claude

git-narrator

Re-narrates a feature branch before merge: rebuilds messy exploratory history into a semantic commit sequence, with a byte-identical final tree and per-commit build gates. Forward mode (narrate-wip) turns the dirty working tree into semantic commits as you go, without rewriting history.

0 on GitHubby jr-jesse123MITupdated 3 days agogit
/

Plugin git-narrator from marketplace jr-claude-toolkit in jr-jesse123/claude-tookit. Commands read from the repo's manifest — 3 days ago.

What it installs

Skills (3)

  • narrate-wip

    Forward-mode narration - turn the current dirty working tree into 1-3 semantic commits at a natural pause point, instead of "git add -A && commit -m wip". No history rewrite, no force-push, safe on branches with an open PR. Slices by purpose then layer, optionally build-gates each commit in a dispos

  • narrate

    Re-narrate the current feature branch before merge - replace messy exploratory commits with a semantic sequence (intent docs, domain + tests, support + tests, wiring + E2E) while keeping the final tree byte-identical. Plans interactively, then delegates execution to the git-narrator executor agent.

  • pr-shape-review

    Review a feature branch before publication and recommend the smallest coherent linear-history shape: squash, recomposed commits, split PRs, or stacked PRs. Use when deciding how a branch should enter main, especially after agentic or exploratory development.

Subagents (1)

  • executor

    Executes an approved git-narrator plan - rebuilds branch history into the planned commit sequence, gates every commit on build and tests, and verifies the final tree is byte-identical to the original. Invoked by the narrate skill after user approval; not for direct use.

View source on GitHub

More from jr-jesse123/claude-tookit

All 18 plugins →

code-review

claude

Fast, focused review of uncommitted changes, guided reading tours of PRs and of implementation plans, plus a security-focused subagent.

4 skills · 2 agents

0

execution-router

claude

Advises on computation form with cheap grounding, exact and typed design, bounded residual composition, and experimental mixed planning; preserves pending work and model-router independence.

5 skills

0

model-router

claude

Recommends the cheapest model, effort level, and execution shape that will complete a task reliably — routing atomic tasks with choose-model and decomposing multi-model work into routed execution plans with plan-execution — from versioned per-provider routing policies (Anthropic and OpenAI) and a project-local calibration log.

4 skills

0

arch-docs

claude

Right-sized architecture documentation: scaffolds a lean docs/architecture layout sized to the repo's real risk, drafts ADRs by interviewing the human for the why it cannot infer, and a read-only drift reviewer that flags diffs touching documented boundaries, contracts, or decisions.

2 skills · 1 agent

0

codex-agents

claude

Role-shaped delegation to Codex models (gpt-5.6 luna/terra/sol) from inside Claude Code: a general delegate skill plus QA and UX subagents that package this session's context into a self-contained prompt, run the analysis on a cheaper model via `codex exec`, and return findings as verified claims.

1 skill · 2 agents

0

devops-tools

claude

Pre-deploy checklist, changelog generation, and a guard hook against destructive shell commands.

1 skill · 1 command · hooks

0

Similar plugins

commit-commands

claude

Commands for git commit workflows including commit, push, and PR creation

3 commands

anthropics/claude-code 155,476

agentic-flow

claude

agentic-flow (external: maintained in ruvnet/agentic-flow, pinned to commit d19737b, plugin 3.4.0): the agentic-flow MCP server pinned to [email protected] (ReasoningBank learning, ecosystem tools prompt_injection_scan, swarm_partition_tasks, sublinear_solve, sublinear_pagerank and ecosystem_status, multi-provider routing, autopilot learning; readonly profile by default, no tool pre-approved), 2 agents, 4 skills, /agentic-flow-status, and a mod guard on agentic_flow_agent with /agentic-flow-guard

4 skills · 1 command · 2 agents · 1 MCP server

ruvnet/ruflo 81,589

headroom-skill

claude

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

open-code-review

claude

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

chronograph-lp

claude

Portfolio monitoring and analytics for private-capital LP teams using the Chronograph connector: cashflow forecasting, commitment pacing, look-through exposure scans and GP-meeting prep. Requires a Chronograph account and the Chronograph connector.

4 skills · 5 agents

anthropics/claude-plugins-official 47,076

developer-essentials

claudecodex

Essential developer skills including Git workflows, SQL optimization, error handling, code review, E2E testing, authentication, debugging, and monorepo management

11 skills · 1 agent

wshobson/agents 42,461

Maintain git-narrator?

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 plugins18 plugins