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 agentmods add skills/teejayen/arc/open-loopsnpx skills add teejayen/arc --skill open-loopsgit clone --depth 1 https://github.com/teejayen/arcWhat 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 | $0.00043 | $0.00818 |
| Opus 5 | $0.00022 | $0.00409 |
| Sonnet 5 | $0.00009 | $0.00164 |
| Haiku 4.5 | $0.00004 | $0.00082 |
Grade A, and why
open-loops 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 2d 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 — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Open Loops
Track and manage open threads - things waiting for follow-up, hanging items, commitments made.
When to Use
- Something needs follow-up but isn't a full project
- Reviewing what's hanging at session start
- Marking something as done/resolved
- Feeling like things are slipping through cracks
Data Structure
Open loops live in state/session-context.json under open_threads:
{
"open_threads": [
"Thread description - context if needed",
"Another hanging item"
]
}
For richer tracking, can optionally use state/open-loops.json:
{
"loops": [
{
"id": "loop-001",
"description": "Send invoices",
"context": "Price TBD - waiting on confirmation",
"added": "2025-12-28",
"area": "finance",
"status": "waiting",
"stale_after_days": 7
}
]
}
Execution Steps
Quick Status
Read current threads:
cat state/session-context.json | jq '.open_threads'
Report:
- Total count
- Flag any that look stale (been mentioned in multiple sessions)
- Group by apparent area if patterns emerge
Add New Loop
When user mentions something that needs follow-up:
-
Ask for clarification if needed:
- What's the actual action?
- Any deadline or "stale by" date?
- Which area does this relate to?
-
Add to
session-context.json:"open_threads": [ "existing thread", "New thread - brief context" ] -
Confirm what was added
Resolve Loop
When something is done:
- Read current threads
- Remove the resolved item
- Optionally note in session summary that it was closed
- Update the file
Review Loops
Full review of what's hanging:
- Read
state/session-context.json - Cross-reference with recent
state/journal.jsonlentries - Identify:
- Active: Recently mentioned, making progress
- Stale: Not mentioned in 3+ sessions, may be stuck
- Waiting: Blocked on external input
- Maybe obsolete: Context has changed
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.
- 2d ago First seen · 144 lines · 43 tokens per session scan A cd28681acaff
open-loops is a skill published in the GitHub repository teejayen/arc (5 stars, last pushed 7mo ago), licensed MIT. It adds 43 tokens to every session and 818 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
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…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.