ork-explore

ork-explore is a skill for Claude Code, Codex from yonatangross/orchestkit. It costs 63 tokens per session (302 once invoked), scanned A, original, MIT.

A read-only workflow for mapping an unfamiliar codebase, feature, architecture, data flow, or operational process using evidence from files.

In plain words
What is it for?
It helps locate entry points, dependencies, tests, monitoring, risks, and the next investigation step.
Why use it?
It helps developers understand where behaviour starts, which components are involved, and what remains uncertain before making changes.

Skill for Claude CodeCodex

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 skills/yonatangross/orchestkit/ork-explore
Any agent
npx skills add yonatangross/orchestkit --skill ork-explore
Clone the repo
git clone --depth 1 https://github.com/yonatangross/orchestkit

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 ork-explore

README.md
[![agentmods](https://agentmods.dev/badge/skills/yonatangross/orchestkit/ork-explore.svg)](https://agentmods.dev/skills/yonatangross/orchestkit/ork-explore)
Your own site
<a href="https://agentmods.dev/skills/yonatangross/orchestkit/ork-explore"><img src="https://agentmods.dev/badge/skills/yonatangross/orchestkit/ork-explore.svg" alt="Measured on agentmods" height="20"></a>
Per session 63 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 302 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 $0.00063 $0.00302
Opus 5 $0.00032 $0.00151
Sonnet 5 $0.00013 $0.00060
Haiku 4.5 $0.00006 $0.00030

Measured 5d ago against content hash 2ec5100cacf0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ork-explore 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.

plugins/ork-codex/skills/ork-explore/SKILL.md · 15 lines

What it actually says

Ork Explore

Stay read-only. Start with the task boundary, repository instructions, entry points, and the smallest searches that can prove the execution path. Cite files and symbols for every material claim; distinguish confirmed behavior from inference.

When the path runs through a third-party library or framework, read its current documentation with the context7 MCP server: call resolve-library-id to get the library ID, then query-docs. Those are the only two tools it exposes. A recalled API detail you could not confirm belongs in the unknowns list, not in the map.

Explore in one context by default. Fan out only for three or more independent questions such as structure, data flow, tests, and deployment. Use a flat fan-out, make each assignment bounded and read-only, and ask for concise evidence rather than proposed fixes. Prefer ork_explorer when installed; otherwise use Codex's built-in explorer.

Return a compact map: entry points, important components and dependencies, tests/observability, risks or unknowns, and the next smallest investigation. Do not change files or turn the map into an implementation plan unless asked.

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. 5d ago First seen · 15 lines · 63 tokens per session scan A 2ec5100cacf0

Subscribe to this mod's changes

ork-explore is a skill published in the GitHub repository yonatangross/orchestkit (225 stars, last pushed yesterday), licensed MIT. It adds 63 tokens to every session and 302 once invoked, about $0.0003 per session on Opus 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 2026-08-30.