An approval checkpoint for project instruction files such as CLAUDE.md and .claude/rules/. It shows new or changed instructions, including files they import, before Claude treats them as trusted.

Use it to review, approve, or revoke trust for project rules and detect changes to them between sessions.

Project instruction files can be changed accidentally or maliciously and influence Claude's behavior. Explicit approval helps catch those changes first.

affirm — Plugin for Claude Code by nullphase-net/enfurbish

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.

Clone the repo

git clone --depth 1 https://github.com/nullphase-net/enfurbish

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/plugins/nullphase-net/enfurbish/affirm/github.svg)](https://agentmods.dev/plugins/nullphase-net/enfurbish/affirm)

Your own site

<a href="https://agentmods.dev/plugins/nullphase-net/enfurbish/affirm"><img src="https://agentmods.dev/badge/plugins/nullphase-net/enfurbish/affirm/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/plugins/nullphase-net/enfurbish/affirm"><img src="https://agentmods.dev/badge/plugins/nullphase-net/enfurbish/affirm.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session not measured What this adds to a session before it is invoked.

When invoked not measured The manifest loads nothing itself; its 1 skill, 1 hook cost 68 tokens a session between them.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Security

Grade A, and why

affirm 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 14d ago.

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.

affirm/.claude-plugin/plugin.json · 15 lines

What it actually says

{
  "name": "affirm",
  "description": "Approval gate for instruction files. Surfaces new or modified CLAUDE.md, CLAUDE.local.md, .claude/rules/* and AGENTS.md files (project, parent directories and user-global) and the files they @import at session start; the user explicitly affirms them before Claude treats them as trusted.",
  "version": "0.9.0",
  "license": "MIT",
  "author": { "name": "phreakocious" },
  "keywords": [
    "security",
    "prompt-injection",
    "claudemd",
    "approval",
    "guard"
  ]
}

Contents

What it installs

The manifest is a name and a version. 1 skill, 1 hook travel with it, and installing the plugin installs all of them — 68 tokens a session between them. Each is measured on its own page, and each can be installed alone.

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.

14d ago Changed db74d6259ecf
16d ago Changed · +1 lines 79bf3dbc5ab5
20d ago Changed afd82f777e2f
22d ago Changed 709229427998
25d ago Changed 8d8b97bb0478
28d ago Changed 0c1f19d0d1d8
1mo ago Changed · +6 lines 59d8df0d60cd
1mo ago Changed f3776d8ccd94
1mo ago First seen · 8 lines scan A ce66baa9489e

Subscribe to this mod's changes

affirm is a plugin published in the GitHub repository nullphase-net/enfurbish (1 stars, last pushed 4d 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.

Building agents Claude Code ai-context ai-continuity claude-code-plugin claude-skills prompt-injection-defense

neatcontext marketplace

Save Claude Code work as reusable, domain-aware context.

XTSoftwareLabs/neatcontext-plugins · not measured

neatcontext

Save Claude Code work as reusable, domain-aware context.

XTSoftwareLabs/neatcontext-plugins · not measured

repo-indexer

Indexes and documents codebases for persistent Claude context with minimal token overhead. Creates tiered memory (native memory + CLAUDE.md + on-demand files + conversation history) so Claude remembers your projects across sessions.

jyshnkr/repo-indexer · not measured

han-communication

Foundational communication plugin for the Han suite. Owns the canonical readability standard, the writing-voice profile, and the explanation standard for talking to a reader who will not implement the work, plus the readability-guidance skill that surfaces the first two into a calling skill's own context for in-voice…

testdouble/han · not measured

han-research

Pre-planning knowledge-work skills for the Han suite: understanding a problem before anyone commits to a plan. Home of research (research an open-ended question and end at an adversarially-validated recommendation), gap-analysis (compare two artifacts and report what is missing, incomplete, or conflicting), and…