Borrowing it
Nothing to install: this file belongs to aegntic/cldcde. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/aegntic/cldcde/main/.claude/skills/compound-engineering/SKILL.mdgit clone --depth 1 https://github.com/aegntic/cldcdeWrote 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/aegntic/cldcde/compound-engineering)<a href="https://agentmods.dev/skills/aegntic/cldcde/compound-engineering"><img src="https://agentmods.dev/badge/skills/aegntic/cldcde/compound-engineering/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.
<a href="https://agentmods.dev/skills/aegntic/cldcde/compound-engineering"><img src="https://agentmods.dev/badge/skills/aegntic/cldcde/compound-engineering.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00054 | $0.01899 |
| Opus 5.5 | $0.00022 | $0.00760 |
| Sonnet 5.5 | $0.00011 | $0.00380 |
| Haiku 4.5 | $0.00005 | $0.00190 |
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 1mo 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 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
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.
- 1mo ago First seen · 310 lines · 54 tokens per session scan A cda41b84348e
compound-engineering is a skill published in the GitHub repository aegntic/cldcde (12 stars, last pushed 1mo ago), licensed MIT. It adds 54 tokens to every session and 1,899 once invoked, about $0.0002 per session on Opus 5.5. 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.
Other skills, from other repositories
apex-review
Cross-cutting review of recent work — catches gaps between specialists. Use when asked to "review what we built", "check the work", "pre-launch review", or after completing a significant chunk of work.
brutal-honesty-review
Unvarnished technical criticism combining Linus Torvalds' precision, Gordon Ramsay's standards, and James Bach's BS-detection. Use when code/tests need harsh reality checks, certification schemes smell fishy, or technical decisions lack rigor. No sugar-coating, just surgical truth about what's broken and why.
quality-gate
Orchestrates the QUALITY pipeline stage for egregore work items, running code review, unbloat, and test updates. Use when running quality checks before a PR.
performance-optimizer
Agents should invoke this skill for slow code, high CPU/memory, latency, large data processing, algorithmic complexity, profiling plans, benchmarks, or optimization requests. Profiles first and weighs trade-offs before changing code.
architecture-review
Agents should invoke this skill for architecture reviews, module boundaries, dependency direction, coupling/cohesion, SOLID concerns, system design trade-offs, layering, service boundaries, or design decisions before implementation.
network-diagnostics
Agents should invoke this skill for connectivity, DNS, Pi-hole, port reachability, routing, firewall reachability, TLS/network timeouts, or service access failures. Provides structured network troubleshooting commands and interpretation.