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.
npx skills add chipi/agentic-ai-homelab --skill close-arcgit clone --depth 1 https://github.com/chipi/agentic-ai-homelabWrote 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/chipi/agentic-ai-homelab/close-arc)<a href="https://agentmods.dev/skills/chipi/agentic-ai-homelab/close-arc"><img src="https://agentmods.dev/badge/skills/chipi/agentic-ai-homelab/close-arc/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/chipi/agentic-ai-homelab/close-arc"><img src="https://agentmods.dev/badge/skills/chipi/agentic-ai-homelab/close-arc.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 | $0.00088 | $0.00739 |
| Opus 5.5 | $0.00035 | $0.00296 |
| Sonnet 5.5 | $0.00018 | $0.00148 |
| Haiku 4.5 | $0.00009 | $0.00074 |
Grade A, and why
close-arc 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 17d 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 — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.
close-arc
Write the paper trail that lets the next session pick up cold. History is append-only — never edit a past session doc; write a new one that references it.
Steps
- Next number. Highest
NNNNindocs/history/+ 1. FilenameNNNN-<short-slug>.md. - Write the entry, matching the convention:
# NNNN — <arc name>·**Date:**·**Operator:**·**Agent:**·**Outcome:**(one line) · a sibling pointer to the prior history doc.- Body: what the operator pointed you at → what landed → decisions → Open threads (so the next session knows exactly where to resume).
- Nav + index. Add a nav entry under History in
mkdocs.yml(the nav is the exhaustive index). Add adocs/history/README.mdbullet only if that file enumerates every session — some repos keep it curated to the founding docs, in which case leave it. - Decisions. For each non-trivial operational decision this arc, append a
D-NNNNentry todocs/history/0002-decisions.md(grep-able, referenced by id). Structural decisions get an ADR instead (usenew-doc). - Strike NEXT_STEPS — against live state, not memory. In
docs/wip/NEXT_STEPS.md, mark completed items- [x] ~~text~~ — *done note (date)*. Strike, never delete — the strikethrough is the paper trail.- Check every item you strike or carry forward against the system, not a handover or your memory of it. On 2026-10-17, four "open" items were already done when checked: an ACL grant already gone, mini changes already landed, a DGX deploy whose purpose was already live, a symlink superseded by a wrapper. One stale handover was trusted for a day before anyone looked.
- Write the check into the item when you add or touch one: a
check:line with a command whose output answers it. For example:check: ssh dgx-llm-1 'docker exec pyannote md5sum /app/app.py'vs podcast main. Closing it next time is then one command. - Infra items: run the
infra-driftskill; telemetry items:deploy-verifyortelemetry-probe. Strike with the command's output in the done note.
- Version tag. If the repo's tagging gate is met, suggest
git tag v<X>-<arc-slug>at the closing commit — don't tag unprompted. - Validate. Run the
docs-preflightskill.
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.
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.
- 17d ago Changed · +11 lines 2ce03a7f5a69
- 2mo ago First seen · 33 lines · 88 tokens per session scan A 96731daeb0bb
close-arc is a skill published in the GitHub repository chipi/agentic-ai-homelab (3 stars, last pushed today), licensed MIT. It adds 88 tokens to every session and 739 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
agentmail
Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by your inbox assignment.
founder-coach
Use when a founder is the bottleneck, can't delegate, is burning out or is moving from IC to CEO. Covers delegation, energy and calendar audits, blind spots and succession.
todos
Use when the user asks for a shared plan, a task needs at least three substantive execution steps, or a loose TODO is pending. Without an explicit plan request, not for one-shot answers or checks, or one- to two-step work that is not already in the list.
meetings
Context for the Meetings app's data — where a meeting's notes, diagram, transcript-derived tasks and calendar cache live, what the lifecycle states mean, how the app's agents are driven. Load when asked about a meeting's notes or action items, or when touching the meetings app data dir.
subscription-setup
A setup workflow for creating recurring medical-learning subscriptions after a doctor’s profile has been registered.
agent-initialization
Initialize or extend an Agent from a user requirement - write AGENTS.md, set identity metadata, and create, install or import Skills and hook packages (scripts the harness runs on every prompt, before tool calls, or after a task). For an Agent with an in-app workbench, pair with penguin-plugin; for a standalone…