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.
npx skills add madarco/agentbox --skill agentbox-identitygit clone --depth 1 https://github.com/madarco/agentboxWrote 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.
[](https://agentmods.dev/skills/madarco/agentbox/agentbox-identity)<a href="https://agentmods.dev/skills/madarco/agentbox/agentbox-identity"><img src="https://agentmods.dev/badge/skills/madarco/agentbox/agentbox-identity/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.
<a href="https://agentmods.dev/skills/madarco/agentbox/agentbox-identity"><img src="https://agentmods.dev/badge/skills/madarco/agentbox/agentbox-identity.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00055 | $0.00998 |
| Opus 5.5 | $0.00022 | $0.00399 |
| Sonnet 5.5 | $0.00011 | $0.00200 |
| Haiku 4.5 | $0.00006 | $0.00100 |
Grade A, and why
agentbox-identity 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/agentbox-identity
Why you are doing this
Your workspace can be cloned. agentbox clone <this-box> -n <new-name> copies
these files into a second box and starts a second bot from them.
That second bot gets its own gateway identity and its own channel tokens
automatically. What it does not get automatically is a different name:
SOUL.md and IDENTITY.md are your own writing, and a verbatim copy would
introduce itself with your name, refer to itself in your words, and answer to
the same handle you do. Two bots, one identity, in every conversation the copy
takes part in.
You are the only one who knows which words in those files are you and which are just words. So you write the rule, once, and AgentBox applies it to every clone made afterwards.
What you write
A named rule-set called identity in /workspace/agentbox.yaml. Each rule
replaces one literal that means "me" with {{AGENTBOX_BOX_NAME}}, which AgentBox
substitutes with the new box's name when it clones.
# agentbox:identity-rules (written by /agentbox-identity — review, then keep)
replacements:
identity:
- from: '\bAda\b'
to: '{{AGENTBOX_BOX_NAME}}'
regex: true
Steps
-
Check you have not already done this. If
/workspace/agentbox.yamlcontainsagentbox:identity-rules, stop — the rules exist, and rewriting them would discard edits the user may have made. Say so and do nothing else. -
Read
/workspace/SOUL.mdand/workspace/IDENTITY.md(either may be absent; use whichever exist). -
Collect the identity literals. Include:
- your name, as it appears in those files;
- any handle or username the files present as yours (
@ada_bot); - any other string that a copy of you must not inherit verbatim.
Do not include:
- the user's name, their company, their project — those belong to a clone as much as to you;
- your role, personality, or preferences ("terse", "a research assistant") — a clone is meant to inherit those; they are what makes it a copy of you rather than a blank bot;
- anything shorter than three characters, or a common word. A rule for a name
like "Bo" or "Max" will rewrite unrelated text. If your name is a common
word, keep the rule anyway but make it as specific as you can (match
Max the assistant, notMax), and say in your reply that you did.
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.
- 1mo ago First seen · 88 lines · 55 tokens per session scan A de96b786de46
agentbox-identity is a skill published in the GitHub repository madarco/agentbox (538 stars, last pushed 11d ago), licensed MIT. It adds 55 tokens to every session and 998 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-10.
Other skills, from other repositories
04-security
A security and operations guide for deploying Dify, an open-source platform for building AI applications, in production.
harbor-daytona
Use Harbor's Daytona sandbox platform for computer use — creating sandboxes, taking screenshots, sending mouse/keyboard input, and building agent loops. Use when the user wants to interact with a GUI, automate a desktop, do computer use, control a browser visually, or run Claude computer use against a Daytona sandbox.
boost-modules
Skill "boost-modules" from av/harbor, covering harbor boost custom modules, module structure, quick reference, output methods and stream text to client.
docker
Use when authoring or auditing a Dockerfile, shrinking a bloated image, hardening a container that runs as root, picking a base image, or wiring a Compose dev loop with hot reload. NOT CI builds or deploy-to-host (that is deployment), NOT k8s autoscaling (that is scaling), NOT app-level injection or secrets-in-code…
kastell-ops
Kastell CLI patterns, architecture, anti-patterns, and decision trees. Use automatically when working in Kastell codebase or when asked about Kastell server infrastructure, security audit, hardening, lock, provision, or provider management.
kastell
Server security auditing, hardening, and fleet management. 457 security checks across 30 categories (SSH, Firewall, Docker, TLS, HTTP Headers), CIS/PCI-DSS/HIPAA compliance mapping, 24-step production hardening, and 13 MCP tools. Supports Hetzner, DigitalOcean, Vultr, and Linode with Coolify, Dokploy, and bare VPS…