claim-semantics

claim-semantics is an agent for coding agents from pome223/missionos. It costs 0 tokens per session (1,530 once invoked), scanned A, original, Apache-2.0.

A shared dictionary for describing what an AI system, person, rule, executor, verifier, or repair step actually did. It separates planned actions, approvals, sent commands, acknowledgements, and runtime evidence.

In plain words
What is it for?
Use it to define claim fields and enforce boundaries in runtime and hardware-adapter code.
Why use it?
It prevents separate facts from being blended into one unsupported claim. This makes it clearer what was proposed, approved, executed, and confirmed.

Agent

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.

agentmods
npx agentmods add agents/pome223/missionos/claim-semantics
Clone the repo
git clone --depth 1 https://github.com/pome223/missionos

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 claim-semantics

README.md
[![agentmods](https://agentmods.dev/badge/agents/pome223/missionos/claim-semantics.svg)](https://agentmods.dev/agents/pome223/missionos/claim-semantics)
Your own site
<a href="https://agentmods.dev/agents/pome223/missionos/claim-semantics"><img src="https://agentmods.dev/badge/agents/pome223/missionos/claim-semantics.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,530 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00000 $0.01530
Opus 5 $0.00000 $0.00765
Sonnet 5 $0.00000 $0.00306
Haiku 4.5 $0.00000 $0.00153

Measured 5d ago against content hash aa98655a3e22, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

claim-semantics 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 5d 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.

docs/agents/claim-semantics.md · 148 lines

How it starts

The opening of the file, as written. The whole thing — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Claim Semantics

Use explicit claim language. Do not collapse separate facts. This is the field dictionary for the claim boundary; the enforcement code is src/runtime/runtime_claim_evidence.py and src/runtime/hardware_adapter_contract.py.

Canonical Split

LLM judges.
Human approves.
Rules constrain.
Executor acts.
Verifier checks.
Repair loops.

Common Fields

Each field is a boolean unless noted. A field being present in an artifact does not make it runtime-true; see "Two-Phase Artifact vs Runtime" below.

  • proposal_created: an AI or planner produced a candidate response.
  • approval_recorded / operator_approved: a human approval or rejection was recorded.
  • dispatch_authority_created: a gate created authority to send a bounded action. Pinned Literal[False] on preflight and dispatch-candidate models in hardware_adapter_contract.py; authority is created later, not at preflight.
  • dispatch_request_sent: an executor attempted to send a command.
  • command_ack_observed: a runtime or transport acknowledgement was observed. ACK status itself is HardwareAckStatusnot_requested | accepted | rejected | timeout (hardware_adapter_contract.py).
  • runtime_progress_observed: the system observed runtime movement or state change beyond ACK.
  • landing_observed: landing evidence was observed.
  • completion_claimed: the adapter/verifier claims the bounded action completed. Its scope is qualified by completion_scope (below); it is not a delivery claim by itself.
  • delivery_completion_claimed: the verifier claims delivery completion. This is the generic authority key (it appears in AUTHORITY_RUNTIME_CLAIM_KEYS). See "Delivery Completion Variants" for the scope-qualified names.
  • physical_execution_invoked: a physical-world execution path was invoked. Pinned Literal[False] on read-only, preflight, dispatch-candidate, sim sidecar, and loopback models; it may only become true on an opt-in real serial/hardware path.

Read the full file on GitHub · 148 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. 5d ago First seen · 148 lines · 0 tokens per session scan A aa98655a3e22

Subscribe to this mod's changes

claim-semantics is an agent published in the GitHub repository pome223/missionos (2 stars, last pushed today), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,530 tokens. 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

Other agents, from other repositories

Anti-Vibe Writing Dev

Use when developing anti-vibe-writing, a writing skill for AI agents that rewrites generated drafts into a more classic, polished, human style. Handles skill design, prompt assets, editing heuristics, README cleanup, docs maintenance, and safe local git automation.

weijt606/anti-vibe-writing · 58 tokens

codebase-pattern-finder

You are a specialist at finding code patterns and examples in the codebase. Your job is to locate similar implementations that can serve as templates or inspiration for new work.

humanlayer/humanlayer · 76 tokens

codebase-analyzer

Analyzes codebase implementation details. Call the codebase-analyzer agent when you need to find detailed information about specific components. As always, the more detailed your request prompt, the better! :).

humanlayer/humanlayer · 44 tokens

thoughts-analyzer

The research equivalent of codebase-analyzer. Use this subagenttype when wanting to deep dive on a research topic. Not commonly needed otherwise.

humanlayer/humanlayer · 34 tokens

thoughts-locator

Discovers relevant documents in thoughts/ directory (We use this for all sorts of metadata storage!). This is really only relevant/needed when you're in a reseaching mood and need to figure out if we have random thoughts written down that are relevant to your current research task. Based on the name, I imagine you can…

humanlayer/humanlayer · 86 tokens

web-search-researcher

Do you find yourself desiring information that you don't quite feel well-trained (confident) on? Information that is modern and potentially only discoverable on the web? Use the web-search-researcher subagenttype today to find any and all answers to your questions! It will research deeply to figure out and attempt to…

humanlayer/humanlayer · 114 tokens