Files
Bo c6558508d1 Consolidate AgentOps into a 34-skill engineering menu (#1133)
AgentOps' 55-skill catalog contained overlapping entry points, stale
routes and descriptions that could lose meaningful guidance in the Codex
projection. This change consolidates 21 roots into existing owners,
leaving 34 distinct skills and a generated, task-oriented menu. README
documents every retired name and its replacement.

Planning now establishes observable behavior in the caller's existing
intent, using proportional Given/When/Then examples and domain language.
Implementation and final validation carry those same examples forward.
Original adaptations informed by Matt Pocock's engineering skills
strengthen existing owners rather than adding a new workflow. Routine
edits need no mandatory plan, coverage report, mutation exercise or
learning artifact.

Codex retains complete source descriptions and translates explicit-only
invocation policy. All descriptions fit the existing 180-character
limit; the root instructions retain their 250-line limit. Generated
catalogs, projections, routers, moved references/helpers and their live
consumers are updated together. RPI remains explicitly selected.

Validation passed: projection/conformance checks, the local aggregate
(10 passed; one existing optional-directory skip), and exact-commit CI
covering the complete gate registry, Bats, Go build/vet/race/coverage,
Windows and security. A fresh author-distinct reviewer passed all
acceptance criteria over the complete 573-path subject at
aa642a55d6, including the installed-link
and protected-backup changes. Review findings were repaired and
revalidated. Existing ranker goldens are regression checks, not
model-quality measurements. A fixed six-case fresh-context pilot
supplied an exact candidate menu: three of four targeted cases loaded
expected guidance, a simple refactor selected no skill, and both
no-skill controls selected none. No wrong owner was selected. This pilot
preceded final wording repairs for existing ranker/context limits; it
does not establish installed automatic activation, coding benefit or
savings. No live coding task was run in that pilot.
2026-09-10 22:18:05 -04:00
..

Coding Standards

Skills Integration

These standards are also available as a library skill in domain-kit:

plugins/domain-kit/skills/standards/references/
├── python.md
├── go.md
├── typescript.md
├── shell.md
├── yaml.md
├── json.md
├── rust.md
├── markdown.md
└── openai.md (+ related OpenAI references)

Skills like /bug-hunt and /complexity depend on the standards library for consistent language-specific guidance.


Standards Index

Language/Format Document Gate Pre-commit AI-Friendly
Python python-style-guide.md CC ≤ 10 ruff ★★★★★
Shell/Bash shell-script-standards.md shellcheck shellcheck ★★★★★
Go golang-style-guide.md golangci-lint, CC ≤ 10 - ★★★★★
Rust cargo clippy, CC ≤ 10 - ★★★★★
TypeScript typescript-standards.md tsc --strict eslint ★★★★★
YAML/Helm yaml-helm-standards.md yamllint yamllint ★★★★★
Markdown markdown-style-guide.md markdownlint - ★★★★★
JSON/JSONL json-jsonl-standards.md jq/prettier - ★★★★★
Documentation Tags tag-vocabulary.md - - ★★★★★

What Makes These Standards AI-Agent-Friendly

Every standard in this repository is optimized for AI agent execution:

Feature Implementation
Tables over prose Scannable, parallel parsing
Decision trees Executable if/then logic
Common Errors tables Symptom → Cause → Fix
Anti-Patterns (named) Recognizable error states
AI Agent Guidelines ALWAYS/NEVER rules
Explicit thresholds Numbers, not "be careful"
Copy-paste examples Ready to use, not fragments

Complexity Requirements

All functions MUST meet complexity thresholds:

Language Tool Threshold Style Guide
Python radon/xenon CC ≤ 10 Yes
Go gocyclo CC ≤ 10 Yes
Rust cargo clippy Clippy warnings = 0
Shell shellcheck Pass all Yes
TypeScript tsc --strict No errors Yes
YAML/Helm yamllint Pass all Yes

Pre-commit Enforcement

Standards are enforced via pre-commit hooks where available.

Quick Start

# Install hooks (one-time)
pre-commit install

# Run manually
pre-commit run --all-files

# Or skip hooks (not recommended)
git commit --no-verify

Manual Validation Commands

Language Command
Python ruff check scripts/ && xenon scripts/ --max-absolute B
Go golangci-lint run ./... && gocyclo -over 10 ./...
Rust cargo clippy --all-targets --all-features -- -D warnings && cargo test
Shell shellcheck scripts/*.sh
TypeScript tsc --noEmit && eslint . --ext .ts,.tsx
YAML yamllint .
Markdown npx markdownlint '**/*.md'
JSON jq empty config.json (validates syntax)

Standard Document Structure

Each standard follows a consistent format:

# Standard Name

## Quick Reference
[Table of key rules and values]

## [Topic Sections]
[Detailed guidance with examples]

## Common Errors
[Symptom | Cause | Fix table]

## Anti-Patterns
[Named patterns to avoid]

## AI Agent Guidelines
[ALWAYS/NEVER rules table]

## Summary
[Key takeaways list]

Common Configuration Files (Examples)

These are common config files you may choose to add to a project that adopts these standards. AgentOps does not require them, and this repository does not ship every file listed below.

File Purpose
.pre-commit-config.yaml Hook definitions
.yamllint.yml YAML linting rules
.markdownlint.yml Markdown linting rules
.shellcheckrc Shell linting rules
.prettierrc JSON/Markdown formatting
pyproject.toml Python tool settings (ruff, pytest)
.golangci.yml Go linting configuration
rustfmt.toml Rust formatting rules
clippy.toml Rust linting configuration
tsconfig.json TypeScript compiler settings
eslint.config.js TypeScript/JS linting

Contributing

To update a standard:

  1. Edit the standard directly in docs/standards/
  2. Run validation to ensure format compliance

Adding a New Standard

  1. Follow the document structure template above
  2. Include: Quick Reference, Common Errors, Anti-Patterns, AI Guidelines
  3. Add to this README's index table
  4. Update related links in other standards

Created: 2024-12-30 Last Updated: 2026-02-09 Related: SKILL-TIERS.md