A reduced set of engineering rules for making small, verifiable code changes. It emphasizes fixing the underlying cause, keeping complexity low, validating data at boundaries, and making shared state ownership clear.

Use it when the user explicitly asks for this coding approach or invokes ub-mode. It guides implementation, debugging, testing, refactoring, retries, and handling of shared state.

Large or indirect changes make failures harder to understand and can hide invalid states. These rules encourage reproducing practical failures, checking observable behavior, and reconsidering the design when repeated fixes fail.

ub-mode — Skill for Claude Code and Codex by CHENyiru3

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.

Any agent

npx skills add CHENyiru3/AI-Skills-Collections --skill ub-mode

Clone the repo

git clone --depth 1 https://github.com/CHENyiru3/AI-Skills-Collections

Made for: Claude Code, Codex.

Or install agents, the plugin that ships this one along with the rest of its 8 skills.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/chenyiru3/ai-skills-collections/ub-mode/github.svg)](https://agentmods.dev/skills/chenyiru3/ai-skills-collections/ub-mode)

Your own site

<a href="https://agentmods.dev/skills/chenyiru3/ai-skills-collections/ub-mode"><img src="https://agentmods.dev/badge/skills/chenyiru3/ai-skills-collections/ub-mode/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/chenyiru3/ai-skills-collections/ub-mode"><img src="https://agentmods.dev/badge/skills/chenyiru3/ai-skills-collections/ub-mode.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 36 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 498 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.

Model	Per session	Once invoked
Fable 5.1	$0.00036	$0.00498
Opus 5.5	$0.00014	$0.00199
Sonnet 5.5	$0.00007	$0.00100
Haiku 4.5	$0.00004	$0.00050

Measured yesterday against content hash bde971fd3665, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ub-mode 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 yesterday.

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.

skills-market/agents/guidelines/ub-mode/SKILL.md · 51 lines

How it starts

The opening of the file, as written. The whole thing — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Reduced Engineering Principles

First make it work

Make the smallest coherent change that solves the problem. Keep each decision in one place and subtract complexity before adding abstractions.
Start with the data shape and domain constraints. Validate at boundaries; represent invalid states explicitly rather than hiding them behind guards.
When a behavioral test is practical, reproduce the failure before the fix. Do not write an implementation-mirroring test merely to satisfy a ritual.
Reconsider a shared premise after repeated fixes fail for the same reason. Explain the faulty assumption and change the design when necessary.
Separate state that need not be shared. When shared mutation is required, make ownership explicit; design retryable operations to be idempotent.

Then make it right

Fix the cause, work in verifiable increments, and check observable behavior. Pin the behavior before a structural refactor and verify it afterward. Use classes for coherent state and functions for stateless transformations when that improves the actual design.

Complexity, duplication, and mutation tools can help when available and relevant. Use the project's chosen tools and thresholds; do not install a tool, impose a universal score, or run expensive mutation analysis for every reversible edit.

Follow practice

Keep concise reasons and relevant checks in the project's existing record. Avoid a transcript of every action or a new mandatory logging system. Use focused context and independent workspaces when the task benefits from them. Reclaim worktrees only within requested cleanup scope after checking ownership and active use; uncommitted work requires resolution.

Follow the user's Git workflow. Make small reviewable commits when committing is requested; this skill alone does not authorize pushing to a remote or main.

These principles are adapted from the installed reduced mode, which credits @poteto's rules and the optional Crapper, Dryer, and Mutator tools. Their availability is not a prerequisite for using the principles.

Read the full file on GitHub · 51 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

agents/openai.yaml 228 B

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.

yesterday First seen · 51 lines · 36 tokens per session scan A bde971fd3665

Subscribe to this mod's changes

ub-mode is a skill published in the GitHub repository CHENyiru3/AI-Skills-Collections (2 stars, last pushed 3d ago), licensed MIT. It adds 36 tokens to every session and 498 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-11-13.

Debugging Testing

ub-mode next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
ub-modeCHENyiru3/AI-Skills-Collections	Skill	2	3d ago	MIT	A	36	Claude Code, Codex
systematic-debuggingopen-metadata/OpenMetadata	Skill	16k	today	Apache-2.0	A	37	Claude Code
log-error-digestzebbern/claude-code-guide	Skill	4.7k	yesterday	MIT	A	71	Claude Code, Codex
cwv-optimizeradobe/skills	Skill	326	today	Apache-2.0	A	112	Claude Code
ci-fixersipyourdrink-ltd/bernstein	Skill	1.2k	today	Apache-2.0	A	15	Claude Code, Codex
self-healhristo2612/jinn	Skill	329	yesterday	MIT	A	19	Claude Code, Codex
diagnosing-missing-recordingsPostHog/posthog	Skill	41k	today	none	A	76	Claude Code, Codex