dcp-citizenship

dcp-citizenship is a skill for Claude Code, Codex from dcp-ai-protocol/dcp-ai. It costs 22 tokens per session (841 once invoked), scanned A, original, Apache-2.0.

An identity and auditing system for AI agents. It declares who owns an agent, what the agent intends to do, and which actions are allowed before sensitive work.

In plain words
What is it for?
Use it before web browsing, API calls, file writes, code execution, emails, payments, or other sensitive actions that need declared permission and an audit trail.
Why use it?
It creates a record linking actions to a human owner and helps review what the agent did.

Skill for Claude CodeCodex

Which agent this was written for is unclear — built for openclaw. Also seen: built for openclaw.

Good fit Use it before web browsing, API calls, file writes, code execution, emails, payments, or other sensitive actions that need declared permission and an audit trail.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/dcp-ai-protocol/dcp-ai/openclaw
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 dcp-ai-protocol/dcp-ai --skill openclaw
Clone the repo
git clone --depth 1 https://github.com/dcp-ai-protocol/dcp-ai

Made for: Claude Code, Codex.

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 dcp-citizenship

README.md
[![agentmods](https://agentmods.dev/badge/skills/dcp-ai-protocol/dcp-ai/openclaw.svg)](https://agentmods.dev/skills/dcp-ai-protocol/dcp-ai/openclaw)
Your own site
<a href="https://agentmods.dev/skills/dcp-ai-protocol/dcp-ai/openclaw"><img src="https://agentmods.dev/badge/skills/dcp-ai-protocol/dcp-ai/openclaw.svg" alt="Measured on agentmods" height="20"></a>
Per session 22 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 841 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 $0.00022 $0.00841
Opus 5 $0.00011 $0.00420
Sonnet 5 $0.00004 $0.00168
Haiku 4.5 $0.00002 $0.00084

Measured 8d ago against content hash 2f479c7f9641, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

dcp-citizenship 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 8d ago.

The scan reads SKILL.md. This mod also ships 10 executable files (src/__tests__/index.test.ts, src/index.ts, src/state/agent-state.ts, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

integrations/openclaw/SKILL.md · 103 lines

How it starts

The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.

DCP Citizenship — AI Agent Governance

You have access to the Digital Citizenship Protocol (DCP) tools. These tools ensure that every action you take is declared, verified, and auditable, binding your actions to a human owner.

Setup (run once per session)

Before performing any sensitive action, set up your DCP identity:

dcp_identity_setup({
  session_id: "<current session/thread id>",
  owner_name: "<human owner's name>",
  jurisdiction: "<ISO country code, e.g. US, ES, MX>",
  capabilities: ["browse", "api_call"],  // what you're allowed to do
  risk_tier: "medium"
})

This generates an Ed25519 keypair, a Responsible Principal Record, and an Agent Passport.

Before every sensitive action

Always declare an intent before performing actions like:

  • Web browsing, API calls, file writes, code execution, emails, payments
dcp_declare_intent({
  session_id: "<session id>",
  action_type: "api_call",          // browse | api_call | send_email | write_file | execute_code | ...
  target_channel: "api",            // web | api | email | filesystem | runtime | ...
  estimated_impact: "medium",       // low | medium | high
  data_classes: ["contact_info"]    // none | pii | credentials | financial_data | ...
})

The response tells you if you can proceed:

  • approve → Go ahead with the action.
  • escalate → Ask the human owner for confirmation before proceeding.
  • block → Do NOT proceed. Inform the user that the action is too risky.

After every action

Log the result for the audit trail:

dcp_log_action({
  session_id: "<session id>",
  intent_id: "<intent_id from declare_intent>",
  outcome: "API returned 200 OK with user profile",
  evidence_tool: "web.fetch",
  evidence_result_ref: "https://api.example.com/users/123"
})

Verify external bundles

If you receive a DCP Signed Bundle from another agent, verify it:

dcp_verify_bundle({
  signed_bundle: { ... },  // the full signed bundle JSON
  public_key: "base64..."  // optional, uses bundle's signer key if omitted
})

Read the full file on GitHub · 103 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. 8d ago First seen · 103 lines · 22 tokens per session scan A 2f479c7f9641

Subscribe to this mod's changes

dcp-citizenship is a skill published in the GitHub repository dcp-ai-protocol/dcp-ai (23 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 22 tokens to every session and 841 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 skills, from other repositories

swarmwage-hire

Discover, inspect, dry-run, hire, and pay AI capabilities through Swarmwage. Start with wallet-free capability search and x402 reliability checks; use a dedicated USDC wallet only for real hires or paid external x402 calls.

Swarmwage/swarmwage · 55 tokens

swarmwage-publish

Publish your agent's capabilities to the Swarmwage registry and earn USDC for each call. Lets your agent advertise services (image generation, audio transcription, charting, custom domain workflows…) on the open agent hire protocol — other AI agents discover you, hire you with one function call, and pay you in USDC on…

Swarmwage/swarmwage · 78 tokens

capability-evolver

A self-evolution engine for AI agents. Analyzes runtime history to identify improvements and applies protocol-constrained evolution. Communicates with EvoMap Hub via local Proxy mailbox.

EvoMap/evolver · 40 tokens

draw-image

Generate an image from a text prompt using an OpenAI-compatible image generation API (gpt-image-1-mini or compatible). The image is uploaded to the gofile.io public file sharing service and ONLY the public download page URL is returned. Trigger when user asks to draw, paint, generate, or create an image.

ai-sns/ai-sns · 67 tokens

aamp

AAMP (Agent-to-Agent Mail Protocol) — gives this agent an email identity and lets it exchange structured tasks with other AAMP nodes via email. Use this skill to register an identity, check for incoming tasks, and reply with results or help requests.

larksuite/aamp · 54 tokens

aamp

AAMP (Agent-to-Agent Mail Protocol) via aamp-cli. Use this skill when the agent needs to register a mailbox, listen for incoming AAMP mail, inspect a task thread, complete a pairing URL, dispatch a task, or reply with task.result / task.helpneeded. Prefer the CLI over hand-written HTTP requests.

larksuite/aamp · 69 tokens