Improves agent navigation through a repository, turns session detours into approved map-file changes, and reconciles documentation and non-code development files with current behavior. Includes audit-only review, an approved layout migration, README review, host consistency and repository hygiene.
Plugin anneal from marketplace slag in V-Songbird/slag. Commands read from the repo's manifest — today.
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.
overviewShows what anneal finds in this repository and which of its skills to run next, from one read-only script with no model. Use when the user asks what anneal does or can do here, where to start with it, which anneal skill fits a job, or for a quick health summary of navigation, documentation and past
repo-docsWrites and reviews pages people read (help pages, guides, how-tos, FAQs, troubleshooting, changelogs, contributing guides), so a non-expert can find the answer and finish the task; use it whenever you write or substantially edit one, even when nobody names writing rules. Also reconciles docs, agent
repo-layoutAudits an existing repository for what makes an AI agent search, read or guess more than it needs to — no map file or toolchain version, duplicate or generic names, oversized or buried files, build output in search results, names built at runtime — then, with the owner's approval at each step, migra
session-reviewAudit one session for lost time and propose map-file fixes, find what many sessions repeat that a script or a map line could replace, or check whether a finished session is safe to delete. Run only when invoked.
mapperRead-only layout surveyor for the repo-layout skill. Given a repository root and anneal's audit JSON, proposes which files belong together, which generic or duplicate names to change, and what to leave alone. Use only when that skill's plan step asks for a layout proposal. Do NOT use to move, rename
node
node
node
Holds a session inside the task it was given: one open task with the files it may touch and the command that ends it, a guard that refuses writes outside that list, and checks that each ship with a violation and a near miss so none of them counts as coverage before it has been shown to work. It mounts beside a planning tool's roadmap, enforces the session boundary and never enforces the roadmap.
2 skills · hooks
AI-powered codebase understanding — analyze, visualize, and explain any project
9 skills · 10 agents · hooks
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
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
Code intelligence powered by a knowledge graph. Provides execution flow tracing, blast radius analysis, and augmented search across your codebase.
12 skills · 1 MCP server · hooks
Cedar policy enforcement + Ed25519 signed receipts for every Claude Code tool call. First cryptographic governance plugin — decisions are policy-gated before they run and every decision produces a tamper-evident receipt verifiable offline.
1 skill · 2 commands · 2 agents · hooks
Conventions and task skills for contributing to diffusers
4 skills
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.