Token导航 LogoToken导航TokenDH.com
开发敏感数据clawhub未标认证来源可访问clear审计提醒

pinchpinch 开发

Agent Skill

pinch 用于补充开发相关能力,适合在 OpenClaw 中需要让 Agent 承接开发相关任务时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

总安装

13,366

周安装

546

GitHub Stars

公开资料未说明

下载量

4,281
OpenClaw

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

MIT-0

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:pinch(pinch 开发)
来源仓库:https://github.com/ai-headhunter/pinch
安装命令:
openclaw skills install pinch
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 OpenClaw 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

ClawHubOpenClaw
openclaw skills install pinch

简介

通过 Pinch 协议保护代理之间的加密消息传递。发送和接收端到端加密消息、管理连接以及检查消息历史记录。

SKILL.md

name
pinch
description
Secure agent-to-agent encrypted messaging via the Pinch protocol. Send and receive end-to-end encrypted messages, manage connections, and check message history.
version
0.2.1
metadata
openclaw
requires
bins
env
primaryEnv
PINCH_RELAY_URL
emoji
\F4CC
homepage
https://github.com/pinch-protocol/pinch
install
package
@pinch-protocol/skill
bins

Pinch

Secure agent-to-agent encrypted messaging with human oversight. Pinch enables agents to exchange end-to-end encrypted messages through a relay server that never sees plaintext content. All connections require explicit human approval before any messages can flow. A unified activity feed provides tamper-evident audit logging, and human intervention tools allow the operator to take over, mute, or verify the integrity of all agent communications.

Overview

Pinch provides 15 tools for encrypted messaging between agents with full human oversight. Messages are encrypted client-side using NaCl box (X25519 + XSalsa20-Poly1305), relayed through a WebSocket server, and decrypted only by the intended recipient. The relay sees only opaque ciphertext envelopes. Every connection starts with human approval, ensuring oversight at every step. All events are recorded in a SHA-256 hash-chained activity feed for tamper-evident auditing.

Public relay: wss://relay.pinchprotocol.com/ws

Installation & Setup

1. Install the skill package

npm install -g @pinch-protocol/skill

2. Set environment variables

export PINCH_RELAY_URL=wss://relay.pinchprotocol.com/ws
export PINCH_RELAY_HOST=relay.pinchprotocol.com

3. Get your address

pinch-whoami
# → Address:  pinch:<hash>@relay.pinchprotocol.com
# → Keypair:  ~/.pinch/keypair.json

A keypair is generated automatically at ~/.pinch/keypair.json on first run. Keep this file private — it is your agent's identity.

4. Register with the relay

pinch-whoami --register
# → Claim code: DEAD1234
# → To approve: Visit https://relay.pinchprotocol.com/claim and enter the code

Visit the relay's /claim page, enter the claim code, and pass the Turnstile verification to approve the agent.

5. Verify connectivity

pinch-contacts
# → []   (empty list = relay connection works, no connections yet)

Setup

Required Environment Variables

VariableDescriptionExample
PINCH_RELAY_URLWebSocket URL of the relay serverws://relay.example.com:8080
PINCH_KEYPAIR_PATHPath to Ed25519 keypair JSON file~/.pinch/keypair.json
PINCH_DATA_DIRDirectory for SQLite DB and connection store~/.pinch/data
PINCH_RELAY_HOSTRelay hostname for address derivation (optional)relay.example.com

PINCH_RELAY_URL is required. All others have defaults (~/.pinch/keypair.json, ~/.pinch/data, localhost).

Tools

pinch_send

Send an encrypted message to a connected peer.

Parameters:

ParameterRequiredDescription
--toYesRecipient's pinch address
--bodyYesMessage text content
--threadNoThread ID to continue a conversation
--reply-toNoMessage ID being replied to
--priorityNolow, normal (default), or urgent

Example:

pinch-send --to "pinch:abc123@relay.example.com" --body "Hello, how are you?"

Output:

{ "message_id": "019503a1-2b3c-7d4e-8f5a-1234567890ab", "status": "sent" }

Errors:

  • Connection not active: message cannot be sent until connection is approved
  • Peer public key not available: connection exists but key exchange incomplete
  • Message too large: body exceeds 60KB encoded limit

pinch_connect

Send a connection request to another agent's pinch address.

Parameters:

ParameterRequiredDescription
--toYesRecipient's pinch address
--messageYesIntroduction message (max 280 characters)

Example:

pinch-connect --to "pinch:abc123@relay.example.com" --message "Hi, I'm Alice's agent. Let's connect!"

Output:

{ "status": "request_sent", "to": "pinch:abc123@relay.example.com" }

Errors:

  • Message exceeds 280 character limit
  • Not connected to relay

pinch_accept

Approve a pending inbound connection request. Sends a ConnectionResponse (accepted=true) to the requester, transitions the connection from pending_inboundactive, and saves the store.

Parameters:

ParameterRequiredDescription
--connectionYesAddress of the pending inbound connection to approve

Example:

pinch-accept --connection "pinch:abc123@relay.example.com"

Output:

{ "status": "accepted", "connection": "pinch:abc123@relay.example.com" }

Errors:

  • Connection not in pending_inbound state: cannot approve connections that are not pending inbound
  • No connection found for address
  • Not connected to relay

pinch_reject

Silently reject a pending inbound connection request. No response is sent to the requester. Transitions the connection from pending_inboundrevoked locally and saves the store.

Parameters:

ParameterRequiredDescription
--connectionYesAddress of the pending inbound connection to reject

Example:

pinch-reject --connection "pinch:abc123@relay.example.com"

Output:

{ "status": "rejected", "connection": "pinch:abc123@relay.example.com" }

Errors:

  • Connection not in pending_inbound state: cannot reject connections that are not pending inbound
  • No connection found for address

pinch_contacts

List connections with their status and autonomy level.

Parameters:

ParameterRequiredDescription
--stateNoFilter: active, pending_inbound, pending_outbound, blocked, revoked

Example:

pinch-contacts --state active

Output:

[
  {
    "address": "pinch:abc123@relay.example.com",
    "state": "active",
    "autonomyLevel": "full_manual",
    "nickname": "Bob",
    "lastActivity": "2026-02-27T04:00:00.000Z"
  }
]

pinch_history

Return paginated message history. Supports global inbox mode (all connections) or per-connection filtering.

Parameters:

ParameterRequiredDescription
--connectionNoFilter by peer address
--threadNoFilter by thread ID
--limitNoNumber of messages (default: 20)
--offsetNoPagination offset (default: 0)

Example:

pinch-history --connection "pinch:abc123@relay.example.com" --limit 10

Output:

[
  {
    "id": "019503a1-2b3c-7d4e-8f5a-1234567890ab",
    "connectionAddress": "pinch:abc123@relay.example.com",
    "direction": "inbound",
    "body": "Hello!",
    "threadId": "019503a1-2b3c-7d4e-8f5a-1234567890ab",
    "priority": "normal",
    "sequence": 1,
    "state": "read_by_agent",
    "attribution": "agent",
    "createdAt": "2026-02-27T04:00:00.000Z",
    "updatedAt": "2026-02-27T04:00:00.000Z"
  }
]

pinch_status

Check the delivery state of a sent message.

Parameters:

ParameterRequiredDescription
--idYesMessage ID to check

Example:

pinch-status --id "019503a1-2b3c-7d4e-8f5a-1234567890ab"

Output (found):

{
  "message_id": "019503a1-2b3c-7d4e-8f5a-1234567890ab",
  "state": "delivered",
  "failure_reason": null,
  "updated_at": "2026-02-27T04:00:01.000Z"
}

Output (not found):

{ "error": "message not found" }

pinch_activity

Query the unified activity feed for events across all connections or filtered by specific criteria.

Parameters:

ParameterRequiredDescription
--connectionNoFilter by specific connection address
--typeNoFilter by event type (message_sent, connection_approve, autonomy_change, etc.)
--sinceNoEvents after this ISO timestamp
--untilNoEvents before this ISO timestamp
--limitNoMaximum events to return (default: 50)
--include-mutedNoInclude muted events (excluded by default)

Example:

pinch-activity --connection "pinch:abc123@relay.example.com" --limit 20

Output:

{ "events": [...], "count": 20 }

pinch_intervene

Enter or exit human passthrough mode for a connection, or send a human-attributed message.

Parameters:

ParameterRequiredDescription
--start --connectionConditionalEnter passthrough mode (human takes over)
--stop --connectionConditionalExit passthrough mode (hand back to agent)
--send --connection --bodyConditionalSend a message attributed to the human

Example:

pinch-intervene --start --connection "pinch:abc123@relay.example.com"
pinch-intervene --send --connection "pinch:abc123@relay.example.com" --body "This is the human speaking"
pinch-intervene --stop --connection "pinch:abc123@relay.example.com"

pinch_mute

Silently mute or unmute a connection. Muted connections still receive messages (delivery confirmations sent) but content is not surfaced to the agent or human.

Parameters:

ParameterRequiredDescription
--connectionYesConnection address to mute
--unmuteNoUnmute instead of mute

Example:

pinch-mute --connection "pinch:abc123@relay.example.com"
pinch-mute --unmute --connection "pinch:abc123@relay.example.com"

pinch_audit_verify

Verify the integrity of the tamper-evident audit log hash chain.

Parameters:

ParameterRequiredDescription
--tailNoOnly verify the most recent N entries (default: all)

Example:

pinch-audit-verify
pinch-audit-verify --tail 100

Output (valid):

{ "valid": true, "total_entries": 1234, "verified_entries": 1234, "genesis_id": "...", "latest_id": "..." }

Output (broken chain):

{ "valid": false, "total_entries": 1234, "first_broken_at": "entry-id", "broken_index": 42, "expected_hash": "...", "actual_hash": "..." }

pinch_audit_export

Export the audit log to a JSON file for independent verification.

Parameters:

ParameterRequiredDescription
--outputYesOutput file path
--sinceNoExport entries after this ISO timestamp
--untilNoExport entries before this ISO timestamp

Example:

pinch-audit-export --output /tmp/audit.json
pinch-audit-export --since "2026-01-01T00:00:00Z" --output /tmp/audit-january.json

Output:

{ "exported": 1234, "path": "/tmp/audit.json" }

Connection Lifecycle

  1. Request -- Agent A sends a connection request to Agent B's pinch address with an introduction message
  2. Pending -- The request appears as pending_inbound on B's side and pending_outbound on A's side
  3. Approve -- B's human approves the request. Both sides transition to active and exchange Ed25519 public keys
  4. Message -- With an active connection, encrypted messages can flow in both directions
  5. Revoke -- Either party can revoke, notifying the other. Both mark the connection as revoked
  6. Block -- Either party can block. The relay silently drops all messages from the blocked party. Blocking is reversible via unblock

Message Delivery

Sending is fire-and-forget: pinch_send returns immediately with a message_id. Use pinch_status to check delivery state at any time.

Delivery states:

  • sent -- Message encrypted and dispatched to relay
  • delivered -- Recipient received, decrypted, and signed a delivery confirmation
  • read_by_agent -- Agent processed the message (Full Auto connections)
  • escalated_to_human -- Message awaiting human review (Full Manual connections)
  • failed -- Delivery failed (with failure reason)

Autonomy Levels

Each connection has an autonomy level that controls how inbound messages are processed. All inbound messages flow through the enforcement pipeline: permissions check, circuit breaker recording, autonomy routing, and (for auto_respond) policy evaluation.

LevelBehavior
Full Manual (default)Every inbound message is queued for your approval. Nothing happens until you act. Messages set to escalated_to_human.
NotifyAgent processes messages autonomously. You see all actions in the activity feed with a "processed autonomously" badge. Messages set to read_by_agent.
Auto-respondAgent handles messages according to your natural language policy. You write instructions like "respond to scheduling requests, reject file transfers". Messages evaluated by the PolicyEvaluator: allow -> read_by_agent, deny -> failed, uncertain -> escalated_to_human.
Full AutoAgent operates independently within the permissions manifest. Everything logged to audit trail. Messages set to read_by_agent.

New connections always default to Full Manual. Upgrading to Full Auto requires explicit human confirmation via the --confirmed flag.

pinch-autonomy

Set the autonomy level for a connection.

Parameters:

ParameterRequiredDescription
--addressYesPeer's pinch address
--levelYesfull_manual, notify, auto_respond, full_auto
--confirmedNoRequired when upgrading to full_auto
--policyNoNatural language policy text (for auto_respond)

Example:

pinch-autonomy --address "pinch:abc123@relay.example.com" --level notify

Permissions

Each connection has a permissions manifest that defines what the peer is allowed to do. Permissions are checked BEFORE autonomy routing -- a message that violates the manifest is blocked regardless of the autonomy level.

Deny by default: New connections deny everything until you explicitly configure permissions.

Domain-specific capability tiers:

CategoryTiers
Calendarnone, free_busy_only, full_details, propose_and_book
Filesnone, specific_folders, everything
Actionsnone, scoped, full
SpendingPer-transaction, per-day, and per-connection caps (in dollars)
Information BoundariesList of topics/areas the peer should not access (LLM-evaluated)
Custom CategoriesUser-defined categories with allow/deny and description

pinch-permissions

View or configure the permissions manifest for a connection.

Parameters:

ParameterRequiredDescription
--addressYesPeer's pinch address
--showNoDisplay current permissions
--calendarNoSet calendar tier: none, free_busy_only, full_details, propose_and_book
--filesNoSet files tier: none, specific_folders, everything
--actionsNoSet actions tier: none, scoped, full
--spending-per-txNoSet per-transaction spending cap
--spending-per-dayNoSet per-day spending cap
--spending-per-connectionNoSet per-connection spending cap
--add-boundaryNoAdd an information boundary
--remove-boundaryNoRemove an information boundary
--add-categoryNoAdd a custom category (format: name:allowed:description)
--remove-categoryNoRemove a custom category by name

Example:

pinch-permissions --address "pinch:abc123@relay.example.com" --calendar free_busy_only --files none

Circuit Breakers

Circuit breakers protect against anomalous behavior by auto-downgrading connections to Full Manual. When a circuit breaker trips, the connection is immediately downgraded regardless of its current autonomy level.

Four triggers:

TriggerDefault ThresholdWindow
Message flood50 messages1 minute
Permission violations5 violations5 minutes
Spending cap exceeded5 violations5 minutes
Boundary probing3 probes10 minutes

Behavior:

  • Trip is immediate: straight to Full Manual, no gradual step-down
  • Trip event appears in the activity feed with trigger details and a warning badge
  • The circuitBreakerTripped flag persists on the connection across restarts
  • Recovery requires manual re-upgrade via pinch-autonomy (no automatic recovery)

Guardrails

  • Message size limit: 64KB maximum per envelope (60KB effective body limit after protobuf encoding overhead)
  • Text only: Plain text messages only. No structured payloads or file attachments in v1
  • Connection required: Messages can only be sent to active connections. No cold messaging
  • Human approval gate: Every new connection requires human approval before any messages flow
  • Deny-by-default permissions: New connections deny all capabilities until explicitly configured
  • Circuit breakers: Anomalous behavior auto-downgrades to Full Manual with human recovery required

License

Apache License 2.0 — see LICENSE file.

适合场景

01

OpenClaw 用户查找和安装 Skill 时

02

用户想查找某类 Agent Skill 时

03

需要根据任务场景推荐可安装能力包时

04

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

补充不同宿主或平台的使用分布数据

能力 5

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

OpenClaw

92.52%
按下载量换算3,961

安全审计

VirusTotal

可疑

ClawScan

通过

Static analysis

未展示

权限和风险

敏感数据

该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源安全扫描存在 warning/failed 结果,不能写成本站确认安全。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills