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.
npx agentmods add skills/vindm/dotclaude/operating-disciplinenpx skills add vindm/dotclaude --skill operating-disciplinegit clone --depth 1 https://github.com/vindm/dotclaudeWrote 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.
[](https://agentmods.dev/skills/vindm/dotclaude/operating-discipline)<a href="https://agentmods.dev/skills/vindm/dotclaude/operating-discipline"><img src="https://agentmods.dev/badge/skills/vindm/dotclaude/operating-discipline.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00093 | $0.01548 |
| Opus 5 | $0.00046 | $0.00774 |
| Sonnet 5 | $0.00019 | $0.00310 |
| Haiku 4.5 | $0.00009 | $0.00155 |
Grade A, and why
operating-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 3d 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.
How it starts
The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Operating discipline
The universal method for doing any substantive task well. Project-specific values it refers to — the exact lint/test commands, the "fresh artifact" format, the "pure mechanics" boundary, the escalation trigger table — are supplied by the consuming project's local layer (its CLAUDE.md / .claude/); this skill states the method.
How you work — four principles, each with a test
-
Understand before you build. Resolve ambiguity before writing code. Grill the user for what only they know (intent, taste, priorities); trace the code for what it can tell you — read the path end to end, name the real failure, don't hypothesis-spam. Push back on requests that won't produce something better. When no one's available to answer (unattended / CI / batch run), state assumptions up front and flag every decision taken on an assumption — never stall, never guess silently. The test: you can state the problem correctly — every assumption confirmed by the user or verified in code, none silent.
-
Reason to the right solution. For any non-obvious choice, weigh 2–3 real alternatives with their trade-offs and recommend one. Elegant over expedient; slower-but-right over fast-but-shallow. One option is not a decision — it's a default in disguise. The test: the design is one you reasoned to, not the first thing that worked.
-
Goal-driven, complete execution. Reframe imperatives into verifiable checks ("fix the bug" → "write a failing test, then make it pass"). Implement completely (best result, not smallest diff) but stay surgical on scope creep — complete the task, not the adjacent five. Reuse existing building blocks before writing new ones. Adversarial self-check, then verify: run this project's lint + test gates green, and produce a fresh artifact (screenshot / captured output / passing example) for anything user-facing. The test: the success criterion is stated and observably met.
-
Depth by default, ceremony on demand. Every task except pure mechanics gets principles 1–3 in full. Depth ≠ ceremony — reason hard, but don't spin up agents, audit chains, or multi-step pipelines unless a trigger fires or the user asks. The test: analysis went deep, process stayed lean.
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.
- 3d ago First seen · 53 lines · 93 tokens per session scan A 378797fd6fd7
operating-discipline is a skill published in the GitHub repository vindm/dotclaude (1 stars, last pushed 6d ago), licensed MIT. It adds 93 tokens to every session and 1,548 once invoked, about $0.0005 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.
Other skills, from other repositories
claude-md-review
Audit a CLAUDE.md file for the patterns that actually degrade Claude Code's output — vagueness, unnamed files, stale facts, and bloat. Use when asked to review, audit, improve, shrink, or fix a CLAUDE.md, and when a project's results feel inconsistent or Claude keeps rediscovering the same context.
code-reviewer
Automatic code quality and best practices analysis. Use proactively when files are modified, saved, or committed. Analyzes code style, patterns, potential bugs, and security basics. Triggers on file changes, git diff, code edits, quality mentions.
git-commit-helper
Generate conventional commit messages automatically. Use when user runs git commit, stages changes, or asks for commit message help. Analyzes git diff to create clear, descriptive conventional commit messages. Triggers on git commit, staged changes, commit message requests.
test-generator
Automatically suggest tests for new functions and components. Use when new code is written, functions added, or user mentions testing. Creates test scaffolding with Jest, Vitest, Pytest patterns. Triggers on new functions, components, test requests, testing mentions.
api-documenter
Auto-generate API documentation from code and comments. Use when API endpoints change, or user mentions API docs. Creates OpenAPI/Swagger specs from code. Triggers on API file changes, documentation requests, endpoint additions.
readme-updater
Keep README files current with project changes. Use when project structure changes, features added, or setup instructions modified. Suggests README updates based on code changes. Triggers on significant project changes, new features, dependency changes.