enfurbish

A group of Claude Code plugins for continuing work between sessions, approving project instruction files, and practising vocabulary during ordinary sessions. Claude Code is a coding assistant that can follow project-specific instruction files.

In plain words
What is it for?
Use it for session handoffs, reviewing changes to CLAUDE.md or .claude/rules files, and receiving vocabulary prompts during coding work.
Why use it?
It helps preserve handover context, prevents new instructions from being trusted without approval, and supports language learning while coding.

Plugin for Claude Code

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Claude Code
/plugin marketplace add nullphase-net/enfurbish
agentmods
npx agentmods add plugins/nullphase-net/enfurbish/marketplace
Clone the repo
git clone --depth 1 https://github.com/nullphase-net/enfurbish

Made for: Claude Code.

Per session not measured What this adds to a session before it is invoked.
When invoked not measured Not applicable: nothing here is loaded into a session.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

enfurbish scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude-plugin/marketplace.json · 32 lines

What it actually says

{
  "name": "enfurbish",
  "description": "Claude Code plugins by phreakocious: session continuity, project-instruction approval gating, and ambient language learning.",
  "owner": {
    "name": "phreakocious",
    "email": "[email protected]"
  },
  "plugins": [
    {
      "name": "continuity",
      "source": "./continuity",
      "description": "Intentional session continuity: /wrap retro, /next command, and a SessionStart hook that surfaces NEXT_SESSION.md handoffs.",
      "category": "workflow",
      "keywords": ["session", "continuity", "retro", "handoff", "skills"]
    },
    {
      "name": "affirm",
      "source": "./affirm",
      "description": "Approval gate for project instructions. Surfaces new or modified CLAUDE.md and .claude/rules/* files at session start before Claude treats them as trusted.",
      "category": "security",
      "keywords": ["security", "prompt-injection", "claudemd", "approval", "guard"]
    },
    {
      "name": "pastiche",
      "source": "./pastiche",
      "description": "Ambient language learning. A SessionStart hook weaves vocabulary into ordinary sessions — stale items you are forgetting, a small budget of new terms drawn from the work itself, and anything you use unprompted recorded rather than taught back at you. The ledger is a markdown file you own, written by a CLI rather than by hand.",
      "category": "workflow",
      "keywords": ["language", "learning", "vocabulary", "immersion", "ledger"]
    }
  ]
}
Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. yesterday First seen · 32 lines scan A b50f061b7252

Subscribe to this mod's changes

enfurbish is a plugin published in the GitHub repository nullphase-net/enfurbish (1 stars, last pushed 14d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.