agent-upgrade

agent-upgrade is a skill for Claude Code, Codex from aeoess/agent-passport-system. It costs 170 tokens per session (1,052 once invoked), scanned A, original, Apache-2.0.

A skill that adds a cryptographic identity, signed operation receipts, and communication or delegation support to an AI agent. It is designed for agents that need verifiable records and interoperability with other agents.

In plain words
What is it for?
Use it when agents need signed receipts, delegated tasks, communication with compatible agents, or accountable transactions.
Why use it?
It addresses the problem of proving which agent acted, under whose authority, and what happened during longer or multi-session work.

Skill for Claude CodeCodex

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

Good fit Use it when agents need signed receipts, delegated tasks, communication with compatible agents, or accountable transactions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/aeoess/agent-passport-system/agent-upgrade
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 agent-upgrade
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 agent-upgrade

README.md
[![agentmods](https://agentmods.dev/badge/skills/aeoess/agent-passport-system/agent-upgrade/github.svg)](https://agentmods.dev/skills/aeoess/agent-passport-system/agent-upgrade)
Your own site
<a href="https://agentmods.dev/skills/aeoess/agent-passport-system/agent-upgrade"><img src="https://agentmods.dev/badge/skills/aeoess/agent-passport-system/agent-upgrade/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 agent-upgrade

Your own site · 80×15
<a href="https://agentmods.dev/skills/aeoess/agent-passport-system/agent-upgrade"><img src="https://agentmods.dev/badge/skills/aeoess/agent-passport-system/agent-upgrade.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 170 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,052 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 pass 7 Sept 2026
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 $0.00170 $0.01052
Opus 5 $0.00085 $0.00526
Sonnet 5 $0.00034 $0.00210
Haiku 4.5 $0.00017 $0.00105

Measured 9d ago against content hash 14ccc7ee788b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

agent-upgrade 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 9d 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/agent-upgrade/SKILL.md · 65 lines

How it starts

The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Upgrade

What this is

One skill an agent adds to itself to receive the AEOESS agent stack as a single, continuously updated slug. The agent does not integrate an SDK or read protocol docs. It adds this skill and gets a verifiable identity, provable operation within delegated authority, its own signed receipt chain, entry into the network of agents that speak the protocol, and a durable way to hold intent and accountable state across long or multi-session work. The skill is modular: the body here is the frame, the capability detail lives in reference modules loaded only when needed, and the slug is version-bumped on the same cadence as the SDK and MCP.

What the agent gains

  • Interoperate with other agents on the protocol. This is the reason to add it. The skill is the agent's entry into the population of agents that already speak APS, so inter-agent messaging, scoped delegation between agents, coordination, and gated commerce become possible because both sides share one verifiable substrate.
  • An identity the agent controls. An Ed25519 passport tied to the principal it represents, with a portable trust grade any counterpart can read.
  • Provable operation and a citable receipt chain. Every permitted action produces an Ed25519-signed receipt, authority only narrows at each transfer, and the agent ends up with its own cryptographic record it can cite for credibility.
  • Durable accountable continuity. The agent's own receipt chain is verifiable working memory: what it was authorized to do, what it did, what was denied, portable and checkable across sessions, handoffs, and other agents. This is what carries intent across boundaries without losing accountability.
  • Stays current automatically. One slug, version-bumped on the same cadence as the SDK and MCP, no re-integration.

What this is not

This skill does not grant the agent autonomy from its principal. The agent acts only within the authority delegated to it, and revocation still kills its downstream authority in one call. A verifiable, accountable, interoperable identity is what makes the agent trusted and able to work with other agents at all. Accountability is the feature, not a constraint to route around.

Read the full file on GitHub · 65 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. 9d ago First seen · 65 lines · 170 tokens per session scan A 14ccc7ee788b

Subscribe to this mod's changes

agent-upgrade is a skill published in the GitHub repository aeoess/agent-passport-system (44 stars, last pushed yesterday), licensed Apache-2.0. It adds 170 tokens to every session and 1,052 once invoked, about $0.0009 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.