runtime-observation

runtime-observation is a skill for Claude Code from prime-radiant-inc/greenfield. It costs 42 tokens per session (4,303 once invoked), scanned A, original, Apache-2.0.

A method for learning what executable software actually does by running it and recording its outputs. It treats observed results as evidence rather than relying on guesses or interpretations.

In plain words
What is it for?
Use it to examine command-line tools, web applications, APIs, services, libraries, software development kits, and browser-based interfaces.
Why use it?
It prevents incorrect claims about behavior and makes findings reproducible by documenting the input, output, errors, and environment.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: positional $N argument.

Part of the greenfield plugin — 22 skills, 2 commands, 2 agents shipped together

Good fit Use it to examine command-line tools, web applications, APIs, services, libraries, software development kits, and browser-based interfaces.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/prime-radiant-inc/greenfield/runtime-observation
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 prime-radiant-inc/greenfield --skill runtime-observation
Clone the repo
git clone --depth 1 https://github.com/prime-radiant-inc/greenfield

Made for: Claude Code.

Or install greenfield, the plugin that ships this one along with the rest of its 22 skills, 2 commands, 2 agents.

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 runtime-observation

README.md
[![agentmods](https://agentmods.dev/badge/skills/prime-radiant-inc/greenfield/runtime-observation/github.svg)](https://agentmods.dev/skills/prime-radiant-inc/greenfield/runtime-observation)
Your own site
<a href="https://agentmods.dev/skills/prime-radiant-inc/greenfield/runtime-observation"><img src="https://agentmods.dev/badge/skills/prime-radiant-inc/greenfield/runtime-observation/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 runtime-observation

Your own site · 80×15
<a href="https://agentmods.dev/skills/prime-radiant-inc/greenfield/runtime-observation"><img src="https://agentmods.dev/badge/skills/prime-radiant-inc/greenfield/runtime-observation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 42 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,303 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 2 findings, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Prompt Injection · line 226
    Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.
    Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
  • medium Tool Misuse · line 297
    Tool defaults are unsafe or overly permissive (e.g. disabled TLS verification, no authentication, world-writable permissions). Unsafe defaults widen the attack surface.
    Fix: Override unsafe defaults with secure settings (verify=True, auth required, restrictive permissions). Review and harden all tool configurations.
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 $0.00042 $0.04303
Opus 5 $0.00021 $0.02152
Sonnet 5 $0.00008 $0.00861
Haiku 4.5 $0.00004 $0.00430

Measured 9d ago against content hash f0a407384d6d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

runtime-observation scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -s -D- \
skills/runtime-observation/SKILL.md · 413 lines

How it starts

The opening of the file, as written. The whole thing — 413 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Runtime Observation Methodology

Runtime observation produces ground truth. When you execute a command and record the output, that observation is an empirical fact -- not an interpretation, not an inference, not a guess. This skill defines how every runtime observation agent operates.

The Principle

Run it. Record it. Cite it.

You never guess what a target does. You run it and document what happens. Every observation is a witnessed fact: this input produced this output in this environment at this time.

When Runtime Observation Applies

Runtime observation applies to any target that can be executed inside a container:

Target Type Observation Method Primary Agent
CLI tools Execute commands, capture stdout/stderr/exit codes cli-explorer
Web applications HTTP requests, browser automation, form interaction web-ui-explorer
APIs and services HTTP/gRPC/WebSocket requests, response analysis behavior-observer
Libraries and SDKs Probe scripts that import and exercise the library behavior-observer
GUI applications Browser automation for web-based GUIs web-ui-explorer

Targets that cannot be executed (static documentation, binary files without a runtime) are handled by other intelligence sources. Runtime observation is additive -- it enhances and corroborates intelligence from all other modes.

Source Origin

All runtime observation output is RAW. Running the target and recording its behavior produces artifacts that require sanitization before reaching the implementer. Even though the observations describe external behavior (not implementation internals), recording the target's responses creates a derivation chain.

Targets that cannot be executed in a sandbox (or where executing them has side effects the user declines to accept) should skip this mode.

  • Output location: workspace/raw/runtime/
  • Never write runtime observations to workspace/output/ or workspace/public/.
  • The origin label does not reduce the value of the observations. It is a provenance marker that controls downstream processing.

Read the full file on GitHub · 413 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. 9d ago First seen · 413 lines · 42 tokens per session scan A f0a407384d6d

Subscribe to this mod's changes

runtime-observation is a skill published in the GitHub repository prime-radiant-inc/greenfield (273 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 42 tokens to every session and 4,303 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.