open

open is a skill for Claude Code from digital-stoic-org/agent-skills. It costs 74 tokens per session (4,004 once invoked), scanned A, original, MIT.

A skill for opening a child work item in a ring, where each ring is a separate problem to settle. It creates a focused brief and assigns the work to an inline process, subagent, or session.

In plain words
What is it for?
Use it to split a larger agent task into a clearly scoped sub-problem and start the chosen worker or session.
Why use it?
It keeps delegated work focused and records how the child work should be carried out. It also sets rules for paths, questions, and file ownership before work starts.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions subagents.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the ring plugin — 4 skills shipped together

Good fit Use it to split a larger agent task into a clearly scoped sub-problem and start the chosen worker or session.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add digital-stoic-org/agent-skills
Claude Code
/plugin install ring

Made for: Claude Code.

Or install ring, the plugin that ships this one along with the rest of its 4 skills.

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 open

README.md
[![agentmods](https://agentmods.dev/badge/skills/digital-stoic-org/agent-skills/open/github.svg)](https://agentmods.dev/skills/digital-stoic-org/agent-skills/open)
Your own site
<a href="https://agentmods.dev/skills/digital-stoic-org/agent-skills/open"><img src="https://agentmods.dev/badge/skills/digital-stoic-org/agent-skills/open/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 open

Your own site · 80×15
<a href="https://agentmods.dev/skills/digital-stoic-org/agent-skills/open"><img src="https://agentmods.dev/badge/skills/digital-stoic-org/agent-skills/open.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 74 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,004 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00074 $0.04004
Opus 5.5 $0.00030 $0.01602
Sonnet 5.5 $0.00015 $0.00801
Haiku 4.5 $0.00007 $0.00400

Measured 5d ago against content hash adb2d9ddfe70, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-30, from the pricing page.

Security

Grade A, and why

open 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.

ring/skills/open/SKILL.md · 145 lines

How it starts

The opening of the file, as written. The whole thing — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Open

OPEN descends: it composes one Brief, targeted at one child problem, and starts its vehicle. Format and fields: ${CLAUDE_PLUGIN_ROOT}/references/ring-file.md (cite by path, do not paraphrase it here). Vehicle rules the child must follow: ${CLAUDE_PLUGIN_ROOT}/references/carrier.md.

Rules. Absolute paths only. Disk commands go through /usr/bin/find, /usr/bin/grep, or python3 ${CLAUDE_PLUGIN_ROOT}/scripts/ring.py — the bare commands are shimmed and fail silently. No git verb, ever. No .bak files. A question to Mat is plain text, asked once, choices A/B/C when it's a choice — never an interactive question tool.

Arguments

Argument Value Required Default
free text the problem to settle yes —
--parent slug or root yes current ring in the conversation, else ask
--vehicle inline | subagent | session no inline — cheapest: no file, no agent, human carries it; natural-language intent parses first ("with a sub agent" → subagent)
--escalade human | parent | irreversible no irreversible for session, parent for subagent
--agent name of a team agent if session —
--dir absolute rings folder no chain: parent's file folder if already known in this conversation → dir: in ${CLAUDE_PROJECT_DIR}/.claude/ring.local.md → cwd (realpath); never asked
--create absolute prefix ending /, repeatable if the ring will create files derived from the deliverable path named in the request
--writes absolute path — existing file or prefix ending /, repeatable no —
--resume slug of a parked or active ring no —
--verbose flag no off — default output is one or two plain-language sentences

Inference. Cost scales with how far the Brief travels, not per field.

  • inline — the Brief stays in the human's own conversation, correctable next turn: infer --vehicle, --dir, --create, closure freely, echo the result in the output, ask nothing.
  • subagent / session — the Brief leaves for an agent with no channel back: infer the same fields, but confirm closure alone, one line ("ok" suffices) — never re-ask the others.
  • session without --agent is still always a question (V6): nothing infers an agent name.
  • Whatever is genuinely underivable after inference (typically --agent, or closure with no candidate anywhere in the request) goes into the one plain-text message at step 2.

Read the full file on GitHub · 145 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 Changed · +24 lines · +15 tokens per session adb2d9ddfe70
  2. 6d ago First seen · 121 lines · 59 tokens per session scan A 84e163d6f5b8

Subscribe to this mod's changes

open is a skill published in the GitHub repository digital-stoic-org/agent-skills (20 stars, last pushed 2d ago), licensed MIT. It adds 74 tokens to every session and 4,004 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-09-24.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens