development-discipline

development-discipline is a skill for Claude Code, Codex from sachinshelke/codevira. It costs 129 tokens per session (1,551 once invoked), scanned A, original, MIT.

A coding-discipline skill that requires the agent to understand existing code, clarify the requested outcome, consider simpler options, and only then write code.

In plain words
What is it for?
Use it before implementing features, fixing bugs, refactoring, creating functions, or modifying project files.
Why use it?
It reduces accidental changes and bugs caused by editing files without first reading them or understanding the task's boundaries.

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/sachinshelke/codevira/development-discipline
Any agent
npx skills add sachinshelke/codevira --skill development-discipline
Clone the repo
git clone --depth 1 https://github.com/sachinshelke/codevira

Made for: Claude Code, 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 development-discipline

README.md
[![agentmods](https://agentmods.dev/badge/skills/sachinshelke/codevira/development-discipline.svg)](https://agentmods.dev/skills/sachinshelke/codevira/development-discipline)
Your own site
<a href="https://agentmods.dev/skills/sachinshelke/codevira/development-discipline"><img src="https://agentmods.dev/badge/skills/sachinshelke/codevira/development-discipline.svg" alt="Measured on agentmods" height="20"></a>
Per session 129 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,551 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 $0.00129 $0.01551
Opus 5 $0.00064 $0.00776
Sonnet 5 $0.00026 $0.00310
Haiku 4.5 $0.00013 $0.00155

Measured 5d ago against content hash e364bee43b64, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

development-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 5d 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.

.claude/skills/development-discipline/SKILL.md · 174 lines

How it starts

The opening of the file, as written. The whole thing — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Development discipline — non-skippable sequence

When this skill triggers, you MUST complete steps 1–4 IN ORDER before calling any Edit, Write, or NotebookEdit tool. Skipping steps produces the kind of silent-failure bugs that shipped to PyPI as v2.0.0.

The 4-step sequence

Step 1 — CONTEXT (read before write)

Before any change, output:

  • "I read <file>:<lines> and the relevant code does X."
  • If editing: quote the exact lines being changed and what they do today.
  • If creating new: list the 3 most similar existing files in the codebase that you considered.

If you haven't read the file you're about to edit, you cannot edit it. Read tool first, Edit tool second. No exceptions.

Step 2 — PURPOSE (rephrase the goal)

Output, before any code:

  • "The user is asking for: ."
  • "Specifically, that means: <list 1-3 concrete outcomes>."
  • "It does NOT mean: ."

The "does NOT mean" line is the discipline anchor. Forces explicit scope. Without it, you'll opportunistically "improve" unrelated code and ship a 47-file PR for a 3-line bug.

Step 3 — REASON (rule out simpler paths)

Output:

  • "Existing code that already does this or something close: ."
  • "Approach chosen: ."
  • "Approaches considered and rejected: ."
  • "Files this will touch (target list): <N files, name them>."

If the touch list has >3 files, justify each one. Refactoring opportunistically beyond the touch list is out of scope. If a new file or dependency is needed, declare it here before you write it.

Step 4 — CODE (minimal diff)

Only NOW may you call Edit/Write/NotebookEdit. Constraints:

  • Only modify files in the Step 3 touch list. Adding files mid-task requires re-doing Step 3.
  • No "while I'm here" cleanups in unrelated files.
  • No reformatting that isn't part of the change.
  • No new dependencies without explicit approval.

After the change:

  • Output "Test that proves the fix: <pytest cmd or test name>."
  • If no test exists, write one before declaring done.

Read the full file on GitHub · 174 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. 5d ago First seen · 174 lines · 129 tokens per session scan A e364bee43b64

Subscribe to this mod's changes

development-discipline is a skill published in the GitHub repository sachinshelke/codevira (12 stars, last pushed 20d ago), licensed MIT. It adds 129 tokens to every session and 1,551 once invoked, about $0.0006 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

test-driven-development

Drives development with tests. Use when implementing any logic, fixing any bug, or changing any behavior. Use when you need to prove that code works, when a bug report arrives, or when you're about to modify existing functionality.

addyosmani/agent-skills · 50 tokens

documentation-and-adrs

Records decisions and documentation. Use when making architectural decisions, changing public APIs, shipping features, or when you need to record context that future engineers and agents will need to understand the codebase.

addyosmani/agent-skills · 43 tokens

idea-refine

Refines raw ideas into sharp, actionable concepts through structured divergent and convergent thinking. Use when an idea is still vague, when you need to stress-test assumptions before committing to a plan, or when you want to expand options before converging on one. Triggers on "ideate", "refine this idea", or…

addyosmani/agent-skills · 75 tokens

peon-ping-log

Log exercise reps for the Peon Trainer. Use when user says they did pushups, squats, or wants to log reps. Examples - "/peon-ping-log 25 pushups", "/peon-ping-log 30 squats", "log 50 pushups".

PeonPing/peon-ping · 64 tokens

excalidraw-architect

Choose and compose the right Excalidraw diagram - architecture, flowchart, sequence, state, ER, swimlane, process, timeline, quadrant, pyramid, venn, loop, gantt, bar, line, scatter, and more - using the excalidraw-architect-mcp server. Use whenever a reader would learn more from a picture than from prose, or when…

BV-Venky/excalidraw-architect-mcp · 101 tokens

ponytail-lazy-senior-dev

Applies the "lazy senior developer" mindset. Use this skill whenever generating, modifying, reviewing code, or fixing bugs to prioritize code reuse, minimalism, YAGNI principles, and root-cause fixes. Also use whenever the user says "ponytail", "be lazy", "lazy mode", "simplest solution", "minimal solution", "yagni"…

GulajavaMinistudio/awesome-copilot-id · 146 tokens