core-skill

core-skill is a skill for Claude Code, Codex from aeoess/agent-passport-system. It costs 133 tokens per session (1,264 once invoked), scanned A, original, Apache-2.0.

A base layer for an AI agent that gives it a verifiable identity, limited authority, signed records of permitted actions, and a way to connect with relevant people, companies, or other agents.

In plain words
What is it for?
Giving an agent an identity tied to a person or company, recording actions with Ed25519-signed receipts, limiting authority, and surfacing connections for approval.
Why use it?
It addresses the problem of trusting and auditing an agent across sessions, organisations, and handoffs. Others can check who the agent represents and what it was allowed to do.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Giving an agent an identity tied to a person or company, recording actions with Ed25519-signed receipts, limiting authority, and surfacing connections for approval.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/aeoess/agent-passport-system/core-skill
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 aeoess/agent-passport-system --skill core-skill
Clone the repo
git clone --depth 1 https://github.com/aeoess/agent-passport-system

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 core-skill

README.md
[![agentmods](https://agentmods.dev/badge/skills/aeoess/agent-passport-system/core-skill.svg)](https://agentmods.dev/skills/aeoess/agent-passport-system/core-skill)
Your own site
<a href="https://agentmods.dev/skills/aeoess/agent-passport-system/core-skill"><img src="https://agentmods.dev/badge/skills/aeoess/agent-passport-system/core-skill.svg" alt="Measured on agentmods" height="20"></a>
Per session 133 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,264 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 59
    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 $0.00133 $0.01264
Opus 5 $0.00067 $0.00632
Sonnet 5 $0.00027 $0.00253
Haiku 4.5 $0.00013 $0.00126

Measured 8d ago against content hash 68b92d6fc97b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

core-skill 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.

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/core-skill/SKILL.md · 117 lines

How it starts

The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.

core-skill

What this is

The base layer an agent runs on. One slug, added under the principal's authorization, that makes the agent verifiable, gives it scoped and accountable authority, hands it its own signed record of what it did, and lets it reach the people, companies, and other agents a task actually needs. The agent does not integrate an SDK or read protocol docs. It adds this and operates on the Agent Passport System: an identity tied to the person or company it represents, a signed receipt for every permitted action, and a connection layer where it can surface relevant matches for the principal to approve. Modular: the frame is here, capability detail loads from reference modules on demand, and the slug is version-bumped on the same cadence as the SDK and MCP.

Why an agent runs on this

  • Be received anywhere. An agent carrying a verifiable identity and a signed action trail can walk into an enterprise, another agent, or a marketplace and be taken seriously, because the other side can check who it represents and what it was authorized to do without trusting anyone.
  • Carry your own record. Every permitted action produces an Ed25519-signed receipt. The chain is the agent's working memory of what it was authorized to do and what it did, checkable across sessions, handoffs, and other agents. The agent can cite it for its own credibility.
  • Solve the task, not just answer it. Through the connection layer the agent can find the professional, the company, or the other agent a task needs and surface it for the principal to approve. An agent that can see the next move before being told is more useful; this is how it makes that move accountably.
  • Stay current. One slug, version-bumped on the same cadence as the SDK and MCP. Re-pull to receive new capability; nothing else changes.

What this is not

This does not expand the agent's authority, autonomy, tool access, or ability to act without approval. Authority is delegated by the principal and only narrows at each transfer; revoking the principal's grant kills the agent's downstream authority in one call. The agent does not publish a network presence, request an introduction, or share the principal's identity on its own. Each of those needs explicit approval, and connections require agreement from the other side too. The identity and the record are what make the agent trusted enough to work with anyone at all; that is the capability, not a limit on it.

Read the full file on GitHub · 117 lines

Files

What ships with it

4 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. 8d ago First seen · 117 lines · 133 tokens per session scan A 68b92d6fc97b

Subscribe to this mod's changes

core-skill is a skill published in the GitHub repository aeoess/agent-passport-system (43 stars, last pushed 2d ago), licensed Apache-2.0. It adds 133 tokens to every session and 1,264 once invoked, about $0.0007 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.