spec-sanitization

spec-sanitization is a skill for Claude Code from prime-radiant-inc/greenfield. It costs 31 tokens per session (5,782 once invoked), scanned A, original, Apache-2.0.

A cleanup step that rewrites analysis specifications so they describe behavior without exposing source-code details. It keeps information about where each finding came from.

In plain words
What is it for?
It helps prepare analysis documents for implementation while preserving their source references and provenance.
Why use it?
Raw analysis can accidentally include function names, file paths, line numbers, and other implementation details that an implementer does not need.

Skill 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 It helps prepare analysis documents for implementation while preserving their source references and provenance.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/prime-radiant-inc/greenfield/spec-sanitization
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.

Any agent
npx skills add prime-radiant-inc/greenfield --skill spec-sanitization
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 spec-sanitization

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/prime-radiant-inc/greenfield/spec-sanitization"><img src="https://agentmods.dev/badge/skills/prime-radiant-inc/greenfield/spec-sanitization.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 31 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,782 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00031 $0.05782
Opus 5 $0.00015 $0.02891
Sonnet 5 $0.00006 $0.01156
Haiku 4.5 $0.00003 $0.00578

Measured 10d ago against content hash 6aacb5056beb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

spec-sanitization 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.

skills/spec-sanitization/SKILL.md · 477 lines

How it starts

The opening of the file, as written. The whole thing — 477 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Spec Sanitization

The sanitization pass turns raw analysis into specs an implementer can build from.

Why This Exists

Analysts read source code, binaries, and runtime behavior. Even with good intentions, they leak implementation details:

  • Function names from source (minified or not)
  • Variable and class names from source
  • Code structure ("function X calls Y which calls Z")
  • Line numbers and file locations
  • Raw file paths (workspace/raw/source/analysis/chunk-42.md:67)

These have no place in the output specs. Your job: READ each spec, UNDERSTAND the behavior, REWRITE without source references, TRANSFORM provenance citations.

The Rewrite Rule

You must not copy text from raw specs into output specs. Not sentences, not paragraphs, not sections. Read the raw specs to understand the behavior, then write a fresh output spec from your understanding.

Why? Raw specs have source code identifiers woven into every sentence — minified names (k0, Wq, z1), internal function signatures (Pn(a, b, c)), and numeric implementation constants. Find-and-replace cannot catch them all; many internal identifiers read like plain English (shouldRetryOnTimeout, evict_stale_connections). A paraphrase that preserves the original's structure is still leaking the original's design. The only reliable approach is to never copy the text at all.

Process per file:

  1. Read the raw spec end-to-end
  2. Close it (do not refer back to it while writing)
  3. Write the output spec from your understanding of the behavior
  4. Use only: behavioral descriptions, user-facing identifiers (env vars, CLI flags, config keys, protocol fields), and numeric constants (timeouts, limits, sizes)
  5. For any concept you could not translate into behavioral language — because you don't understand what it does — add: [UNCERTAINTY: U-{DOMAIN}-{NNN}] {what the raw spec said, in behavioral terms as best you can} — behavioral purpose could not be determined from available analysis.

Never preserve implementation jargon in slightly-reworded form. "validator.Exists() is called" rewritten as "the exists check runs" is still jargon — neither you nor the implementer knows what it means. Either translate it to behavior ("verifies the value exists in the constrained list") or flag it as uncertain.

Read the full file on GitHub · 477 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. 10d ago First seen · 477 lines · 31 tokens per session scan A 6aacb5056beb

Subscribe to this mod's changes

spec-sanitization is a skill published in the GitHub repository prime-radiant-inc/greenfield (275 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 31 tokens to every session and 5,782 once invoked, about $0.0002 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 skills, from other repositories

benchmark

Local-only regression / benchmark skill for ui-clone-skills maintainers. Drives the standard ui-reverse-engineering pipeline against the canonical reference site (https://realfood.gov) and records AE/SSIM, iteration count, gate fail counts, and outcome to benchmark/history.csv so prompt / sub-doc / model-version drift…

voidmatcha/ui-clone-skills · 152 tokens

ui-capture

Capture baseline evidence from a live website URL: screenshots, scroll states, hover/click behavior, parallax, timers, and transition recordings. Use when reference artifacts are needed before implementation or comparison; not to build or diagnose a clone.

voidmatcha/ui-clone-skills · 51 tokens

write-test-plans

Interactive workflow for writing new Speky test plans for requirements lacking coverage, guided by the Speky MCP server.

agagniere/speky · 26 tokens

speky-workflow

Guidelines for working with Speky requirements and tests via the speky MCP server tools.

agagniere/speky · 22 tokens

SPI Flash Dump via OpenOCD

This skill should be used when the user asks to "dump SPI flash", "read EEPROM through OpenOCD", "dump flash via MCU", "read SPI through debug interface", "extract firmware from SPI", or mentions scenarios involving SPI flash connected to a microcontroller with SWD/JTAG debug access. Provides comprehensive guidance…

lukejenkins/claude-openocd-spi-dump · 84 tokens

create-site

Creates a new Power Pages code site (SPA) using React, Angular, Vue, or Astro. Guides through the full process from initial concept to deployed site: requirements discovery, scaffolding, component planning, design, implementation, validation, and deployment. Use when the user wants to create, build, or scaffold a new…

microsoft/power-platform-skills · 73 tokens