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/close)<a href="https://agentmods.dev/skills/digital-stoic-org/agent-skills/close"><img src="https://agentmods.dev/badge/skills/digital-stoic-org/agent-skills/close/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/close"><img src="https://agentmods.dev/badge/skills/digital-stoic-org/agent-skills/close.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 | $0.00064 | $0.03522 |
| Opus 5.5 | $0.00026 | $0.01409 |
| Sonnet 5.5 | $0.00013 | $0.00704 |
| Haiku 4.5 | $0.00006 | $0.00352 |
Grade A, and why
close 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 — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Close
CLOSE is a reading. The parent reads the child's Delta and reformulates it in its own terms — it never re-executes the child's plan, never re-applies a DELIVERABLE, and never writes to the child's file while the child is still WORKing. Exactly one turn: the Delta crosses to the direct parent and stops there, never to the grandparent.
Format reference (cite by path, don't reopen it here): ${CLAUDE_PLUGIN_ROOT}/references/ring-file.md. Carrier rules the vehicle already followed: ${CLAUDE_PLUGIN_ROOT}/references/carrier.md.
Common rules (all ring skills)
- Disk commands go through absolute paths and
/usr/bin/find,/usr/bin/grep, orpython3 ${CLAUDE_PLUGIN_ROOT}/scripts/ring.py(everyring.pybelow means this) — barefind/grepare shimmed and fail silently. - No git verb of any kind. No
.bakfiles. - A question to the human is posed in plain text, once, with A/B/C choices — never an interactive question tool.
Arguments
| Argument | Value | Required |
|---|---|---|
| slug | the ring to close | yes |
--park |
park instead of close (status: parked, no Delta reading) |
no |
--root |
absolute root(s) for the closing sweep, repeatable | no — default: root: line(s) from ${CLAUDE_PROJECT_DIR}/.claude/ring.local.md if present, else realpath of the ring directory's parent |
--opened |
ISO instant, overrides the sweep's cutoff | no — default: ring.py resolve-opened; if that finds nothing, the sweep is skipped and it is stated in the output |
--verbose |
full inventory, full review list, and the exact commands run, instead of the default summary | no |
Preconditions — refuse before reading anything
| Vehicle | Precondition | Else |
|---|---|---|
session |
last signal received from the agent is a REPORT — it has stopped writing | refuse: the pen is still with the vehicle |
resumed / inline (already promoted) |
the child's own carrier: equals this conversation's token, is —, or is absent (v0.1.0 file) — token rule: ring-file.md §2 carrier row |
refuse: another conversation holds the child's pen → /open --resume <slug> first |
subagent |
the sub-agent's final report is present in this conversation | refuse: nothing to read |
| any | /close runs in the parent's carrier — closing is a read the parent does on its own file |
refuse |
| any | the parent's file, if it carries a carrier: header, names this conversation's carrier token |
refuse: another carrier holds the parent's pen |
arc (parent: root, closing itself) |
its own carrier: equals this conversation's token, is —, or is absent (v0.1.0 file) |
refuse: another conversation holds the arc's pen → /open --resume <slug> first |
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 · +9 lines 8ed75cd086ef
- 6d ago First seen · 123 lines · 64 tokens per session scan A c739494c7498
close is a skill published in the GitHub repository digital-stoic-org/agent-skills (20 stars, last pushed 2d ago), licensed MIT. It adds 64 tokens to every session and 3,522 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…