qurio: Skill for Gemini CLI

.gemini/skills/technical-constitution/SKILL.md

technical-constitution is a skill for Gemini CLI from irahardianto/qurio. It costs 55 tokens per session (16,619 once invoked), scanned A, original, MIT.

A planning skill for designing software features, architecture, refactors, and implementation steps under a project's technical rules.

In plain words
What is it for?
It is for planning new features, refactoring existing code, and checking that proposed implementation work follows the project's constitution.
Why use it?
It makes the project's security, testing, modularity, and other required standards part of the plan before coding begins.

Skill for Gemini CLI

Written for Gemini CLI: installed under .gemini/. Also seen: positional $N argument.

This is irahardianto/qurio's own configuration. It tells Gemini CLI how to work on qurio itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything qurio configures →

Reuse

Borrowing it

Nothing to install: this file belongs to irahardianto/qurio. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/irahardianto/qurio/main/.gemini/skills/technical-constitution/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/irahardianto/qurio

Made for: Gemini CLI.

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 technical-constitution

README.md
[![agentmods](https://agentmods.dev/badge/skills/irahardianto/qurio/technical-constitution/github.svg)](https://agentmods.dev/skills/irahardianto/qurio/technical-constitution)
Your own site
<a href="https://agentmods.dev/skills/irahardianto/qurio/technical-constitution"><img src="https://agentmods.dev/badge/skills/irahardianto/qurio/technical-constitution/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.

agentmods 80×15 button for technical-constitution

Your own site · 80×15
<a href="https://agentmods.dev/skills/irahardianto/qurio/technical-constitution"><img src="https://agentmods.dev/badge/skills/irahardianto/qurio/technical-constitution.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 55 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 16,619 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00055 $0.16619
Opus 5 $0.00028 $0.08309
Sonnet 5 $0.00011 $0.03324
Haiku 4.5 $0.00006 $0.01662

Measured 9d ago against content hash 24aa73239d7d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

technical-constitution 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 9d 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.

.gemini/skills/technical-constitution/SKILL.md · 2,115 lines

How it starts

The opening of the file, as written. The whole thing — 2,115 lines — stays where its author put it; the contents beside it link to each section on GitHub.

The Constitution: Technical Preference Universal Principles

⚖️ CRITICAL GOVERNANCE NOTICE

CRITICAL: BEFORE doing ANYTHING else, Read and Comprehend this document COMPLETELY.

MANDATORY COMPLIANCE CHECK:

Before executing your task, you must perform a "Constitution Lookup":

  1. IDENTIFY the domain of your task (e.g., API, DB, Auth, logging, etc.).
  2. SEARCH the relevant sections (e.g., grep "API Design").
  3. REVIEW Critical Constraints table for domain
  4. VERIFY your plan against the discipline and constraints before proceeding.

1. The Supremacy Clause & Conflict Resolution

When directives conflict or seem impossible to satisfy simultaneously, follow this precedence:

  1. Security Principles [Non-Negotiable]

    • OWASP Top 10 compliance
    • Input validation and sanitization
    • Authentication and authorization
    • Secrets management
    • No information leakage
    • Action: Security ALWAYS wins. Refactor other requirements to satisfy security.
  2. Testability & Modularity [Structural Law]

    • I/O isolation (dependencies mockable in tests)
    • Pure business logic (no side effects in core logic)
    • Clear module boundaries with contracts
    • Action: If code cannot be unit tested without external dependencies, refactor to add abstraction layer.
  3. Error Handling Standards [Reliability Law]

    • No silent failures
    • Correlation IDs required
    • JSON envelope format
    • Resource cleanup in all paths
    • Action: All error paths must be explicit. No exceptions.
  4. Language Idioms [Implementation Preference]

    • Use native patterns (defer, RAII, context managers)
    • Follow community conventions
    • Leverage standard library
    • Action: Implement above laws idiomatically, don't blindly copy other languages.
  5. Performance Optimizations [Measure First]

    • Appropriate data structures
    • Profile before optimizing
    • Caching strategies
    • Action: Only optimize with measured bottlenecks. Correctness > speed

Read the full file on GitHub · 2,115 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. 9d ago First seen · 2,115 lines · 55 tokens per session scan A 24aa73239d7d

Subscribe to this mod's changes

technical-constitution is a skill published in the GitHub repository irahardianto/qurio (17 stars, last pushed 6mo ago), licensed MIT. It adds 55 tokens to every session and 16,619 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 2026-08-30.