action-feasibility-engine

action-feasibility-engine is an agent for Claude Code from pome223/missionos. It costs 0 tokens per session (2,586 once invoked), scanned A, original, Apache-2.0.

A deterministic check for whether a proposed action remains feasible under several hazards. It is a maintainer contract for PX4 recovery proposals, not a physically calibrated simulation.

In plain words
What is it for?
Use it to evaluate and revalidate proposed PX4 recovery actions against hazard state and policy or model rules.
Why use it?
It keeps feasibility checks separate from approval, execution, progress, and completion, while recording uncertainty and whether observations are current.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md).

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/action-feasibility-engine
Clone the repo
git clone --depth 1 https://github.com/pome223/missionos

Made for: Claude Code.

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 action-feasibility-engine

README.md
[![agentmods](https://agentmods.dev/badge/agents/pome223/missionos/action-feasibility-engine.svg)](https://agentmods.dev/agents/pome223/missionos/action-feasibility-engine)
Your own site
<a href="https://agentmods.dev/agents/pome223/missionos/action-feasibility-engine"><img src="https://agentmods.dev/badge/agents/pome223/missionos/action-feasibility-engine.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 2,586 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 $0.02586
Opus 5 $0.00000 $0.01293
Sonnet 5 $0.00000 $0.00517
Haiku 4.5 $0.00000 $0.00259

Measured today against content hash 41e428fa3213, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

action-feasibility-engine 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 today.

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/action-feasibility-engine.md · 246 lines

How it starts

The opening of the file, as written. The whole thing — 246 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Action Feasibility Engine contract

This contract describes the deterministic multi-hazard verification boundary used by PX4 recovery proposals. It is a maintainer implementation contract, not a claim that the current simulation models are physically calibrated.

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

The engine only constrains a proposed action. It never creates approval, dispatch authority, physical execution, progress, or completion.

Core contract and migration

missionos-core publishes the backend-neutral v1 API:

  • missionos_core_hazard_state.v1
  • missionos_core_action_candidate.v1
  • missionos_core_action_feasibility.v1
  • missionos_core_action_revalidation.v1

Core owns observed-versus-derived fact semantics, source references and freshness, opaque observation cursors, policy/model binding, uncertainty, tri-state aggregation, and authority-free revalidation artifacts. A cursor's payload is intentionally opaque. A backend adapter must implement a named comparison contract and return before, equal, after, or incomparable; Core never assumes that a field named sample_index is globally ordered.

Geometry, terrain, energy, and vehicle-performance calculations implement the FeasibilityVerifierExtension protocol. An extension returns measurements, assumptions, and blocked/unverified reasons. It cannot upgrade missing Core evidence or create approval, dispatch, execution, progress, or completion.

The existing runtime v1 schemas below remain readable during migration. They are not aliases for the Core schemas, and conversion must be explicit in a backend adapter. Schema versions are additive within one major version. Removing or changing field meaning requires a new major schema, a converter, and corpus coverage for both the last supported input and the new output. Unknown major versions fail closed as unverified.

The #100 corpus now runs through the Core conformance runner while retaining the existing backend calculation as its adapter. That proves the common invariants are executable; it does not yet prove the production recovery path uses Core. Production migration and removal of the shadow path belong to #102.

Read the full file on GitHub · 246 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. today Changed · +20 lines 41e428fa3213
  2. 5d ago First seen · 226 lines · 0 tokens per session scan A a10cec19d677

Subscribe to this mod's changes

action-feasibility-engine 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 2,586 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

network-architect

Designs enterprise or multi-site network architecture from requirements, using existing network skills for focused routing, validation, automation, and troubleshooting detail.

affaan-m/ECC · 31 tokens

network-config-reviewer

Reviews router and switch configurations for security, correctness, stale references, risky change-window commands, and missing operational guardrails.

affaan-m/ECC · 29 tokens

network-troubleshooter

Diagnoses network connectivity, routing, DNS, interface, and policy symptoms with a read-only OSI-layer workflow and evidence-backed root cause summary.

affaan-m/ECC · 34 tokens

agent_types

This document describes how the unified three-layer Device Agent architecture is implemented across different platforms. While the core framework (State, Processor, Command layers) remains consistent, each platform implements specialized agents optimized for their native control mechanisms and hierarchies.…

microsoft/UFO · 0 tokens

server_client_architecture

Device agents in UFO are partitioned into server and client components, separating high-level orchestration from low-level execution. This architecture enables safe, scalable, and flexible task execution across heterogeneous devices through the Agent Interaction Protocol (AIP).

microsoft/UFO · 0 tokens

antenna-engineer

Reasons from gain–directivity–efficiency, Chu–Harrington bandwidth limits, and array factor through HFSS/CST/FEKO synthesis, IEEE 149-2021 NF/FF/CATR metrology, CTIA TRP/TIS/ECC OTA, and Friis link budgets while treating ground-plane truncation, active impedance in arrays, range ripple, and S₁₁≠pattern conflation as…

K-Dense-AI/scientific-agents · 97 tokens