claude

python-harness

Python engineering for Claude Code: eight skills (build-web-service, enterprise-design, design-persistence, design-tests, data-engineering, data-analysis, automate-task and tactical-slop-review), four agents (pylens, pep-talk, reviewer and test-engineer), the ty language server, standard-library docs on demand, and hooks that brief each session on the project's Python toolchain and a note whenever a Bash command runs plain python instead of uv run python.

2 on GitHubby Ryanv0.2.0updated 10 days ago
/

Plugin python-harness from marketplace rygentic-harness in rhawk117/rygentic-harness. Commands read from the repo's manifest — 10 days ago.

This plugin runs code on your machine — its hooks fire automatically on events like tool use and it starts local MCP servers. The exact commands are listed below; read them before installing.

What it installs

Skills (8)

  • automate-task

    Turns one automation request into one runnable Python script with inline dependencies, a command line, logging, a dry run and exit codes. Confirms the domain with the user, presents package and design options with a recommendation, maps a parallelism level to worker counts, keeps every technical cho

  • build-web-service

    Leads the design of a Python HTTP service from a requirements interview to one vertical-slice handoff packet: classifies the service, brings in the contract, persistence and test design skills, and settles identity, deferred work, rate limits, caching and deployment lifecycle. The primary recipe is

  • data-analysis

    Answers a question from data with a result that can be defended: fixes the question, the observation grain, the denominator and the baseline before choosing a method, validates along the deployment boundary without leakage, and reports effect size with uncertainty and what the evidence does not show

  • data-engineering

    Makes data code correct first and cheap second: pins down the output, estimates sizes before running, checks schema and join contracts, chooses the engine, reads the query plan before tuning, and has results returned or published as artifacts instead of printed. Covers synthetic data and tests for d

  • design-persistence

    Designs how a Python system stores durable records: record meaning and access patterns, invariants and state transitions, where each constraint is enforced, transaction and concurrency ownership, repository boundaries and a migration plan. Chooses the database from the requirements, writes no projec

  • design-tests

    Designs the tests that give evidence for a Python contract: scenarios chosen by ranked risk, each aimed at public behavior and able to fail for a plausible broken implementation. Writes no files: it briefs the test-engineer agent to write and run the tests, strict XFAIL where the implementation is m

  • enterprise-design

    Turns business intent into a caller-facing Python contract before implementation: outcomes, a rule table, the architecture boundary, and the exact public types, signatures and error classes, shown to the user as declarations. Keeps partial success, duplicates, expected rejection and dependency failu

  • tactical-slop-review

    Reviews a Python pull request, branch or codebase against the expert's engineering guide and writes one file: PYTHON-REVIEW.md with findings or REFACTOR-PLAN.md with an ordered refactor plan. Facts come from the plugin's MCP tools and pylens subagents, every citation is checked by a tool before it s

Subagents (4)

  • pep-talk

    Use this agent as a read-only Python standard-library documentation helper when a question needs an exact API name, signature, or documented behavior; whether a symbol was added, changed, deprecated, or removed across versions; a comparison of documented stdlib alternatives for a stated need; a chec

  • pylens

    Read-only fact gatherer for a Python code review. Given one import-graph cluster and a question set, returns cited, neutral facts as Markdown tables. Dispatch this agent only when the review lead needs code-grounded evidence, as the tactical-slop-review skill does.

  • reviewer

    Use this agent when a meaningful completed Python slice needs independent review, when a public API changes, or when a conclusion needs scrutiny. It reports evidence-backed findings and does not rewrite the work.

  • test-engineer

    Use this agent when a Python contract needs a risk-ranked, minimal test portfolio spanning domain rules, use-case behavior, repository contracts, or adapter integration, or when brittle tests must be challenged against plausible broken implementations. Invoke after caller-visible promises are suppli

MCP servers (1)

  • python-harness

    runs: uv tool run --python >=3.14 --exclude-newer 2026-10-05T04:00:00Z --with tree-sitter==0.26.0 --with tree-sitter-bash==0.25.1 --with anyio==4.15.1 --with beautifulsoup4==4.15.0 --with cachetools==7.2.0

Hooks (2)

  • SessionStart

    "${CLAUDE_PLUGIN_ROOT}/bin/python-harness" hooks session-start || exit 1

  • PreToolUse

    "${CLAUDE_PLUGIN_ROOT}/bin/python-harness" hooks guard-python || exit 1

Language servers (1)

  • ty
View source on GitHub

More from rhawk117/rygentic-harness

All 4 plugins →

Context management for agentic coding in Claude Code. The main session keeps its window for judgment, every task runs in a worker with a clean context and a precise brief, state survives compaction, and the record of the work goes to GitHub or Jira instead of your repository.

19 skills · hooks

2

Terraform and IaC repositories in Claude Code: an MCP server that checks modules, digests plans, traces change impact and looks up provider schemas, four subagents, skills, terraform-ls, and hooks that format and check .tf files as Claude works.

8 skills · 4 agents · 1 MCP server · hooks · LSP

2

vibe-code

claude

Eleven skills for building, hardening and tuning Claude Code agents, skills, hooks, instructions, MCP servers, and loops, plus a vibe-code CLI that needs uv on PATH.

11 skills

2

Similar plugins

Matt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).

39 skills

mattpocock/skills 323,108

ecc

claudecodex

Harness-native ECC operator layer - 71 agents, 314 skills, 98 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses

200 skills · 98 commands · 71 agents · 1 MCP server · hooks

affaan-m/ECC 302,088

Automated code review for pull requests using multiple specialized agents with confidence-based scoring to filter false positives

1 command

anthropics/claude-code 155,476

Skill: add headroom-ai compress() to a Python or TypeScript app to cut LLM input tokens (tool outputs, logs, JSON, chat history). No API key.

1 skill

headroomlabs-ai/headroom 79,508

Generate natively editable PPTX from PDF / DOCX / URL / Markdown — real DrawingML shapes, text boxes, charts, and animations. Note: run `pip install -r requirements.txt` inside the installed plugin directory for the Python post-processing scripts to work.

1 skill

hugohe3/ppt-master 76,375

Use Alibaba Open Code Review from local Codex.

2 skills

alibaba/open-code-review 50,068

Maintain python-harness?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex plugins4 plugins