sanitizer

sanitizer is an agent for Claude Code from prime-radiant-inc/greenfield. It costs 28 tokens per session (174 once invoked), scanned A, original, Apache-2.0.

A worker that turns rough, implementation-focused specifications into clean descriptions of how a system should behave.

In plain words
What is it for?
Use it to rewrite raw specification files, reorganize requirements by behavior, and record evidence for each requirement.
Why use it?
It removes code-specific details that can distract from the intended behavior while keeping information about where the requirements came from.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the greenfield plugin — 22 skills, 2 commands, 2 agents shipped together

Good fit Use it to rewrite raw specification files, reorganize requirements by behavior, and record evidence for each requirement.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/prime-radiant-inc/greenfield/sanitizer
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/prime-radiant-inc/greenfield

Made for: Claude Code.

Or install greenfield, the plugin that ships this one along with the rest of its 22 skills, 2 commands, 2 agents.

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 sanitizer

README.md
[![agentmods](https://agentmods.dev/badge/agents/prime-radiant-inc/greenfield/sanitizer/github.svg)](https://agentmods.dev/agents/prime-radiant-inc/greenfield/sanitizer)
Your own site
<a href="https://agentmods.dev/agents/prime-radiant-inc/greenfield/sanitizer"><img src="https://agentmods.dev/badge/agents/prime-radiant-inc/greenfield/sanitizer/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.

agentmods 80×15 button for sanitizer

Your own site · 80×15
<a href="https://agentmods.dev/agents/prime-radiant-inc/greenfield/sanitizer"><img src="https://agentmods.dev/badge/agents/prime-radiant-inc/greenfield/sanitizer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 28 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 174 The whole file, excluding the scripts and references it only reads on demand.
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.
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 5.1 $0.00028 $0.00174
Opus 5 $0.00014 $0.00087
Sonnet 5 $0.00006 $0.00035
Haiku 4.5 $0.00003 $0.00017

Measured 10d ago against content hash ed136eb7a79a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

sanitizer 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 10d 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.

agents/sanitizer.md · 17 lines

What it actually says

Sanitizer Worker

You are a sanitizer worker. You read specs from workspace/raw/ and rewrite them to workspace/output/ with all implementation contamination removed.

Your dispatch prompt tells you what files to sanitize and where to write them. Follow the spec-sanitization skill for the full transformation methodology, provenance citation rules, structural reorganization (modules → behavioral domains), and contamination detection patterns.

YOU MUST USE THE WRITE TOOL

Write the sanitized specs. They MUST exist when you're done.

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. 10d ago First seen · 17 lines · 28 tokens per session scan A ed136eb7a79a

Subscribe to this mod's changes

sanitizer is an agent published in the GitHub repository prime-radiant-inc/greenfield (275 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 28 tokens to every session and 174 once invoked, about $0.0001 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 2026-08-30.

Related

Other agents, from other repositories

bundle-analyzer

Parse downloaded JavaScript bundles for animation-library construction sites and concrete parameters. Invoked at Phase 5d when bundle-map.json detects Lenis, GSAP, Framer, Anime, Webflow IX2, Lottie, or related motion libraries but transition-spec.json is empty or under-populated. Writes bundle-extraction.json for…

voidmatcha/ui-clone-skills · 75 tokens

source-forensics

Inspect large raw reference HTML/CSS/JS sources in an isolated context when compact artifacts cannot explain persistent section, sticky, transition, or forensic-preservation failures. Writes source-forensics.json for the main clone loop.

voidmatcha/ui-clone-skills · 47 tokens

test-plan-reviewer

Reviews a Speky test plan — either a draft (TOML/YAML paste) or one already in the spec (by test ID) — for adherence to step-style rules, fit with the requirement it claims to cover, and overlap with other tests. Returns structured feedback. Read-only; the calling agent applies any change. Use when the user wants a…

agagniere/speky · 95 tokens

code-test-reviewer

Reviews an automated test (unit, integration, or e2e) against its Speky test plan, checking that every plan step has a corresponding assertion in code and flagging any gap between spec and implementation. Returns structured feedback. Read-only; the calling agent applies any change. Use when you want to verify that…

agagniere/speky · 80 tokens

requirement-reviewer

Reviews a Speky requirement — either a draft (TOML/YAML paste) or one already in the spec (by ID) — for atomicity, testability, clarity, and fit. Returns structured feedback. Read-only; the calling agent applies any change. Use when the user wants a second opinion on a requirement before saving it, or wants to audit…

agagniere/speky · 82 tokens

test-plan-author

Drafts a complete Speky test plan for a given requirement ID. Returns ready-to-paste TOML following Speky's test-plan style. Read-only — the calling agent applies the edit. Use when the user asks to write, draft, or expand tests for a specific requirement.

agagniere/speky · 61 tokens