole thing — 310 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Compound Engineering: Workflow Orchestration

Overview

Compound Engineering orchestrates the Essential 2026 Plugin Suite (Debt-Sentinel, Red Team Tribunal, Spec-Lock) into unified, multi-stage workflows. It provides comprehensive quality gates and metrics tracking.

Workflows

1. Safe Edit Workflow ⭐ Most Popular

Three-stage quality gate for individual file edits

Stage 1: Pre-Edit Validation (Debt-Sentinel)
  └─ BLOCKS critical anti-patterns
  └─ Scores technical debt

Stage 2: Post-Edit Sync (Spec-Lock)
  └─ Detects documentation drift
  └─ Auto-resolves if possible

Stage 3: Adversarial Review (Red Team Tribunal)
  └─ Multi-agent consensus required
  └─ REJECTS if concerns not addressed

Usage:

python3 /a0/usr/plugins/compound-engineering/compound-engineering.py \
  --workflow safe-edit --file src/auth/login.ts

Outcomes:

  • APPROVED: All stages passed → Ready to merge
  • BLOCKED: Critical debt detected → Must fix
  • CONDITIONAL: Minor concerns → Address then merge
  • REJECTED: Tribunal rejected → Significant rework needed

2. CI Pipeline Workflow

Pre-deployment validation for entire codebase

Stage 1: Technical Debt Analysis
  └─ Scan all files for accumulated debt
  └─ Calculate aggregate scores

Stage 2: Critical Path Review
  └─ Tribunal reviews security files
  └─ Auth, payment, API validation

Stage 3: Documentation Health
  └─ Verify all specs synchronized
  └─ Check for drift across codebase

Result: DEPLOY_READY or BLOCKED

Usage:

python3 /a0/usr/plugins/compound-engineering/compound-engineering.py \
  --workflow ci-pipeline --branch main

3. Enhancement Pipeline 🚀 Progressive Quality

Four-level enhancement for new features

Level 1: Basic Implementation
  └─ Anti-pattern checks (Debt-Sentinel)
  └─ Clean architecture validation

Level 2: Performance Optimization
  └─ Algorithm review
  └─ Resource usage analysis
  └─ Caching opportunities

Level 3: Security Hardening
  └─ Vulnerability scan
  └─ Input validation
  └─ Rate limiting

Level 4: Documentation Sync
  └─ Update all affected specs
  └─ Generate migration guides
  └─ Verify sync status

Read the full file on GitHub · 310 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. 4d ago First seen · 310 lines · 54 tokens per session scan A cda41b84348e

Subscribe to this mod's changes

compound-engineering is a skill published in the GitHub repository aegntic/cldcde (11 stars, last pushed 7d ago), licensed MIT. It adds 54 tokens to every session and 1,899 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). 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

hono-core

Hono ultrafast web framework fundamentals - routing, context, handlers, and response patterns for multi-runtime deployment.

bobmatnyc/claude-mpm-skills · 26 tokens

crewai-multi-agent

Multi-agent orchestration framework for autonomous AI collaboration. Use when building teams of specialized agents working together on complex tasks, when you need role-based agent collaboration with memory, or for production workflows requiring sequential/hierarchical execution. Built without LangChain dependencies…

davila7/claude-code-templates · 61 tokens

bump-mthds

Move this repo's exact mthds dependency pin to the latest release on PyPI (or a version you name), re-lock, adapt the engine source to whatever the new release broke, run the checks, and write the CHANGELOG entry — stopping before the commit. Use whenever the user says "bump mthds", "update mthds", "upgrade mthds"…

Pipelex/pipelex · 286 tokens

add-migration

Write a migration ledger entry for a configuration schema change in pipelex, so that a user's existing file can be repaired instead of thrown away. Use when make check-migration-schemas (alias cmig) or make check-ledger (alias cl) refuses a change, when the user says "add a migration", "write the ledger entry", "the…

Pipelex/pipelex · 154 tokens

add-model

Add a new AI model to the Pipelex inference system. Guides through all required steps: backend TOML configuration (OpenAI, Azure, Anthropic, Google, etc.), kit sync, test profile collections, and fixture regeneration. Use when the user says "add a model", "add GPT-X", "add Claude X", "new model", "register a model"…

Pipelex/pipelex · 131 tokens

release

Automates the Pipelex release workflow: bumps the version in pyproject.toml, finalizes the CHANGELOG.md Unreleased section, runs quality checks, creates a release/vX.Y.Z branch, commits, pushes, and opens a PR to main. Use when user says "release", "cut a release", "bump version", "prepare a release", "make a…

Pipelex/pipelex · 138 tokens