holy-trinity

holy-trinity is a skill for Claude Code from itsribbZ/Godspeed. It costs 58 tokens per session (9,045 once invoked), scanned A, original, MIT.

A structured process for diagnosing, researching, improving, and checking a system, skill, or architecture. It uses different scoring criteria depending on whether the target is code, a tool, a skill, or another supported type.

In plain words
What is it for?
It helps assess and improve code, architectures, skills, tools, and game-design documents through diagnosis, research, implementation, verification, and measured scoring.
Why use it?
It gives improvement work a repeatable loop and stops when further changes are unlikely to provide enough benefit or may add too much regression risk.

Skill for Claude Code

Written for Claude Code: effort in frontmatter. Also seen: model in frontmatter; reads .claude/ paths.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the godspeed plugin — 18 skills, 3 commands, 1 agent, 5 hooks shipped together

Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add itsribbZ/Godspeed
Claude Code
/plugin install godspeed

Made for: Claude Code.

Or install godspeed, the plugin that ships this one along with the rest of its 18 skills, 3 commands, 1 agent, 5 hooks.

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 holy-trinity

README.md
[![agentmods](https://agentmods.dev/badge/skills/itsribbz/godspeed/holy-trinity.svg)](https://agentmods.dev/skills/itsribbz/godspeed/holy-trinity)
Your own site
<a href="https://agentmods.dev/skills/itsribbz/godspeed/holy-trinity"><img src="https://agentmods.dev/badge/skills/itsribbz/godspeed/holy-trinity.svg" alt="Measured on agentmods" height="20"></a>
Per session 58 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 9,045 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 $0.00058 $0.09045
Opus 5 $0.00029 $0.04522
Sonnet 5 $0.00012 $0.01809
Haiku 4.5 $0.00006 $0.00904

Measured 5d ago against content hash 0b0f9c77cd8b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

holy-trinity 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 5d 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.

plugins/godspeed/skills/holy-trinity/SKILL.md · 745 lines

How it starts

The opening of the file, as written. The whole thing — 745 lines — stays where its author put it; the contents beside it link to each section on GitHub.

The Holy Trinity v4.0 — Adaptive Convergent Improvement Engine

When to Trigger

  • User says "holy trinity", "deploy holy trinity", "run holy trinity", "trinity on [topic]"
  • User says "upgrade [system]", "self-improve [system]", "make [system] better"
  • User wants the complete diagnose → research → implement → verify loop
  • When a system, skill, or architecture needs measured improvement, not just research

Target Type Auto-Presets (v2.0)

Before scoring, auto-detect the target type and load preset scoring dimensions. This eliminates the manual dimension-definition step from v1.0.

Preset Library (validated across 5+ runs)

Target Type Detection Signal Dimensions (7 × 0-5 = 35 max)
Code/Architecture Source files, .h/.cpp, .ts/.tsx Law1:Simplicity, Law2:DataDriven, Law3:EdgeCases, Law4:Decoupling, Law5:Liability, Law6:Disclosure, Law7:WorkRightFast
Skill/Tool SKILL.md, _learnings.md, .claude/skills/ Reliability, SelfImprovement, CrossSkillIntegration, Resilience, OutputQuality, Efficiency, Extensibility
Game Design GDD, design docs, no code target Coherence, ScopeFeasibility, CoreLoop, Differentiation, Interconnection, TechSpec, PlayerMotivation
Product/Business Market analysis, revenue model MktValidation, CompetitiveGap, RevenueModel, BuildFeasibility, DistributionPath, UniqueAdvantage, ScalePotential
Standalone Tool Python/script, standalone app FeatureCompleteness, Architecture, SafetyReliability, UX, Extensibility, Documentation, Integration
Infrastructure CI/CD, deploy, configs Reliability, Security, Observability, Automation, Recovery, Scalability, Maintainability
Custom Cannot auto-detect Define 7 dimensions in Phase 0 — document rationale

Cross-run note: When running on a target that matches a previous run's type, load that run's scoring calibration notes. If the previous run flagged "dimension X was most impactful", weight it higher.

Read the full file on GitHub · 745 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. 5d ago First seen · 745 lines · 58 tokens per session scan A 0b0f9c77cd8b

Subscribe to this mod's changes

holy-trinity is a skill published in the GitHub repository itsribbZ/Godspeed (1 stars, last pushed 2mo ago), licensed MIT. It adds 58 tokens to every session and 9,045 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

release-it

Build production-ready systems with stability patterns: circuit breakers, bulkheads, timeouts, and retry logic. Use when the user mentions "production outage", "circuit breaker", "deployment pipeline", "chaos engineering", "retry storm", "health checks", "my service keeps crashing", "prevent cascading failures", or…

wondelai/skills · 131 tokens

tidewave-integration

Tidewave MCP runtime tools — debugging, smoke testing, live state inspection, SQL queries, hex docs. Use when evaluating code in a running Phoenix app.

oliver-kriska/claude-elixir-phoenix · 38 tokens

git-investigate

Git history investigation. Use when: tracking code changes, finding where bugs were introduced, root cause analysis. Not for: code exploration (use code-explore), issue analysis (use issue-analyze). Output: history trace + root cause report.

sd0xdev/sd0x-harness · 53 tokens

analyze

Deep-dive codebase analysis that explains how things actually work — business rules, architecture patterns, auth flows, data models, integrations, and performance hotspots. Use whenever the user asks "how does X work", "map the Y flow", "what are the business rules for Z", "trace the auth path", "explore the codebase…

rsmdt/the-startup · 118 tokens

simplify

Wrap-up refactoring — simplify code, eliminate duplication, preserve behavior.

sd0xdev/sd0x-harness · 16 tokens

incremental-analysis

Detect existing workspace, diff current sources against high water mark metadata, classify specs as unchanged/stale/orphaned/new, re-analyze only what changed. Activates automatically when /analyze finds an existing workspace.

prime-radiant-inc/greenfield · 47 tokens