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 instructions/rjmurillo/ai-agents/code-qualitygit clone --depth 1 https://github.com/rjmurillo/ai-agentsWrote 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/instructions/rjmurillo/ai-agents/code-quality)<a href="https://agentmods.dev/instructions/rjmurillo/ai-agents/code-quality"><img src="https://agentmods.dev/badge/instructions/rjmurillo/ai-agents/code-quality.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 | $0.03178 | $0.03178 |
| Opus 5 | $0.01589 | $0.01589 |
| Sonnet 5 | $0.00636 | $0.00636 |
| Haiku 4.5 | $0.00318 | $0.00318 |
Grade A, and why
ai-agents code-quality.instructions.md 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.
How it starts
The opening of the file, as written. The whole thing — 238 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Quality
This rule sets the baseline quality standard for all code you write or change. It merges the everyday fundamentals from Robert Martin's Clean Code and Steve McConnell's Code Complete. Apply these rules on every edit. They override stylistic preferences but defer to project conventions found in AGENTS.md, .editorconfig, and .markdownlint-cli2.yaml.
Naming
Names are documentation. A reader who knows nothing about the change should understand the code from the names alone.
- Choose intention-revealing names.
daysSinceLastLoginbeatsdordelta.isExpiredbeatsflag. - Use pronounceable, searchable names.
customerCountbeatscc. - Drop abbreviations and Hungarian prefixes.
userListbeatsusrLstorlstUsr. - Use one word per concept across the whole codebase. Pick
fetch,get, orretrieveand stay with it. - Names track scope. Short names fit short scopes. Long names fit long-lived classes and public APIs.
- Class names are nouns. Method names are verbs. Boolean methods read as predicates:
isReady,hasChildren,canCommit. - Avoid disinformation. Do not call something
accountListif it is aSet. Do not name abooleanstatus. - Mirror the domain. If the team says "tenant," do not write
customerin code. Ubiquitous language reduces translation cost.
When you find yourself writing a comment to explain a name, rename instead.
Functions
Functions are the core unit of design. Keep them small, single-purpose, and easy to test.
- Functions should do one thing. If you can describe the function as "X and Y," split it.
- Prefer 20 lines or fewer. The project ceiling is 60. Past that, extract.
- Aim for cyclomatic complexity of 10 or lower. Past that, extract or use table-driven logic.
- Limit parameters to three. Prefer two. Zero is best. Bundle related parameters into a parameter object.
- Avoid flag arguments. A
booleanargument means the function does two things. Split it intorenderTextual()andrenderHtml(). - Output parameters are confusing. Return a value, a tuple, or a small record.
- One level of abstraction per function. A high-level orchestrator should not parse strings; a parser should not log analytics.
- Apply the Stepdown Rule. Read top to bottom: each function calls the next level of detail.
- No side effects beyond the function's name.
validatePassword(user)should not also log the user in.
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 · 238 lines · 3,178 tokens per session scan A 09b6b94a49d0
ai-agents code-quality.instructions.md is an instructions file published in the GitHub repository rjmurillo/ai-agents (45 stars, last pushed today), licensed MIT. It adds 3,178 tokens to every session, about $0.0159 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 2026-09-03.
Other instructions, from other repositories
abtars AGENTS.md
Instructions for aksika/abtars, covering agents.md, quick commands, architecture, model-call chokepoint: spin(spec) (#1271) and external dependency: abmind.
Alex_Skill_Mall mall-maintenance-rules.instructions.md
Always-on routing for Mall maintenance work — fires the right Mall skill at the right moment. Distinguishes Mall-owned automation from out-of-scope editorial work.
gameforge AGENTS.md
Instructions for robcost/gameforge, covering general guidelines for working with nx, scaffolding & generators and when to use nxdocs.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.