agentsclimarketplace

Plankton code quality

Skill Sheshiyer/skill-clusters/skills/plankton-code-quality

Write-time code quality enforcement using Plankton — auto-formatting, linting, and Claude-powered fixes on every file edit via PostToolUse hooks. USE WHEN you want automatic format/lint on each edit, defense against agents weakening linter configs, or tiered model routing for fixes across many languages.From its SKILL.md

Install
npx -y skills add Sheshiyer/skill-clusters --skill plankton-code-quality

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

8.3 KB, ~2.1k tokens by cl100k_base, as published. Nobody here has run it

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

ScenarioAgent seesHook exit
No violationsNothing0
All fixed by subprocessNothing0
Violations remain after subprocess[hook] N violation(s) remain2
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

LanguageRequiredOptional
Pythonruff, uvty (types), vulture (dead code), bandit (security)
TypeScript/JSbiomeoxlint, semgrep, knip (dead exports)
Shellshellcheck, shfmt
YAMLyamllint
Markdownmarkdownlint-cli2
Dockerfilehadolint (>= 2.12.0)
TOMLtaplo
JSONjaq

Pairing with other quality gates

Complementary, Not Overlapping

Plankton is the write-time gate (every file edit). It pairs cleanly with a commit-time gate (verification-loop) and a release-time gate (production-audit). Plankton catches style/lint/type drift the instant it lands; the later gates catch behavior and shipping risk.

ConcernA baseline formatter hookPlankton
Code quality enforcementPostToolUse hooks (Prettier, tsc)PostToolUse hooks (20+ linters + subprocess fixes)
Security scanningexternal security reviewerBandit (Python), Semgrep (TypeScript)
Config protectionPreToolUse blocks + Stop hook detection
Package managerDetection + setupEnforcement (blocks legacy PMs)
CI integrationPre-commit hooks for git
Model routingManual (/model opus)Automatic (violation complexity → tier)

Recommended Combination

  1. Add Plankton hooks for write-time quality enforcement
  2. Run a dedicated security audit on top
  3. Use verification-loop as a final gate before PRs

Avoiding Hook Conflicts

If running Plankton alongside a separate Prettier formatter hook:

  • A standalone Prettier hook and Plankton's biome formatter may conflict on JS/TS files
  • Resolution: disable the standalone Prettier PostToolUse hook when using Plankton (Plankton's biome is more comprehensive)
  • Both can coexist on different file types (the standalone hook 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

VariablePurpose
HOOK_SKIP_SUBPROCESS=1Skip Phase 3, report violations directly
HOOK_SUBPROCESS_TIMEOUT=NOverride tier timeout
HOOK_DEBUG_MODEL=1Log model selection decisions
HOOK_SKIP_PM=1Bypass package manager enforcement

References

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

Strict-mode profile

Copyable Hook Profile

Set strict quality behavior:

export QUALITY_HOOK_PROFILE=strict
export QUALITY_GATE_FIX=true
export 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

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Keep looking

Skills are one crate of 326,851. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.