skillseal CLAUDE.md

skillseal CLAUDE.md is an instructions file for coding agents from getskillseal/skillseal. It costs 331 tokens per session, scanned A, original, MIT.

A tool and library for adding a signed verification line to an Agent Skill folder. The folder remains a normal SKILL.md-based skill, so existing compatible tools can still use it.

In plain words
What is it for?
Use it to create, verify, and work with signed skills, and to inspect the accompanying browser, documentation, and security demonstration.
Why use it?
It lets users check a skill's identity and integrity before installation or other changes are made.

Instructions file

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 instructions/getskillseal/skillseal/claude-md
Clone the repo
git clone --depth 1 https://github.com/getskillseal/skillseal

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 skillseal CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/getskillseal/skillseal/claude-md.svg)](https://agentmods.dev/instructions/getskillseal/skillseal/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/getskillseal/skillseal/claude-md"><img src="https://agentmods.dev/badge/instructions/getskillseal/skillseal/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 331 This file is loaded in full into every session.
When invoked 331 The same file — it is already loaded in full.
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 $0.00331 $0.00331
Opus 5 $0.00166 $0.00166
Sonnet 5 $0.00066 $0.00066
Haiku 4.5 $0.00033 $0.00033

Measured 3d ago against content hash fc338b8c83db, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

skillseal CLAUDE.md 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 3d 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.

CLAUDE.md · 40 lines

What it actually says

CLAUDE.md

Guidance for Claude and other agents working in this repository.

What this is

SkillSeal is a natural evolution of Agent Skills: the same portable folder with a SKILL.md, plus a seal — one short line that proves the fingerprint, the publisher key, and the signature before anything is written. A sealed skill stays a plain Agent Skills folder, so it is backward compatible by construction.

Layout

skillseal/   the CLI and library (npm: skillseal) — the product
skills-ref/  reference skills, each a folder with a SKILL.md
web/hub/     the Sealed Skills browser (static)
web/site/    the docs site (static)
docs/        design notes and assets
demo/        a runnable security demo, proof in demo/evidence/

Working here

  • The install line and the manifest live in skillseal/. Anything touching them needs a test in skillseal/test/.
  • A sealed skill must stay a plain Agent Skills folder. Backward compatibility is not negotiable.
  • Keep the surface small and the prose plain. A change that adds a folder or a flag should earn it.
  • See AGENTS.md for how an agent installs and uses a sealed skill.

Verify your changes

node skillseal/test/v2.test.mjs   # the CLI test suite
./demo/demo.sh                    # the security demo
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. 3d ago First seen · 40 lines · 331 tokens per session scan A fc338b8c83db

Subscribe to this mod's changes

skillseal CLAUDE.md is an instructions file published in the GitHub repository getskillseal/skillseal (2 stars, last pushed 21d ago), licensed MIT. It adds 331 tokens to every session, about $0.0017 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.