claude

deeppairing

Delegate implementation without losing the decisions that matter: a local companion UI where Claude Code's findings, specs, options, and plans are shaped with you. Rejected approaches are checked by words and a short synonym list, not meaning: a matching present_* proposal is refused with your reason quoted back, a matching direct edit gets a permission prompt (it asks, it doesn't refuse), and, once you enable cross-project publishing, other projects get an advisory nudge, never a block.

1 on GitHubby deepPairingv0.1.76MITupdated 3 days ago
/

Plugin deeppairing from marketplace deeppairing in mitchjablonski/deepPairing. Commands read from the repo's manifest — 3 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 (1)

  • pairing-protocol

    Use this whenever the user asks me to investigate code, compare options, plan a refactor, scope a spec, walk through a PR, decide between approaches, weigh tradeoffs, review a change, reason about a fix, or figure out why something is the way it is — even if they don't say "pair." Routes the work th

Slash commands (11)

  • /deeppairing:delegate

    Delegate a task — a brief only when there's a real decision, a quiet run, a short summary and one packet at the end

  • /deeppairing:doctor

    Diagnose this project's deepPairing setup with the bundled doctor

  • /deeppairing:post-pr

    Post what we landed on as a review on a GitHub PR — inline comments from the findings that survived

  • /deeppairing:reject

    Record a stance in this project from the terminal — "don't do X, because Y" — so the gate quotes your reason when X comes back

  • /deeppairing:review-pr

    Review a PR you were pinged on, in tandem — the diff on the rich surface, an orientation first, risks talked through together, posted only on your word

  • /deeppairing:review

    Review past deepPairing sessions — search for a concept, artifact, or pattern across every session in this project

  • /deeppairing:share

    Turn this session into a self-contained HTML page a colleague who wasn't here can read — you write the story, then export it

  • /deeppairing:skeleton-fill

    Fill an approved skeleton plan's fences. One step then stop by default, a step id to fill that step, or `all` to fill the rest in order

  • /deeppairing:skeleton

    Plan a feature as a code skeleton (stubs fenced with SKEL markers plus an architecture diagram), get the shape approved once, then fill each fence with edits gated to it

  • /deeppairing:stance

    Check this project's stances and the cross-project ledger on a concept before proposing anything related to it

  • /deeppairing:start

    Begin a deepPairing session — pull cross-project philosophy, active session state, and any rejected approaches before I propose anything

MCP servers (1)

  • deeppairing

    runs: node ${CLAUDE_PLUGIN_ROOT}/server.mjs

Hooks (3)

  • PreToolUse

    node "${CLAUDE_PLUGIN_ROOT}/server/preflight.mjs"

  • PreToolUse

    sh "${CLAUDE_PLUGIN_ROOT}/hooks/stance-allow-ask.sh"

  • Stop

    node "${CLAUDE_PLUGIN_ROOT}/server/stop.mjs"

View source on GitHub

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

superpowers

claudecodex

Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques

15 skills · hooks

obra/superpowers 316,836

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

MetaHarness integration — surfaces score/genome/mint/mcp-scan/threat-model via skills; pairs with @metaharness/router (ADR-148/149) for cost-optimal model routing; honors ADR-150 optional-augmentation constraint

13 skills · 1 command · 1 agent · hooks

ruvnet/ruflo 81,589

Use Alibaba Open Code Review from local Codex.

2 skills

alibaba/open-code-review 50,068

Maintain deeppairing?

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 pluginslisted