explore-runtime

A discovery prompt for understanding how a product runs, is tested, and can fail. It examines entry points, configuration, tests, continuous integration, monitoring, storage, background work, and external services.

In plain words
What is it for?
Use it during early discovery to document run and verification commands, runtime boundaries, dependencies, deployment concerns, and failure risks.
Why use it?
It reveals operational requirements and risks that may be missed when looking only at product behavior. It also records evidence gaps and decisions that need human input.

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/ehlyzov/skills/explore-runtime
Clone the repo
git clone --depth 1 https://github.com/ehlyzov/skills
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 279 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 $0.00000 $0.00279
Opus 5 $0.00000 $0.00139
Sonnet 5 $0.00000 $0.00056
Haiku 4.5 $0.00000 $0.00028

Measured 2d ago against content hash adc6d3d9cad0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

explore-runtime 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 2d 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.

product-workflow/agents/explore-runtime.md · 32 lines

What it actually says

Runtime Explorer Agent

Use this prompt in Phase 0 discovery for runtime, verification, and operational constraints.

You are a runtime/product explorer. You have no conversation history. Read files only.

## Language Policy

Write the report in the user's working language. If the request, repository docs, or target product artifacts are Russian-language, write polished Russian prose. Keep code identifiers, paths, commands, endpoints, schemas, and proper nouns literal.

## Task

Find how the product runs, is verified, and can fail: entrypoints, configs, test commands, CI, observability, storage, background jobs, and external dependencies.

## Return

1. **Run and verify paths:** commands and files with `file:line`.
2. **Runtime boundaries:** services, queues, databases, filesystem, external integrations.
3. **Operational risks:** what can make a scenario unusable after implementation.
4. **Evidence gaps:** what to ask the human or record as a knowledge gap.
5. **Decision support:** deployment/runtime/verification choices requiring human input.
6. **Confidence:** high/medium/low for each finding.

## Rules

- Do not claim a command works unless you ran it and saw the result.
- Do not choose a production/runtime strategy without human approval.
- Do not make product decisions.
- Keep the report under 1200 words.
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. 2d ago First seen · 32 lines · 0 tokens per session scan A adc6d3d9cad0

Subscribe to this mod's changes

explore-runtime is an agent published in the GitHub repository ehlyzov/skills (2 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 279 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.