Catalog
affaan-m/plankton-code-quality

affaan-m

plankton-code-quality

Write-time code quality enforcement using Plankton — auto-formatting, linting, and Claude-powered fixes on every file edit via hooks.

global
New~1.9k
v1.1Saved May 11, 2026

Plankton Code Quality Skill

Integration reference for Plankton (credit: @alxfazio), a write-time code quality enforcement system for Claude Code. Plankton runs formatters and linters on every file edit via PostToolUse hooks, then spawns Claude subprocesses to fix violations the agent didn't catch.

When to Use

  • You want automatic formatting and linting on every file edit (not just at commit time)
  • You need defense against agents modifying linter configs to pass instead of fixing code
  • You want tiered model routing for fixes (Haiku for simple style, Sonnet for logic, Opus for types)
  • You work with multiple languages (Python, TypeScript, Shell, YAML, JSON, TOML, Markdown, Dockerfile)

How It Works

Three-Phase Architecture

Every time Claude Code edits or writes a file, Plankton's multi_linter.sh PostToolUse hook runs:

Phase 1: Auto-Format (Silent)
├─ Runs formatters (ruff format, biome, shfmt, taplo, markdownlint)
├─ Fixes 40-50% of issues silently
└─ No output to main agent

Phase 2: Collect Violations (JSON)
├─ Runs linters and collects unfixable violations
├─ Returns structured JSON: {line, column, code, message, linter}
└─ Still no output to main agent

Phase 3: Delegate + Verify
├─ Spawns claude -p subprocess with violations JSON
├─ Routes to model tier based on violation complexity:
│   ├─ Haiku: formatting, imports, style (E/W/F codes) — 120s timeout
│   ├─ Sonnet: complexity, refactoring (C901, PLR codes) — 300s timeout
│   └─ Opus: type system, deep reasoning (unresolved-attribute) — 600s timeout
├─ Re-runs Phase 1+2 to verify fixes
└─ Exit 0 if clean, Exit 2 if violations remain (reported to main agent)

What the Main Agent Sees

Scenario Agent sees Hook exit
No violations Nothing 0
All fixed by subprocess Nothing 0
Violations remain after subprocess [hook] N violation(s) remain 2
Advisory (duplicates, old tooling) [hook:advisory] ... 0

The main agent only sees issues the subprocess couldn't fix. Most quality problems are resolved transparently.

Config Protection (Defense Against Rule-Gaming)

LLMs will modify .ruff.toml or biome.json to disable rules rather than fix code. Plankton blocks this with three layers:

  1. PreToolUse hookprotect_linter_configs.sh blocks edits to all linter configs before they happen
  2. Stop hookstop_config_guardian.sh detects config changes via git diff at session end
  3. Protected files list.ruff.toml, biome.json, .shellcheckrc, .yamllint, .hadolint.yaml, and more

Package Manager Enforcement

A PreToolUse hook on Bash blocks legacy package managers:

  • pip, pip3, poetry, pipenv → Blocked (use uv)
  • npm, yarn, pnpm → Blocked (use bun)
  • Allowed exceptions: npm audit, npm view, npm publish

Setup

Quick Start

Note: Plankton requires manual installation from its repository. Review the code before installing.

# Install core dependencies
brew install jaq ruff uv

# Install Python linters
uv sync --all-extras

# Start Claude Code — hooks activate automatically
claude

No install command, no plugin config. The hooks in .claude/settings.json are picked up automatically when you run Claude Code in the Plankton directory.

Per-Project Integration

To use Plankton hooks in your own project:

  1. Copy .claude/hooks/ directory to your project
  2. Copy .claude/settings.json hook configuration
  3. Copy linter config files (.ruff.toml, biome.json, etc.)
  4. Install the linters for your languages

Language-Specific Dependencies

Language Required Optional
Python ruff, uv ty (types), vulture (dead code), bandit (security)
TypeScript/JS biome oxlint, semgrep, knip (dead exports)
Shell shellcheck, shfmt
YAML yamllint
Markdown markdownlint-cli2
Dockerfile hadolint (>= 2.12.0)
TOML taplo
JSON jaq

Pairing with ECC

Complementary, Not Overlapping

Concern ECC Plankton
Code quality enforcement PostToolUse hooks (Prettier, tsc) PostToolUse hooks (20+ linters + subprocess fixes)
Security scanning AgentShield, security-reviewer agent Bandit (Python), Semgrep (TypeScript)
Config protection PreToolUse blocks + Stop hook detection
Package manager Detection + setup Enforcement (blocks legacy PMs)
CI integration Pre-commit hooks for git
Model routing Manual (/model opus) Automatic (violation complexity → tier)
  1. Install ECC as your plugin (agents, skills, commands, rules)
  2. Add Plankton hooks for write-time quality enforcement
  3. Use AgentShield for security audits
  4. Use ECC's verification-loop as a final gate before PRs

Avoiding Hook Conflicts

If running both ECC and Plankton hooks:

  • ECC's Prettier hook and Plankton's biome formatter may conflict on JS/TS files
  • Resolution: disable ECC's Prettier PostToolUse hook when using Plankton (Plankton's biome is more comprehensive)
  • Both can coexist on different file types (ECC handles what Plankton doesn't cover)

Configuration Reference

Plankton's .claude/hooks/config.json controls all behavior:

{
  "languages": {
    "python": true,
    "shell": true,
    "yaml": true,
    "json": true,
    "toml": true,
    "dockerfile": true,
    "markdown": true,
    "typescript": {
      "enabled": true,
      "js_runtime": "auto",
      "biome_nursery": "warn",
      "semgrep": true
    }
  },
  "phases": {
    "auto_format": true,
    "subprocess_delegation": true
  },
  "subprocess": {
    "tiers": {
      "haiku":  { "timeout": 120, "max_turns": 10 },
      "sonnet": { "timeout": 300, "max_turns": 10 },
      "opus":   { "timeout": 600, "max_turns": 15 }
    },
    "volume_threshold": 5
  }
}

Key settings:

  • Disable languages you don't use to speed up hooks
  • volume_threshold — violations > this count auto-escalate to a higher model tier
  • subprocess_delegation: false — skip Phase 3 entirely (just report violations)

Environment Overrides

Variable Purpose
HOOK_SKIP_SUBPROCESS=1 Skip Phase 3, report violations directly
HOOK_SUBPROCESS_TIMEOUT=N Override tier timeout
HOOK_DEBUG_MODEL=1 Log model selection decisions
HOOK_SKIP_PM=1 Bypass package manager enforcement

References

  • Plankton (credit: @alxfazio)
  • Plankton REFERENCE.md — Full architecture documentation (credit: @alxfazio)
  • Plankton SETUP.md — Detailed installation guide (credit: @alxfazio)

ECC v1.8 Additions

Copyable Hook Profile

Set strict quality behavior:

export ECC_HOOK_PROFILE=strict
export ECC_QUALITY_GATE_FIX=true
export ECC_QUALITY_GATE_STRICT=true

Language Gate Table

  • TypeScript/JavaScript: Biome preferred, Prettier fallback
  • Python: Ruff format/check
  • Go: gofmt

Config Tamper Guard

During quality enforcement, flag changes to config files in same iteration:

  • biome.json, .eslintrc*, prettier.config*, tsconfig.json, pyproject.toml

If config is changed to suppress violations, require explicit review before merge.

CI Integration Pattern

Use the same commands in CI as local hooks:

  1. run formatter checks
  2. run lint/type checks
  3. fail fast on strict mode
  4. publish remediation summary

Health Metrics

Track:

  • edits flagged by gates
  • average remediation time
  • repeat violations by category
  • merge blocks due to gate failures
Files1
1 files · 1.0 KB

Select a file to preview

Overall Score

78/100

Grade

B

Good

Safety

78

Quality

80

Clarity

82

Completeness

68

Summary

Plankton Code Quality Skill is an integration guide for a Claude Code write-time code quality enforcement system that auto-formats, lints, and uses Claude subprocesses to fix violations across multiple languages (Python, TypeScript, Shell, YAML, JSON, etc.). It operates via PostToolUse hooks that run in three phases: auto-formatting, violation collection, and model-routed subprocess delegation with config protection mechanisms to prevent rule-gaming.

Detected Capabilities

shell execution (formatters, linters)file system operations (reading/writing project files)hook management (PreToolUse, PostToolUse, Stop hooks)subprocess spawning with model routingenvironment variable configurationgit operations (diff detection)JSON configuration parsingpackage manager detection and blockingmulti-language code analysis

Trigger Keywords

Phrases that MCP clients use to match this skill to user intent.

plankton code qualitywrite-time lintingauto-format on editclaude subprocess fixesconfig protectionmulti-language lintingmodel-routed violations

Risk Signals

INFO

Subprocess spawning with claude -p command using violation JSON payloads

Phase 3: Delegate + Verify section
INFO

Package manager blocking via PreToolUse hook on Bash with whitelist exceptions (npm audit, npm view, npm publish allowed)

Package Manager Enforcement section
INFO

Config file protection via PreToolUse hook with protected files list (.ruff.toml, biome.json, etc.)

Config Protection section
INFO

Git diff usage for detecting config changes at session end

Stop hook — stop_config_guardian.sh
INFO

Environment variable overrides for hook behavior (HOOK_SKIP_SUBPROCESS, HOOK_SUBPROCESS_TIMEOUT, HOOK_DEBUG_MODEL, HOOK_SKIP_PM)

Environment Overrides section

Use Cases

  • Enforce code quality automatically on every file edit without manual linter runs
  • Route code violations to appropriate model tiers (Haiku, Sonnet, Opus) based on complexity
  • Prevent agent rule-gaming by blocking edits to linter configuration files
  • Enforce package manager standards (uv, bun) while allowing legitimate operations
  • Support multi-language projects with unified formatting and linting pipelines
  • Integrate Plankton hooks into existing Claude Code projects for transparent quality fixes

Quality Notes

  • Well-structured documentation with clear three-phase architecture explanation using flowcharts
  • Comprehensive language support matrix and dependency table help users understand installation scope
  • Defensive design against common agent gaming patterns (config modification) is well-articulated with three-layer protection
  • Good integration guidance with ECC (Extract Code Context) showing complementary rather than overlapping functionality
  • Configuration reference provided with JSON schema showing all tunable parameters and their purposes
  • Clear explanation of what agent sees vs. what is handled transparently by hooks reduces surprises
  • Environment overrides provide escape hatches for debugging and override scenarios
  • Some setup gaps: no explicit error handling instructions for when dependencies are missing or hooks fail
  • References to external REFERENCE.md and SETUP.md documentation suggest skill assumes supplementary docs exist (not self-contained)
  • Model routing strategy based on violation complexity is sound but requires subprocess context awareness from agents
Model: claude-haiku-4-5-20251001Analyzed: May 11, 2026

Reviews

Add this skill to your library to leave a review.

No reviews yet

Be the first to share your experience.

Version History

v1.1

Content updated

2026-04-20

Latest
v1.0

Seeded from github.com/affaan-m/everything-claude-code

2026-03-16

Add affaan-m/plankton-code-quality to your library

Command Palette

Search for a command to run...

affaan-m/plankton-code-quality | SkillRepo