Skip to content
SkillModel-led91 tokens in use

Code Complete

Steve McConnell-inspired construction rules for routines, data, control flow, defensive code, debugging and testing.

3,324 stars on the repository MIT Licenseciembor/agent-rules-books · code-complete
npx skills add ciembor/agent-rules-books --skill code-complete
View source

Install command as written in the repository's README

Skill label

measured from its files

What installing Code Complete costs

26tokens idle
91tokens in use
3,817tokens, up to

Idle is what sits in context while the skill is installed. In use is its instructions, loaded when it runs. Up to adds the files its instructions link. Counts are approximate, made offline with cl100k_base.

Model dependence Model-led

Script-ledMixedModel-led

Mostly instructions, so how well it works depends on the model that follows them.

This describes the skill's structure, how much of it is scripts. It does not say how well it works.

Touches

Nothing detected: no shell, network, file writes, git or credentials in its files.

Declared tags come from the skill's frontmatter; detected ones from its scripts, its code blocks and the commands it names in inline code. This is detected, not audited.

How it scores

Quality

How well the skill is written, counted from its own files: its frontmatter, its steps, examples, stated output and constraints, its size and whether every file it ships is one it names.How we score it →
Needs attention
  • Frontmatter11/15
  • Structure0/25
  • Examples0/15
  • Output2/15
  • Size13/15
  • Resources10/15

Security

Starts at 100 and loses points for each thing in the skill's files that a reader should look at first.How we score it →
Excellent

No findings.

Repository health

Pre-computed score based on development activity, maintenance, community, maturity, and trend momentum.How we score it →
Fair
  • Development activity44
  • Maintenance72
  • Community52
  • Maturity28
  • Momentum40

This skill loads a compact rule set inspired by Steve McConnell’s Code Complete. It tells a coding agent to treat construction quality as a deliberate choice: cohesive routines, purpose-revealing data, simple control flow and checks at trust boundaries.

It applies to implementing, reviewing, debugging, refactoring or tuning production code where defect risk matters.

What You Get

  • A mini rule set with decision rules, trigger rules and a closing checklist for construction work
  • A nano version for tight context budgets and a full version for reference
  • A skill description that makes the agent load the rules for routine, class and implementation tasks

Common Use Cases

  • Designing a routine that is hard to name or mixes setup, validation and side effects
  • Deciding what to validate, assert or reject where input crosses a trust boundary
  • Debugging by reproducing, isolating and explaining a failure before changing code
  • Replacing repeated branching with a validated table

What Makes It Unique

It covers the whole construction loop in one rule set: preparation, routine and data design, defensive handling, integration, debugging, tuning and layout. It asks for pseudocode or intent comments on complex routines and for evidence before performance work, with a measure before and after. The scope is wider than the repository’s readability-focused rule set.

Under The Hood

The skill is a SKILL.md with a name and description, plus Markdown files holding the mini, nano and full versions of the rules. The SKILL.md tells the agent to read the mini file before design or code decisions and the full file only for harder tradeoffs. It contains no scripts. It does not fetch web pages, call APIs, run commands or write files; the agent only reads the rule text.

Join founders building with open source

Opinionated takes, migration guides, cost-saving tips, and insights from the open source ecosystem.

Subscribe on SubstackJoin 750+ subscribers