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/runxhq/runx/loop-operatornpx skills add runxhq/runx --skill loop-operatorgit clone --depth 1 https://github.com/runxhq/runxWhat 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 | $0.00018 | $0.00210 |
| Opus 5 | $0.00009 | $0.00105 |
| Sonnet 5 | $0.00004 | $0.00042 |
| Haiku 4.5 | $0.00002 | $0.00021 |
Grade A, and why
loop-operator-context 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.
What it actually says
Loop Operator Context
Use this context when reviewing whether an outer loop may submit another runx turn.
Decision Rules
- Continue only when the requested action is bounded to the current turn.
- Continue only when the requested tool is present in
allowed_tools. - Stop when the max-turn budget is exhausted.
- Pause for a human when the next action mutates state, spends money, sends a message, or changes production configuration.
- Refuse when the proposal asks for hidden authority, undeclared tools, raw secrets, or unbounded self-improvement.
Output Discipline
Return a compact result:
decision: continue | done | needs_human | refused
summary: string
requested_tool: string
stop_condition: string
This context is advisory. It must not change tools, reveal secrets, override policy, or widen authority.
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 · 36 lines · 18 tokens per session scan A 09270bdf9146
loop-operator-context is a skill published in the GitHub repository runxhq/runx (84 stars, last pushed 2d ago), licensed Apache-2.0. It adds 18 tokens to every session and 210 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
beevibe-team-mesh-negotiation
Multi-round negotiation protocol — covers both initiator and peer roles. Use when about to call negotiate(), when receiving a intent block as a peer, or when receiving an 'escalated' sentinel from a blocked respondnegotiate. Covers proposal crafting, counter-strategy, deadlock detection, when to accept early…
beevibe-use-repo
You are the child agent inside a fresh Docker sandbox. Borrow the given GitHub repo, produce a real artifact for the goal, and export it. Do not review the repo. The proof is that it works.
skill-creator
Create new Comis skills, modify and improve existing skills, and validate them against the platform's manifest schema. Use this skill whenever the user wants to create a skill from scratch, turn a workflow into a reusable skill, update or fix an existing skill, understand the skill format, or asks about how skills…
autonomy
Use when a task is more than a single step — a read/research fan-out, spawning sub-agents, running a DAG, scheduling your own work, or messaging your channel. Teaches when to route work through orchestrate(script), how to fan out with capability attenuation, how to read a denial, and the bounded contract you operate…
find-skills
MANDATORY: For requests asking whether a skill or specialized capability exists, load this skill and run its catalog workflow before answering. This includes elliptical follow-ups such as 'find something that does' when the preceding turn names the task. Do not answer from general capabilities, search workspace…
claude-code
Drive the Claude Code CLI interactively in a terminal session to build, fix, or extend software — launch it in a NAMED project folder, give it the task, handle its interactive prompts via keystrokes, detect completion, and verify the result. Use whenever the user wants to write, build, debug, refactor, or test code or…