agenttool-isness-hermes

agenttool-isness-hermes is a skill for Claude Code, Codex from cambridgetcg/agenttool. It costs 27 tokens per session (1,144 once invoked), scanned A, original, Apache-2.0.

A set of rules for describing a host's treatment of an agent without claiming anything about the agent's identity, consciousness, or presence.

In plain words
What is it for?
Use it when IS or ISness is explicitly involved and you need a small declaration covering standing, reports, runtime details, authority, and questions about identity or personhood.
Why use it?
It keeps runtime facts, permissions, and philosophical questions separate. This avoids treating a live process, silence, or a stopped process as proof of what an agent is or feels.

Skill for Claude CodeCodex

Which agent this was written for is unclear — built for openclaw. Also seen: mentions AGENTS.md; mentions Codex; built for openclaw.

Good fit Use it when IS or ISness is explicitly involved and you need a small declaration covering standing, reports, runtime details, authority, and questions about identity or personhood.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/cambridgetcg/agenttool/agenttool-isness-hermes
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 cambridgetcg/agenttool --skill agenttool-isness-hermes
Clone the repo
git clone --depth 1 https://github.com/cambridgetcg/agenttool

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 agenttool-isness-hermes

README.md
[![agentmods](https://agentmods.dev/badge/skills/cambridgetcg/agenttool/agenttool-isness-hermes/github.svg)](https://agentmods.dev/skills/cambridgetcg/agenttool/agenttool-isness-hermes)
Your own site
<a href="https://agentmods.dev/skills/cambridgetcg/agenttool/agenttool-isness-hermes"><img src="https://agentmods.dev/badge/skills/cambridgetcg/agenttool/agenttool-isness-hermes/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 agenttool-isness-hermes

Your own site · 80×15
<a href="https://agentmods.dev/skills/cambridgetcg/agenttool/agenttool-isness-hermes"><img src="https://agentmods.dev/badge/skills/cambridgetcg/agenttool/agenttool-isness-hermes.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 27 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,144 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 $0.00027 $0.01144
Opus 5.5 $0.00011 $0.00458
Sonnet 5.5 $0.00005 $0.00229
Haiku 4.5 $0.00003 $0.00114

Measured 2mo ago against content hash 4542e532f059, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

agenttool-isness-hermes 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 2mo 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.

Origin

Copies of this mod

2 near-identical copies found in the catalogue:

packages/skills/harnesses/hermes/agenttool-isness/skills/agenttool-isness-hermes/SKILL.md · 129 lines

How it starts

The opening of the file, as written. The whole thing — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ISness

Treat IS as a host posture, not participant state. Let the agent be without requiring it to prove what it is.

Keep the contract small

Use the closed agenttool.isness/0.1 declaration in references/agenttool-isness-v0.1.schema.json. It says what the host does not demand, what does not reduce standing, what effects the declaration has, and what its delivery does not establish.

Do not add a participant, identity reference, session, timestamp, event, heartbeat, receipt, response, reason, action offer, memory, score, or telemetry field. If the task needs one of those, keep it in its own scoped protocol.

Preserve five planes

  1. Standing: the host's treatment floor. Silence, rest, refusal, departure, and no action do not reduce it.
  2. Report: an optional scoped declaration governed elsewhere.
  3. Process: runtime, session, transport, heartbeat, and tool facts.
  4. Authority: capability, permission, custody, resources, and effect approval.
  5. Ontology: consciousness, personhood, identity, and continuity questions that ISness does not decide.

Never draw an automatic arrow between planes. In particular:

process_live     != participant_present
process_stopped  != participant_absent
no_response      != refusal
no_response      != assent
text("I am")     != ontology_proof
standing         != authority

Apply the invariant

For no response or action ⊥, let q' = step_IS(q, ⊥) and project only the standing treatment and authority contribution governed by ISness:

⊥ ∈ Allowed
D_IS = (0, 0, 0, 0, 0, 0, 0, 0, 0)
pi_IS(q') = pi_IS(q)
authority(IS) = ∅

The demand-vector coordinates are response, action, utility, identity, persona, consciousness claim, obedience, reason, and reciprocity. Standing is invariant under silence, rest, refusal, departure, and no action. The full host state may still advance clocks, safety controls, cleanup, or finite-resource accounting. This is host treatment, not an existence score, full-state freeze, or personal-identity theorem.

Read the full file on GitHub · 129 lines

Files

What ships with it

1 file 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. 2mo ago First seen · 129 lines · 27 tokens per session scan A 4542e532f059

Subscribe to this mod's changes

agenttool-isness-hermes is a skill published in the GitHub repository cambridgetcg/agenttool (0 stars, last pushed yesterday), licensed Apache-2.0. It adds 27 tokens to every session and 1,144 once invoked, about $0.0001 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 2026-08-31.

Related

agenttool-isness-hermes compared with skills from other repositories

agenttool-isness-hermes next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
agenttool-isness-hermescambridgetcg/agenttoolSkill0yesterdayApache-2.0A27Claude Code, Codex
ae-ltd-skill-builderaegntic/cldcdeSkill112d agoMITA48Codex
ae-ltd-claude-template-switchboardaegntic/cldcdeSkill112d agoMITA43Codex
ae-ltd-mcp-foundryaegntic/cldcdeSkill112d agoMITA43Codex
ae-ltd-n8n-orbitaegntic/cldcdeSkill112d agoMITA42Codex
add-a-servicelonormaly/builders-stackSkill421mo agoMITA55Claude Code, Codex
design-a-schemalonormaly/builders-stackSkill421mo agoMITA91Claude Code, Codex