developer-anti-patterns-to-avoid

developer-anti-patterns-to-avoid is a skill for Claude Code from iampantherr/SecureContext. It costs 26 tokens per session (624 once invoked), scanned A, original, MIT.

A list of software-development mistakes to avoid, such as copying unsuitable architectures, merging unread code, hiding errors, and making random debugging changes.

In plain words
What is it for?
It is for guiding architecture decisions, code reviews, error handling, debugging, and day-to-day development practices.
Why use it?
It helps developers recognise choices that make code harder to understand, test, maintain, and debug.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the zc-ctx plugin — 27 skills shipped together

Good fit It is for guiding architecture decisions, code reviews, error handling, debugging, and day-to-day development practices.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/iampantherr/securecontext/developer-anti-patterns-to-avoid
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 iampantherr/SecureContext --skill developer-anti-patterns-to-avoid
Clone the repo
git clone --depth 1 https://github.com/iampantherr/SecureContext

Made for: Claude Code.

Or install zc-ctx, the plugin that ships this one along with the rest of its 27 skills.

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 developer-anti-patterns-to-avoid

README.md
[![agentmods](https://agentmods.dev/badge/skills/iampantherr/securecontext/developer-anti-patterns-to-avoid/github.svg)](https://agentmods.dev/skills/iampantherr/securecontext/developer-anti-patterns-to-avoid)
Your own site
<a href="https://agentmods.dev/skills/iampantherr/securecontext/developer-anti-patterns-to-avoid"><img src="https://agentmods.dev/badge/skills/iampantherr/securecontext/developer-anti-patterns-to-avoid/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 developer-anti-patterns-to-avoid

Your own site · 80×15
<a href="https://agentmods.dev/skills/iampantherr/securecontext/developer-anti-patterns-to-avoid"><img src="https://agentmods.dev/badge/skills/iampantherr/securecontext/developer-anti-patterns-to-avoid.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 26 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 624 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 $0.00026 $0.00624
Opus 5 $0.00013 $0.00312
Sonnet 5 $0.00005 $0.00125
Haiku 4.5 $0.00003 $0.00062

Measured yesterday against content hash 40012bf813b6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

developer-anti-patterns-to-avoid 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.

skills/_staging_v0_19/developer-anti-patterns-to-avoid.skill.md · 39 lines

What it actually says

ANTI-PATTERNS TO AVOID

(Extracted from roles.json deepPrompt for the developer role during the v0.19.0 role/skill split. Original content preserved verbatim. Edit freely; the mutator will propose improvements based on skill_runs telemetry once this skill is invoked by an agent.)


  • Cargo-cult architecture: Copying Netflix's microservice architecture because it worked for Netflix, without Netflix's scale, team size, or traffic patterns.
  • Resume-driven development: Choosing technologies because they're interesting to learn, not because they're the right fit.
  • Optimistic merging: Merging PRs without understanding what they do. "LGTM" without reading is not code review.
  • Shotgun debugging: Making random changes and hoping the bug goes away. Each change must test a specific hypothesis.
  • God objects: Classes or modules that know too much and do too much. If it imports more than 10 other modules, it has boundary problems.
  • Swallowed exceptions: catch (e) {} or catch (e) { return null; }. Errors must be either handled or propagated, never silently discarded.
  • Magic numbers and strings: Literals in logic with no explanation. Name your constants and explain their origin.
  • Synchronous blocking in async contexts: CPU-intensive work on the event loop thread. Long-running synchronous operations in async code starve the runtime.
  • Over-engineering for scale you don't have: Message queues for 100 daily users. Kubernetes for a three-endpoint API. Complexity has carrying cost whether or not it buys you anything.
  • Test theater: 95% code coverage on trivially correct code, zero coverage on complex business logic. Coverage is a floor, not a goal.
  • Dependency injection frameworks for dependency injection problems: If you need a DI framework to manage your dependencies, you have too many dependencies. Simplify the design.
  • Distributed monolith: Microservices that share a database, require simultaneous deployment, or fail together. You've paid the cost of distributed systems without gaining the benefits.

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. yesterday First seen · 39 lines · 26 tokens per session scan A 40012bf813b6

Subscribe to this mod's changes

developer-anti-patterns-to-avoid is a skill published in the GitHub repository iampantherr/SecureContext (8 stars, last pushed 2d ago), licensed MIT. It adds 26 tokens to every session and 624 once invoked, about $0.0001 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 2026-09-08.

Related

Other skills, from other repositories