claude

discipline

Generic dev hygiene: TODO+issue enforcement, frontmatter lint, plan validation (issue+value+retrospective), spec-code drift checker, finish-and-push workflow, and pitfalls-pointer routing, plus a fact-forcing edit gate, git-state checkpoint/snapshot tooling, and council + session-handoff skills, and a compact-plan skill for plan-preserving context compaction.

0 on GitHubby Garrett Manleyv1.2.1MITupdated 2 days agoquality
/

Plugin discipline from marketplace garrettmanley in GarrettManley/claude-marketplace. Commands read from the repo's manifest — 2 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 (4)

  • compact-plan

    Use when conversation context is nearly full mid-task and the work is governed by a plan, SDD ledger, or delivery run — saves a short intent note to disk and emits a ready-to-paste /compact command with targeted preservation instructions, so the post-compaction session resumes with plan position int

  • council

    Convene a four-voice council for ambiguous decisions, tradeoffs, and go/no-go calls. Use when multiple valid paths exist and you need structured disagreement before choosing. Not for code review, implementation planning, or architecture design.

  • finish-and-push

    Close out a feature branch using the standard rebase-onto-main + FF-merge + push routine. User-invocable only (disable-model-invocation true) because pushing is hard-to-reverse. Use after a logical task cluster lands on a feature branch and tests are green.

  • session-handoff

    Write a thorough end-of-session handoff document using a structured 8-section schema (What We're Building / What WORKED / What Did NOT Work / What Has NOT Been Tried Yet / Current State of Files / Decisions Made / Blockers & Open Questions / Exact Next Step). Use when closing a work cluster, before

Slash commands (1)

  • /discipline:checkpoint

    Create, verify, or list git-state checkpoints with delta reporting (files changed, lines +/-, live test pass-count). Use to mark stable points mid-work so you can compare current state to a known-good baseline.

Subagents (1)

  • spec-code-drift-checker

    Audit a long-lived spec doc for drift between cited symbols and the current codebase. Use when reviewing a spec that has accumulated retrospective claims like "Decision E.3 says…", "the FooBar field on BazResponse" — those concrete code references rot as the codebase evolves. This agent grep-validat

Hooks (12)

  • SessionStart

    uv run --no-project "${CLAUDE_PLUGIN_ROOT}/scripts/run_with_flags.py" "${CLAUDE_PLUGIN_ROOT}/hooks/inject_issues.sh" discipline:session-start:inject-issues minimal,standard,strict

  • SessionStart

    uv run --no-project "${CLAUDE_PLUGIN_ROOT}/scripts/run_with_flags.py" "${CLAUDE_PLUGIN_ROOT}/hooks/inject_branch_state.sh" discipline:session-start:inject-branch-state minimal,standard,strict

  • SessionStart

    uv run --no-project "${CLAUDE_PLUGIN_ROOT}/scripts/run_with_flags.py" "${CLAUDE_PLUGIN_ROOT}/scripts/session_resume_context.py" discipline:session-start:resume-context standard,strict

  • PreCompact

    uv run --no-project "${CLAUDE_PLUGIN_ROOT}/scripts/run_with_flags.py" "${CLAUDE_PLUGIN_ROOT}/scripts/pre_compact_snapshot.py" discipline:pre-compact:snapshot standard,strict

  • PreToolUse

    uv run --no-project "${CLAUDE_PLUGIN_ROOT}/scripts/run_with_flags.py" "${CLAUDE_PLUGIN_ROOT}/hooks/todo_issue_hook.py" discipline:pre-edit:todo-issue standard,strict

  • PreToolUse

    uv run --no-project "${CLAUDE_PLUGIN_ROOT}/scripts/run_with_flags.py" "${CLAUDE_PLUGIN_ROOT}/scripts/gateguard.py" discipline:pre-edit:gateguard-fact-force strict

  • PreToolUse

    uv run --no-project "${CLAUDE_PLUGIN_ROOT}/scripts/run_with_flags.py" "${CLAUDE_PLUGIN_ROOT}/scripts/gateguard.py" discipline:pre-bash:gateguard-fact-force standard,strict

  • PostToolUse

    uv run --no-project "${CLAUDE_PLUGIN_ROOT}/scripts/run_with_flags.py" "${CLAUDE_PLUGIN_ROOT}/hooks/plan_issue_check.py" discipline:post-edit:plan-issue-check standard,strict

  • PostToolUse

    uv run --no-project "${CLAUDE_PLUGIN_ROOT}/scripts/run_with_flags.py" "${CLAUDE_PLUGIN_ROOT}/hooks/memory_tracker_check.py" discipline:post-edit:memory-tracker-check standard,strict

  • PostToolUse

    uv run --no-project "${CLAUDE_PLUGIN_ROOT}/scripts/run_with_flags.py" "${CLAUDE_PLUGIN_ROOT}/hooks/frontmatter_lint.py" discipline:post-edit:frontmatter-lint standard,strict

  • PostToolUse

    uv run --no-project "${CLAUDE_PLUGIN_ROOT}/scripts/run_with_flags.py" "${CLAUDE_PLUGIN_ROOT}/hooks/pitfalls_pointer.py" discipline:post-edit:pitfalls-pointer standard,strict

  • PostToolUse

    uv run --no-project "${CLAUDE_PLUGIN_ROOT}/scripts/run_with_flags.py" "${CLAUDE_PLUGIN_ROOT}/hooks/spec_companion_check.py" discipline:post-write:spec-companion-check strict

View source on GitHub

More from GarrettManley/claude-marketplace

All 13 plugins →

review

claude

Multi-lens review: the reviewer-personas skill maps an artifact (design docs, PRs, work items, wiki pages, or skill files) to a set of 17 archetype agents and dispatches them as sub-agents (security-auditor, observability-champion, data-architect, incident-commander, ecosystem-context-reviewer, new-engineer, skill-craft-reviewer, architect, contract-surface, performance-scalability, test-strategy, migration-safety, compliance, api-contract, error-handling, accessibility, architecture-conformance); each agent definition is the persona. SessionStart hook nags about review-triggering artifacts that completed without a review token. Includes persona-stub template for adopters to add their own archetype agents.

1 skill · 1 command · 17 agents · hooks

0

learning

claude

Continuous-learning toolkit: atomic instinct storage plus project-scoped observation hooks (default-off) and an /analyze-observations review report. Adapted from affaan-m/everything-claude-code @ 4774946d.

10 commands · hooks

0

docs

claude

Documentation craft: tech-writing (universal prose rules from Google Tech Writing), mermaid-diagram (Mermaid authoring with a configurable brand palette and renderer-agnostic fencing), design-document (structured design-doc creation with a pluggable template).

7 skills · 3 agents

0

aether

claude

Aether Engine TTRPG/narrative framework support: domain-specific hooks (cd_core_guard, ledger truncation, classifier/harness/Rust-rebuild reminders), 6 skills (doc-cluster, edit-checklist, plan-writer, ledger-doctor, eval-run, value-justify), classifier-regression-checker agent. Hooks no-op outside Aether-shaped repos; safe to enable globally.

6 skills · 1 agent · hooks

0

Plan retrospective discipline: a self-contained cycle of marker-drop (exit plan mode), session-start nag, and a retro-authoring skill. Forces a pause after every approved plan to capture what worked, what surprised you, and concrete improvements.

3 skills · 1 command · hooks

0

Autonomous maintenance toolkit: drift-check runner against context-file verification commands, morning-briefing template, Windows Task Scheduler registration helper, auto-memory housekeeping for ~/.claude/projects/*/memory/.

2 skills · 1 command · 1 agent · hooks

0

Similar plugins

CMEM Pro

claude

CMEM Pro for the Claude app - hooks stream tool use to cmem.ai and inject observations into new sessions and agents

3 skills · 1 MCP server · hooks

thedotmack/claude-mem 116,618

mempalace

claudecodex

AI memory system — mine projects and conversations into a searchable palace. 47 MCP tools, auto-save hooks, guided setup.

3 skills · 6 commands · 1 MCP server · hooks

MemPalace/mempalace 60,536

pensyve

claude

Universal memory runtime for Claude Code with cross-session memory, entity-aware recall, lifecycle hooks, skills, commands, and memory-curator agents

7 skills · 7 commands · 2 agents · hooks

wshobson/agents 42,461

Real-time statusline showing context usage, active tools, running agents, and todo progress. Always visible below your input, zero config required.

1 skill

jarrodwatts/claude-hud 29,182

Create, inspect, validate, and assess furniture layouts with bounded next actions in Pascal through MCP.

3 skills · 2 MCP servers

pascalorg/editor 25,479

worktrunk

claudecodex

Worktrunk is a CLI for Git worktree management, designed for parallel AI agent workflows. This plugin provides configuration guidance (LLM commit messages, project hooks, worktree paths), automatic activity tracking (🤖/💬 indicators in `wt list` showing active Claude sessions), and a `/wt-diff` pane showing each worktree's changes.

2 skills · hooks

max-sixty/worktrunk 12,481

Maintain discipline?

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 plugins13 plugins