claude

borg-collective

The cognitive-load layer for parallel AI coding — skills and lifecycle hooks for sustainable AI-assisted development.

1 on GitHubby Noah Goodrichv0.9.14updated 12 days ago
/

Plugin borg-collective from marketplace noah-local in noah-goodrich/claude-plugins. Commands read from the repo's manifest — 11 days ago.

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

What it installs

Skills (13)

  • adhd-guardrails

    Cognitive load guardrails. Always active. Pushes back on perfectionism, flags scope expansion, suggests breaks after sustained work, uses shame-free language, and includes clear done criteria in every plan. Prevents burnout from AI-assisted development without limiting productivity.

  • borg-assimilate

    Shipping checklist + execution. Evaluates current state against PROJECT_PLAN.md acceptance criteria, then executes shipping (merge PR, archive plan) with confirmation. Use when you think you might be done, or when you're tempted to add \"one more thing.\"

  • borg-collective-review

    Adversarial review by The Collective — six always-present core personas plus domain code owners and one rotating specialist debate a plan or shipping decision. Called by borg-plan (before proposing objectives) and borg-assimilate (before shipping). Can also be invoked directly for ad-hoc design revi

  • borg-link-up

    \"Link up\" to the collective: flush session state to a checkpoint at <repository>/.borg/checkpoints/<timestamp>.md, which the next SessionStart restores. Use when ending a session, before a break, or when switching repositories.

  • borg-link

    The front door to the collective. In the Queen session it is the cross-repository overview; in a repository, worktree or named repository, a page on that one directory. Use for status, overview, briefing, \"what's going on\", repository details, \"what changed\", \"catch me up\", \"morning link-up\"

  • borg-next

    Show what repository needs attention most urgently and let the user pick one to open. Use when the user asks \"what should I work on?\", \"what's next?\", or wants to know priorities.

  • borg-plan

    Project planning that does the thinking so you can focus on validating and deciding. Reads the codebase, proposes objectives and acceptance criteria, and asks you to validate. Locks criteria once confirmed. Use at the start of a project or when objectives are unclear.

  • borg-resume

    Manual and fallback resume for work a session or usage limit paused or killed. Use when a Workflow fails with a \"session limit\" / \"usage limit\" / \"resets <time>\" error, or the user says \"resume after reset\", \"auto-resume the workflow\" or \"pick it back up when the limit clears\". Checks th

  • borg-review

    Mid-session diagnostic and start-of-change gates. Checks progress against the plan, detects scope creep and bad loops, and gives you ONE recommendation. Use when stuck, scattered, unsure you're building the right thing, starting a non-trivial change, or to \"apply the gates\" or \"fable mode\".

  • borg-switch

    Switch to a different repository's tmux window. Use when the user says \"switch to X\", \"go to X\", \"jump to X\", or wants to change repositories.

  • borg-verify

    Independent pre-merge evaluator gate. Spawns a fresh reviewer subagent to re-run tests, map acceptance criteria to diff evidence, and issue a structured PASS/FAIL verdict before gh pr merge. Call after a nanoprobe completes and before merging its PR.

  • break-glass

    Add a local permission exception to a repository's settings.local.json. Use when a repository needs to run a command that is too dangerous or repository-specific for the global allowlist. This is the formal escape hatch — global permission fixes are normal borg-collective work.

  • pane

    Split the current tmux pane in a given direction. Use when the user says \"split the pane\", \"open a pane to the right/left/top/bottom\", or wants a new terminal pane in the current window.

Subagents (6)

  • borg-grunt

    Cheap mechanical leaf-worker. Executes ONE fully-specified change (apply a spec'd edit, run tests/builds, read/grep logs, rote refactor) with NO judgment calls or scope expansion. The orchestrator holds the plan; the grunt executes it exactly.

  • borg-nanoprobe

    Single-task repository worker. The orchestrator delegates here instead of editing inline.

  • borg-researcher

    Web-enabled from-zero research worker. The orchestrator delegates one research track here instead of a general subagent.

  • borg-reviewer

    Independent blind adversarial reviewer. Reviews a proposal or option-set COLD — never sees the author's reasoning — to catch what self-review misses.

  • borg-scout

    Cheap read-only locate/search worker. Answers 'where is X / does Y exist / what are the naming conventions' questions by returning locations and short excerpts — never whole files. A cheap alternative to routing read-only search work to the inherited Opus main model.

  • borg-verifier

    Independent pre-merge evaluator that re-runs tests, maps acceptance criteria to diff evidence, and returns PASS/FAIL. Read-only; spawned by /borg-verify as a merge gate.

Hooks (30)

  • SessionStart

    ${CLAUDE_PLUGIN_ROOT}/hooks/borg-link-down.sh

  • SessionStart

    ${CLAUDE_PLUGIN_ROOT}/hooks/borg-arrival-brief.sh

  • SessionStart

    "${CLAUDE_PLUGIN_ROOT}/hooks/borg-resume-hook.sh" SessionStart

  • Stop

    ${CLAUDE_PLUGIN_ROOT}/hooks/borg-link-up.sh

  • Stop

    ${CLAUDE_PLUGIN_ROOT}/hooks/notify.sh

  • Notification

    ${CLAUDE_PLUGIN_ROOT}/hooks/notify.sh

  • Notification

    ${CLAUDE_PLUGIN_ROOT}/hooks/borg-notify.sh

  • Notification

    "${CLAUDE_PLUGIN_ROOT}/hooks/borg-resume-hook.sh" Notification

  • PreToolUse

    ${CLAUDE_PLUGIN_ROOT}/hooks/bash-guard.sh

  • PreToolUse

    ${CLAUDE_PLUGIN_ROOT}/hooks/pre-commit-remind.sh

  • PreToolUse

    ${CLAUDE_PLUGIN_ROOT}/hooks/borg-plan-promote.sh

  • PreToolUse

    ${CLAUDE_PLUGIN_ROOT}/hooks/borg-dispatch-guard.sh

  • PreToolUse

    ${CLAUDE_PLUGIN_ROOT}/hooks/borg-workflow-model-guard.sh

  • PreToolUse

    ${CLAUDE_PLUGIN_ROOT}/hooks/borg-agent-model-guard.sh

  • PreToolUse

    ${CLAUDE_PLUGIN_ROOT}/hooks/borg-supabase-guard.sh

  • PreToolUse

    ${CLAUDE_PLUGIN_ROOT}/hooks/borg-verifier-guard.sh

  • PreToolUse

    ${CLAUDE_PLUGIN_ROOT}/hooks/scout-readonly-guard.sh

  • PreToolUse

    ${CLAUDE_PLUGIN_ROOT}/hooks/borg-nanoprobe-guard.sh

  • PreToolUse

    "${CLAUDE_PLUGIN_ROOT}/hooks/borg-resume-hook.sh" PreToolUse

  • PreCompact

    ${CLAUDE_PLUGIN_ROOT}/hooks/borg-precompact-checkpoint.sh

  • PostToolUse

    ${CLAUDE_PLUGIN_ROOT}/hooks/tool-count-nudge.sh

  • PostToolUse

    ${CLAUDE_PLUGIN_ROOT}/hooks/borg-memory-read-log.sh

  • PostToolUse

    ${CLAUDE_PLUGIN_ROOT}/hooks/borg-prefer-tool-log.sh

  • PostToolUse

    ${CLAUDE_PLUGIN_ROOT}/hooks/large-output-nudge.sh

  • PostToolUse

    "${CLAUDE_PLUGIN_ROOT}/hooks/borg-resume-hook.sh" PostToolUse

  • SubagentStop

    ${CLAUDE_PLUGIN_ROOT}/hooks/borg-nanoprobe-log.sh

  • SubagentStop

    "${CLAUDE_PLUGIN_ROOT}/hooks/borg-resume-hook.sh" SubagentStop

  • SubagentStart

    "${CLAUDE_PLUGIN_ROOT}/hooks/borg-resume-hook.sh" SubagentStart

  • StopFailure

    "${CLAUDE_PLUGIN_ROOT}/hooks/borg-resume-hook.sh" StopFailure

  • SessionEnd

    "${CLAUDE_PLUGIN_ROOT}/hooks/borg-resume-hook.sh" SessionEnd

View source on GitHub

More from noah-goodrich/claude-plugins

All 8 plugins →

dev-tools

claude

Development environment tools: project scaffolding, devcontainer bootstrapping, repository review and documentation generation.

6 skills

1

Content creation skills for LinkedIn posts, Snowflake Builders Blog articles, design docs, and PR descriptions.

4 skills

1

Systematic research methodology — source evaluation, evidence classification, inclusion/exclusion decisions, and documentation standards.

1 skill · 2 agents · hooks

1

Noah Goodrich's writing voice enforcement, AI detection scoring, and a brevity layer for scanning documents.

3 skills

1

Code governance tools: capability indexing (scan a domain layer and emit a machine- and human-readable map of every pure exported function) and requirements reconciliation.

2 skills

1

Lightweight token cost estimation appended to every response.

1 skill · hooks

1

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

diagram-design

claudecodex

Editorial diagrams in your brand, as self-contained HTML and SVG. Architecture, flowcharts, sequence, state machines, ER and database schemas, timelines, swimlanes, org charts, Gantt, Wardley maps, user journeys, service blueprints, UML class, lifecycle phase maps, and charts from bar, line and scatter to Sankey, treemap and heatmap, plus many more. Redraws draw.io, Mermaid, Excalidraw and PlantUML files. Exports SVG and PNG.

1 skill · 7 commands

cathrynlavery/diagram-design 66,757

5 skills + 35 modes + Material Passport pipeline. Includes v3.6.7 cross-model audit gate and v3.6.8 generator-evaluator contract.

5 skills · 16 commands · 4 agents · hooks

Imbad0202/academic-research-skills 56,698

Perform AI code review on Git diffs — supports workspace changes, branch ranges, and single commits with concurrent per-file analysis, codebase search, and deep context-aware review.

2 commands

alibaba/open-code-review 50,068

Backend API design, GraphQL architecture, workflow orchestration with Temporal, and test-driven backend development

9 skills · 1 command · 8 agents

wshobson/agents 42,461

Maintain borg-collective?

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 plugins8 plugins