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.
/plugin marketplace add digital-stoic-org/agent-skills/plugin install ringWrote 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.
[](https://agentmods.dev/skills/digital-stoic-org/agent-skills/open)<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.
<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>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.
| Model | Per session | Once 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 |
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.
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,closurefreely, 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 confirmclosurealone, one line ("ok" suffices) — never re-ask the others.sessionwithout--agentis still always a question (V6): nothing infers an agent name.- Whatever is genuinely underivable after inference (typically
--agent, orclosurewith no candidate anywhere in the request) goes into the one plain-text message at step 2.
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.
- 5d ago Changed · +24 lines · +15 tokens per session adb2d9ddfe70
- 6d ago First seen · 121 lines · 59 tokens per session scan A 84e163d6f5b8
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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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.
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…
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…
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…