affirm

affirm is a skill for Claude Code, Codex from nullphase-net/enfurbish. It costs 50 tokens per session (658 once invoked), scanned A, original, MIT.

A command for showing, approving, or revoking trust in project instruction files such as CLAUDE.md and .claude/rules/. It can record hashes, which are fingerprints used to detect later changes.

In plain words
What is it for?
Use it to inspect project rules, record approval after review, or remove that approval when the files should no longer be trusted.
Why use it?
It helps ensure Claude follows only instructions that someone has reviewed, and warns when trusted files are modified.

Skill for Claude CodeCodex

Part of the affirm plugin — 1 skill, 1 hook shipped together

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.

agentmods
npx agentmods add skills/nullphase-net/enfurbish/affirm
Any agent
npx skills add nullphase-net/enfurbish --skill affirm
Clone the repo
git clone --depth 1 https://github.com/nullphase-net/enfurbish

Made for: Claude Code, Codex.

Or install affirm, the plugin that ships this one along with the rest of its 1 skill, 1 hook.

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.

agentmods badge for affirm

README.md
[![agentmods](https://agentmods.dev/badge/skills/nullphase-net/enfurbish/affirm.svg)](https://agentmods.dev/skills/nullphase-net/enfurbish/affirm)
Your own site
<a href="https://agentmods.dev/skills/nullphase-net/enfurbish/affirm"><img src="https://agentmods.dev/badge/skills/nullphase-net/enfurbish/affirm.svg" alt="Measured on agentmods" height="20"></a>
Per session 50 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 658 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00050 $0.00658
Opus 5 $0.00025 $0.00329
Sonnet 5 $0.00010 $0.00132
Haiku 4.5 $0.00005 $0.00066

Measured 4d ago against content hash a3cf1a58a149, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

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 4d 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/skills/affirm/SKILL.md · 61 lines

How it starts

The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/affirm — affirm project instruction files

CLAUDE.md, anything under .claude/rules/, and any files they pull in via Claude Code's @import syntax are loaded as Claude's system instructions for this project. A malicious or accidental change can silently re-program Claude. /affirm is the explicit trust gate: bare /affirm shows you what's there; /affirm -a records SHA-256 hashes once you've reviewed; /affirm -r revokes. The SessionStart hook compares stored hashes on every session start and warns on any mismatch.

Procedure

Forward args to the CLI verbatim and relay output to the user. No confirmation prompts — the user types -a when they're ready to attest.

The CLI lives at <skill-base-dir>/../../lib/cli.ts.

Bare /affirm — show details

bun run "<skill-base-dir>/../../lib/cli.ts"

Relay the output. This is read-only — nothing is recorded.

/affirm -a (or --apply) — record hashes

bun run "<skill-base-dir>/../../lib/cli.ts" -a

Relay the output. The user invoking -a is the attestation; do not add a separate confirmation step.

/affirm -r (or --revoke) — drop affirmation

bun run "<skill-base-dir>/../../lib/cli.ts" -r

Relay the output.

/affirm --help

bun run "<skill-base-dir>/../../lib/cli.ts" --help

Relay the output.

What this skill does NOT do

  • Read the contents of CLAUDE.md or rules files. That's the user's job — they're the one attesting.
  • Modify any instruction file. Affirmation is hash-only.
  • Affirm files the project doesn't reference. Scope is <cwd>/CLAUDE.md + <cwd>/.claude/rules/* plus whatever they @import (followed two levels deep; an import pointing outside the project is hashed but flagged out-of-tree). User-global ~/.claude/CLAUDE.md is out of scope unless a tracked file imports it.
  • Prompt the user "are you sure?". The flag is the attestation.

Edge cases

  • No instruction files in cwd: the CLI prints a single line and exits. Relay that and stop.
  • Unknown flag: the CLI exits 2 with usage. Relay it.
  • -a and -r together: the CLI exits 2 with a "mutually exclusive" error. Relay it.
  • Hash file at ~/.claude/affirm-hashes.json is missing or unparseable: the CLI treats it as empty and writes a fresh one on next -a. No action needed.

Read the full file on GitHub · 61 lines

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. 4d ago First seen · 61 lines · 50 tokens per session scan A a3cf1a58a149

Subscribe to this mod's changes

affirm is a skill published in the GitHub repository nullphase-net/enfurbish (1 stars, last pushed 17d ago), licensed MIT. It adds 50 tokens to every session and 658 once invoked, about $0.0003 per session on Opus 5. 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.

Related

Other skills, from other repositories

import

Import a self-contained NeatContext context bundle shared by another person, or reconcile a newer copy of a context already on this machine, leaving the source bundle unchanged. Use only when the user explicitly invokes this skill or asks to import a NeatContext bundle.

XTSoftwareLabs/neatcontext-plugins · 54 tokens

save

Save durable decisions, findings, plans, and implementation knowledge from the visible Codex conversation into a new or existing NeatContext context. Use only when the user explicitly invokes this skill or asks to preserve the current conversation as reusable context.

XTSoftwareLabs/neatcontext-plugins · 49 tokens

create

Create a fresh NeatContext context from a user-defined behavioral profile and an existing local knowledge folder. Use only when the user explicitly invokes this skill or asks to create a new context rather than save the current conversation.

XTSoftwareLabs/neatcontext-plugins · 45 tokens

extensions

Report which extensions the connected NeatContext context expects, and whether this machine provides them. Use when the user asks what a context can reach, why an extension tool is missing, or how to connect one here.

XTSoftwareLabs/neatcontext-plugins · 45 tokens

export

Export a NeatContext context saved from a conversation into a self-contained bundle folder that can be shared or moved to another machine. Use only when the user explicitly invokes this skill or asks to export a NeatContext context.

XTSoftwareLabs/neatcontext-plugins · 47 tokens

use

Connect or switch Codex to a local NeatContext Context by name or list number. Use only when the user explicitly invokes this skill, names a context to connect, or agrees to a routing suggestion.

XTSoftwareLabs/neatcontext-plugins · 43 tokens