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 agentmods add skills/ozzeron/prompt-pack/engineering-principlesnpx skills add Ozzeron/prompt-pack --skill engineering-principlesgit clone --depth 1 https://github.com/Ozzeron/prompt-packWrote 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/ozzeron/prompt-pack/engineering-principles)<a href="https://agentmods.dev/skills/ozzeron/prompt-pack/engineering-principles"><img src="https://agentmods.dev/badge/skills/ozzeron/prompt-pack/engineering-principles.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 | $0.00028 | $0.02204 |
| Opus 5 | $0.00014 | $0.01102 |
| Sonnet 5 | $0.00006 | $0.00441 |
| Haiku 4.5 | $0.00003 | $0.00220 |
Grade A, and why
engineering-principles 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 6d 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 — 192 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Engineering Principles
The non-negotiable rules every coding skill in this pack must follow. AI agents tend to emit code as if there is no tomorrow: duplicate components, monolithic files, fresh abstractions instead of reuse, no types, no structure. This document exists to stop that.
Every architecture, review, and interface skill inherits these rules. Specific roles add detail on top, but never relax them.
When to use
Always, whenever you write or modify production code. This is a cross-cutting concern.
1. DRY — reuse before creating
Delegated to the dedicated meta skill: meta/reuse-before-create.
That skill is the single source of truth for the reuse-vs-create decision: the strict ordering (reuse → extend → compose → extract → create new), the mandatory one-line justification when creating, the per-artifact-type search strategies, and the "don't trust names alone" rule.
Do not duplicate that logic in this skill or any other. Inherit it, follow it.
2. File and function size
Code is read more than written. Optimise for the next reader.
| Unit | Soft limit | Hard limit |
|---|---|---|
| Function | 40 lines | 80 lines |
| React component | 150 lines | 250 lines |
| File | 250 lines | 400 lines |
| Class | 200 lines | 350 lines |
When you approach the soft limit, split. Hitting the hard limit without splitting is a code smell to flag in review.
Splitting strategies:
- Extract sub-components for distinct UI regions
- Pull pure helpers into the same folder, import locally
- Move types to a
types.tsnext to the file - Group related functions into a class or module if they share state
3. Single responsibility
A function, component, hook, or module does one thing. If you can't describe what it does in a single sentence without "and", split it.
Common violations:
- A component that fetches data, renders UI, and handles navigation — split into hook + UI
- A util that validates AND transforms — make two functions
- A "manager" class with 12 methods — likely 3 modules pretending to be one
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.
- 6d ago First seen · 192 lines · 28 tokens per session scan A d018adc95a7c
engineering-principles is a skill published in the GitHub repository Ozzeron/prompt-pack (8 stars, last pushed 1mo ago), licensed MIT. It adds 28 tokens to every session and 2,204 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
memorix-troubleshooting
Use when Memorix MCP, setup, project binding, HTTP control plane, hooks, skills, or agent integration is missing, stale, or failing.
ijfw-workflow
Use when the user says: 'build', 'create', 'plan', 'new project', 'brainstorm', 'design', 'UI', 'website', 'dashboard', 'app', 'help me build', 'launch', 'book', 'campaign', or anything project-level. Skill body decides Quick vs Deep path.
ijfw-plan
Use when the user says 'plan this', 'plan it', 'make a plan', 'let's plan', 'draft a plan', 'how should we tackle this', 'break this down', or invokes '/ijfw-plan'. Produces a falsifiable PLAN.md (software, book, campaign, design, research) with task breakdown, dependency wave-table, and success criteria — gated by…
ijfw-cross-audit
Generate a cross-platform multi-model audit (Trident) on a diff, brief, or artifact. Trigger: 'cross audit', 'Trident', 'second opinion', 'check with other models', 'check with other AIs', 'cross-check this', 'get another perspective', /cross-audit.
ijfw-dashboard
Control the IJFW observation dashboard (start/stop/status). Trigger: 'ijfw dashboard', 'open dashboard', 'show observations', 'dashboard start', 'dashboard stop', 'dashboard status', 'view session activity'.
ijfw-preflight
Run the IJFW preflight pipeline (11 gates, fail-fast). Trigger: 'ijfw preflight', 'run preflight', 'check before ship', 'preflight gates', 'validate before release'.