amethyst: Skill for Claude Code

.claude/skills/auth-signers/SKILL.md

auth-signers is a skill for Claude Code from vitorpamplona/amethyst. It costs 0 tokens per session (1,607 once invoked), scanned A, original, MIT.

A guide to the signer system in Amethyst, a Nostr app, where a signer creates the cryptographic approval attached to an event. It covers local keys, remote bunker signers, and Android external-app signers through one shared interface.

In plain words
What is it for?
Use it when publishing signed Nostr events, adding signer types, reviewing remote or external signing flows, or debugging signing failures.
Why use it?
It helps features work with different ways of approving actions instead of assuming the user's private key is stored locally. It also helps diagnose approvals that time out or produce no result.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is vitorpamplona/amethyst's own configuration. It tells Claude Code how to work on amethyst itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything amethyst configures →

About the project

Amethyst is an Android client for Nostr, a social network protocol that lets people control their own social activity and connections. People use it to read and publish Nostr content, follow accounts, and exchange encrypted direct messages from Android and other supported platforms. The catalogue add-ons support workflows for developing or operating the client.

vitorpamplona/amethyst · 1,620 stars · on GitHub · amethyst.social

Reuse

Borrowing it

Nothing to install: this file belongs to vitorpamplona/amethyst. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/vitorpamplona/amethyst/main/.claude/skills/auth-signers/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/vitorpamplona/amethyst

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.

agentmods badge for auth-signers

README.md
[![agentmods](https://agentmods.dev/badge/skills/vitorpamplona/amethyst/auth-signers/github.svg)](https://agentmods.dev/skills/vitorpamplona/amethyst/auth-signers)
Your own site
<a href="https://agentmods.dev/skills/vitorpamplona/amethyst/auth-signers"><img src="https://agentmods.dev/badge/skills/vitorpamplona/amethyst/auth-signers/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 auth-signers

Your own site · 80×15
<a href="https://agentmods.dev/skills/vitorpamplona/amethyst/auth-signers"><img src="https://agentmods.dev/badge/skills/vitorpamplona/amethyst/auth-signers.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,607 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 warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Excessive Agency · line 87
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 $0.00000 $0.01607
Opus 5.5 $0.00000 $0.00643
Sonnet 5.5 $0.00000 $0.00321
Haiku 4.5 $0.00000 $0.00161

Measured yesterday against content hash f54b0f46d020, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

auth-signers 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 yesterday.

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/skills/auth-signers/SKILL.md · 107 lines

How it starts

The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Signers

Every signed event and every NIP-04/NIP-44 operation goes through a NostrSigner. Feature code never knows which of the three kinds the user has.

The contract (all suspend)

quartz/src/commonMain/kotlin/com/vitorpamplona/quartz/nip01Core/signers/NostrSigner.kt:

abstract class NostrSigner(pubKey: HexKey) {
    open val pubKey: HexKey                       // open: NIP-46 resolves it from the bunker
    abstract fun isWriteable(): Boolean
    suspend fun <T : Event> sign(ev: EventTemplate<T>): T
    abstract suspend fun <T : Event> sign(createdAt: Long, kind: Int, tags: Array<Array<String>>, content: String): T
    abstract suspend fun nip04Encrypt(plaintext: String, toPublicKey: HexKey): String
    abstract suspend fun nip04Decrypt(ciphertext: String, fromPublicKey: HexKey): String
    abstract suspend fun nip44Encrypt(plaintext: String, toPublicKey: HexKey): String
    abstract suspend fun nip44Decrypt(ciphertext: String, fromPublicKey: HexKey): String
    abstract suspend fun decryptZapEvent(event: ZapRequestEvent): PrivateZapEvent
    abstract suspend fun deriveKey(nonce: HexKey): HexKey
    abstract suspend fun signPsbt(psbtHex: String): String   // NIP-BC; may throw UnsupportedMethodException
    abstract fun hasForegroundSupport(): Boolean
    suspend fun decrypt(encryptedContent: String, fromPublicKey: HexKey): String   // picks NIP-04 vs NIP-44
}

Failures are thrown as SignerExceptions (nip01Core/signers/SignerExceptions.kt): ReadOnlyException, UnauthorizedDecryptionException, NothingToDecrypt, AutomaticallyUnauthorizedException, ManuallyUnauthorizedException, TimedOutException, CouldNotPerformException, RunningOnBackgroundWithoutAutomaticPermissionException, SignerNotFoundException, UnsupportedMethodException. Same folder: NostrSignerSync (blocking, for tests/scripts), EventTemplate.kt, caches/ (DecryptCache).

The three signers

Signer File Notes
NostrSignerInternal quartz/.../nip01Core/signers/NostrSignerInternal.kt key in process memory; created/imported accounts
NostrSignerRemote quartz/.../nip46RemoteSigner/signer/NostrSignerRemote.kt NIP-46 bunker over kind 24133; references/nip46-remote-signer.md
NostrSignerExternal quartz/src/androidMain/.../nip55AndroidSigner/client/NostrSignerExternal.kt NIP-55 app (Amber…) via intents + content provider; Android only; references/nip55-android-signer.md

Read the full file on GitHub · 107 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. yesterday Changed · +2 lines f54b0f46d020
  2. 15d ago Changed 71b9e0deeebb
  3. 25d ago Changed · -102 tokens per session f473193653c9
  4. 28d ago Changed 56fe91d70e51
  5. 1mo ago Changed 3f42b5fdd9a7
  6. 2mo ago First seen · 105 lines · 102 tokens per session scan A 1aff8f2d16f3

Subscribe to this mod's changes

auth-signers is a skill published in the GitHub repository vitorpamplona/amethyst (1,620 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,607 tokens. 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

auth-signers compared with skills from other repositories

auth-signers next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
auth-signersvitorpamplona/amethystSkill1.6kyesterdayMITA0Claude Code
burner-walletsepivip/SeekerClawSkill3199d agoMITA91Claude Code, Codex
crypto-pricessepivip/SeekerClawSkill3199d agoMITA70Claude Code, Codex
sceneviewsceneview/sceneviewSkill1.4kyesterdayApache-2.0A156Codex
compose-focus-navigationchrisbanes/skillsSkill1.1kyesterdayApache-2.0A41Claude Code
kotlin-androidericrisco/rsc-harnessSkill5032d agoMITA78Claude Code, Codex
compose-multiplatformericrisco/rsc-harnessSkill5032d agoMITA80Claude Code, Codex