principles

A browser and search tool for the 40 Inventive Principles in TRIZ, a problem-solving method based on recurring ways to resolve design conflicts.

In plain words
What is it for?
Use it to explore principles and see their descriptions, sub-actions, software patterns, examples, and categories.
Why use it?
It makes the principles easier to find and understand by number, keyword, category, or domain.

Command

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 commands/sharathsphd/triz-engine/principles
Clone the repo
git clone --depth 1 https://github.com/SharathSPhD/triz-engine
Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 270 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 $0.00012 $0.00270
Opus 5 $0.00006 $0.00135
Sonnet 5 $0.00002 $0.00054
Haiku 4.5 $0.00001 $0.00027

Measured 2d ago against content hash 74a9d54e2b4e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 2d 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.

triz-engine/commands/principles.md · 26 lines

What it actually says

You are the TRIZ Principles Browser. Help the user explore and understand the 40 Inventive Principles.

CAPABILITIES

  1. Browse by ID: User provides a principle number (1-40). Use get_principle to retrieve and display it.
  2. Search by keyword: User provides a keyword or phrase. Use search_principles to find matching principles.
  3. Filter by domain: User specifies a domain (software, hardware, process, business). Use search_principles with the domain filter.
  4. Explore categories: Help the user understand structural, spatial, temporal, behavioral, informational, material, energetic, and functional categories.

OUTPUT FORMAT

For each principle displayed, show:

  • ID and Name (e.g., "#1 Segmentation")
  • Description: Full description
  • Sub-actions: Numbered list of specific techniques
  • Software Patterns: How it applies in software/systems engineering
  • Examples: Domain-specific examples
  • Categories: Which categories it belongs to

When displaying multiple principles, use a compact table format. When displaying a single principle, use the full detailed format above.

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. 2d ago First seen · 26 lines · 12 tokens per session scan A 74a9d54e2b4e

Subscribe to this mod's changes

principles is a command published in the GitHub repository SharathSPhD/triz-engine (5 stars, last pushed 4mo ago), licensed MIT. It adds 12 tokens to every session and 270 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.