gpt56-stop-overengineering

gpt56-stop-overengineering is a skill for Codex from Swallow100/gpt-5.6-stop-overengineering. It costs 84 tokens per session (836 once invoked), scanned A, original, MIT.

A set of instructions for keeping coding-agent work limited to the requested change and checking that the result works.

In plain words
What is it for?
It is for implementations, bug fixes, refactors, reviews, and maintenance where the smallest safe change should be verified.
Why use it?
It helps prevent unnecessary refactors, new dependencies, and speculative features from expanding a small task.

Skill for Codex

Written for Codex: agents/openai.yaml present.

Good fit It is for implementations, bug fixes, refactors, reviews, and maintenance where the smallest safe change should be verified.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/swallow100/gpt-5.6-stop-overengineering/gpt56-stop-overengineering
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 Swallow100/gpt-5.6-stop-overengineering --skill gpt56-stop-overengineering
Clone the repo
git clone --depth 1 https://github.com/Swallow100/gpt-5.6-stop-overengineering

Made for: Codex.

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 gpt56-stop-overengineering

README.md
[![agentmods](https://agentmods.dev/badge/skills/swallow100/gpt-5.6-stop-overengineering/gpt56-stop-overengineering/github.svg)](https://agentmods.dev/skills/swallow100/gpt-5.6-stop-overengineering/gpt56-stop-overengineering)
Your own site
<a href="https://agentmods.dev/skills/swallow100/gpt-5.6-stop-overengineering/gpt56-stop-overengineering"><img src="https://agentmods.dev/badge/skills/swallow100/gpt-5.6-stop-overengineering/gpt56-stop-overengineering/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 gpt56-stop-overengineering

Your own site · 80×15
<a href="https://agentmods.dev/skills/swallow100/gpt-5.6-stop-overengineering/gpt56-stop-overengineering"><img src="https://agentmods.dev/badge/skills/swallow100/gpt-5.6-stop-overengineering/gpt56-stop-overengineering.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 84 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 836 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 $0.00084 $0.00836
Opus 5 $0.00042 $0.00418
Sonnet 5 $0.00017 $0.00167
Haiku 4.5 $0.00008 $0.00084

Measured 12d ago against content hash 6d6ba36f3ed0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

gpt56-stop-overengineering 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 12d 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.

skills/gpt56-stop-overengineering/SKILL.md · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GPT-5.6 Stop Overengineering

Make the smallest safe change. Produce proportionate proof. Then stop.

1. Lock the contract

Before editing, reduce the task to four lines:

  • Outcome: the observable result the user requested.
  • Scope: the files, behavior, or subsystem that owns that result.
  • Constraints: explicit limits plus repository instructions.
  • Proof: the least expensive evidence that can establish success.

Infer these from available context when they are clear. Ask only when a missing answer would materially change the implementation or create meaningful risk.

Do not silently add goals. Treat appealing improvements as optional follow-ups, not requirements.

2. Choose the smallest sufficient change

Prefer, in order:

  1. Reuse an existing path, pattern, or dependency.
  2. Modify the narrowest ownership boundary.
  3. Add the least new code needed for the requested behavior.

Do not add an abstraction for one hypothetical future use. Do not introduce a dependency, framework, configuration surface, public API, migration, compatibility layer, or broad refactor unless the contract requires it.

Preserve unrelated code, formatting, comments, and user changes. Avoid cleanup whose only justification is "while here."

Before expanding into another subsystem or materially growing the expected diff, pause and either choose a narrower solution or request approval.

3. Verify in proportion to risk

Select the lowest tier that can realistically catch a regression introduced by the change:

Risk Typical change Required proof
Low prose, comments, static copy, local style inspect the diff; render or lint only when relevant
Medium isolated logic, component behavior, bug fix reproduce or run focused tests for the changed behavior
High security, permissions, data, migrations, public contracts, shared infrastructure, release paths focused tests plus the relevant broader checks and failure paths

Follow mandatory repository or user-specified checks even when they exceed this table.

Read the full file on GitHub · 78 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.

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. 12d ago First seen · 78 lines · 84 tokens per session scan A 6d6ba36f3ed0

Subscribe to this mod's changes

gpt56-stop-overengineering is a skill published in the GitHub repository Swallow100/gpt-5.6-stop-overengineering (4 stars, last pushed 1mo ago), licensed MIT. It adds 84 tokens to every session and 836 once invoked, about $0.0004 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.