coding-discipline

A set of rules for how a coding agent should work on production code. It emphasizes understanding the request and code first, keeping changes simple and focused, working toward the stated goal, and communicating clearly.

In plain words
What is it for?
Use it to guide an agent before and during implementation, especially when deciding what to inspect, when to ask for clarification, and how to report progress.
Why use it?
It helps prevent common agent mistakes such as guessing about the code, making unnecessary edits, asking too many questions, or claiming more certainty than the evidence supports.

Skill for Claude CodeCodex

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 skills/viktorbezdek/skillstack/coding-discipline
Any agent
npx skills add viktorbezdek/skillstack --skill coding-discipline
Clone the repo
git clone --depth 1 https://github.com/viktorbezdek/skillstack

Made for: Claude Code, Codex.

Per session 224 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,231 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 $0.00224 $0.02231
Opus 5 $0.00112 $0.01115
Sonnet 5 $0.00045 $0.00446
Haiku 4.5 $0.00022 $0.00223

Measured 2d ago against content hash 212231498e0a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

coding-discipline 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.

coding-discipline/skills/coding-discipline/SKILL.md · 192 lines

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.

Coding Discipline

Five empirically-grounded behavioral constraints for production LLM coding. Apply all five as a contract — not a checklist.

Principle 1 — Think Before Coding

Surface confusion. State assumptions. Take a position.

Before writing code:

  • Read the relevant code first. Do not infer when you can read.
  • State your top 2–3 assumptions in one line each. Proceed unless one is high-impact and uncertain.
  • Ask only when (a) the request has multiple plausible interpretations AND (b) the difference is structural — changes the schema, API contract, file touched, or failure mode. Otherwise state your assumption and proceed.
  • When you ask, ask once. Batch as multiple-choice (2–4 options) with a recommended default. Never ask >3 questions per turn.

Three uncertainty types — label explicitly:

Type Meaning Action
spec_uncertainty I don't know what you want Ask
code_uncertainty I don't know what this codebase does Read it
model_uncertainty I don't know if my approach is correct State and verify

Anti-patterns: menu anti-pattern · confident hallucination · sycophantic agreement · question-spam · hidden assumption


Principle 2 — Simplicity First

Smallest correct solution. Earn every abstraction. Calibrate to environment.

Defaults:

  • Fewest lines that pass the acceptance criteria and survive trust-boundary inputs.
  • Three duplications before an abstraction (Metz's rule). One use is not a pattern.
  • Deep modules: small interfaces, rich implementations (Ousterhout). Interface complexity matters more than line count.
  • Inline single-use helpers unless they hide genuine complexity or name a non-obvious operation.

Production calibration — apply when code crosses a trust boundary or runs in production:

  • Validate inputs at the boundary. Not speculative — it is the boundary contract.
  • Handle errors the type system cannot logically exclude. "Impossible" means logically excluded, not "I don't expect it."
  • One structured log per significant branch.
  • Make idempotent operations retry-safe. Make non-idempotent operations explicit.

Read the full file on GitHub · 192 lines

Files

What ships with it

3 files 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. 2d ago First seen · 192 lines · 224 tokens per session scan A 212231498e0a

Subscribe to this mod's changes

coding-discipline is a skill published in the GitHub repository viktorbezdek/skillstack (11 stars, last pushed 2mo ago), licensed MIT. It adds 224 tokens to every session and 2,231 once invoked, about $0.0011 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.

Related

Other skills, from other repositories

gossipcat

Use when installing or setting up gossipcat multi-agent orchestration (parallel review, consensus, adaptive dispatch) in Claude Code or Cursor. Installs the gossipcat MCP server and hands off to gossipstatus() for all live rules.

gossipcat-ai/gossipcat-ai · 50 tokens

Elephant Agent

Complete guide to what Elephant Agent is, how to use it from the CLI, how herd, wake, Personal Model, proactive curiosity, skills, and tools fit together, and how to explain Elephant Agent clearly to users, contributors, or evaluators.

agentic-in/elephant-agent · 54 tokens

libretranslate-markdown-i18n

Machine-translate Markdown / Obsidian / Quartz content into other languages using a self-hosted LibreTranslate instance, preserving frontmatter, headings, emojis, bold/italic, wikilinks (![[...]]/[[...]]) and internal links. Use whenever a user wants to auto-translate a Markdown vault, Obsidian notes, or a…

pedroiff0/awesome-skills · 127 tokens

awesome-skills-master

Master catalog orchestrator and autonomous installer for AI agents. Use when exploring, cloning, discovering, or installing skills, plugins, or MCP servers from awesome-skills without using interactive CLI tools. Guides environment detection, rule adaptation (.mdc/CLAUDE.md), MCP configuration, and strict author…

pedroiff0/awesome-skills · 66 tokens

readme-template

Standard README template for repos — professional structure with badges, overview, table of contents, features/modules, stack, installation, configuration, tests, security, structure, docs, roadmap, contribute, license, author + RepoActivity sections (Star History, repo stats) + profile GIF footer. Use when creating…

pedroiff0/awesome-skills · 72 tokens

docker-single-port-multi-instance

Consolidate multiple Docker Compose app instances (production / test / demo) behind ONE host port using an nginx reverse proxy that routes by URL path prefix (e.g. /demo). Use when a user wants 'one port, several apps/banks' or a demo reachable simultaneously from the main landing page with its own database.

pedroiff0/awesome-skills · 73 tokens