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 erstanai/erstan-agent-tools-beta --skill erstan-run-operatorgit clone --depth 1 https://github.com/erstanai/erstan-agent-tools-betaWrote 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/erstanai/erstan-agent-tools-beta/erstan-run-operator)<a href="https://agentmods.dev/skills/erstanai/erstan-agent-tools-beta/erstan-run-operator"><img src="https://agentmods.dev/badge/skills/erstanai/erstan-agent-tools-beta/erstan-run-operator/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/erstanai/erstan-agent-tools-beta/erstan-run-operator"><img src="https://agentmods.dev/badge/skills/erstanai/erstan-agent-tools-beta/erstan-run-operator.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 | $0.00803 |
| Opus 5 | $0.00032 | $0.00402 |
| Sonnet 5 | $0.00013 | $0.00161 |
| Haiku 4.5 | $0.00006 | $0.00080 |
Grade A, and why
erstan-run-operator 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 8d 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Erstan run operator
Operate one run through its complete durable lifecycle without guessing state or duplicating side effects.
Reference
Read run lifecycle before launching or continuing a run.
Workflow
- Confirm the intended Agent, lane, input, attachments, and material external
effects. Use
list_agentsto resolve a published Agent and its public lane contract. Do not launch a run from a vague name or guessed input schema. - Require an explicit request to launch. Supply a stable
idempotencyKeywhen a retry, network failure, or upstream event could otherwise create a duplicate run. - Call
run_agentonce and preserve the returned run ID and the Erstan connection that launched it. - Poll
get_runat a reasonable interval. Honor server retry guidance and do not restart a merely slow run. - When status is
waiting, inspect top-levelinterruptDispositionand the currentpendingInteraction:- Continue only when
interruptDisposition === "actionable"and a currentpendingInteractionis present. Its ownstatusfield is not the actionability discriminator. - For user input, obtain the user's answer unless it is already explicit,
then call
reply_to_runwith the exact currentinteractionId. - For approval, show the bounded proposed action and obtain the user's
explicit approve or reject decision before
decide_run_approval. - If the interaction is retained, claimed, or changed, keep polling or re-read; never reuse an older interaction ID.
- Continue only when
- Stop polling at
completed,failed, orcancelled. Report the durable status, final response or error, and any unresolved external effect. - To send the next message of the same conversation after a run reaches a
terminal status, call
continue_runwith the run ID and the message (attachments optional,idempotencyKeyrecommended). Always resume pollingget_runwith the run ID returned by the call: a completed chat run usually continues under the same ID, while failed/cancelled chat runs and post-run-continuation agents fork a new run ID on the same conversation thread. A waiting run takesreply_to_runordecide_run_approvalinstead, andrun_not_continuablemeans start a newrun_agentrun. - When mechanism matters, page
get_run_tracechronologically through every cursor. Pair tool calls and results by call and occurrence identity rather than tool name alone.
What ships with it
2 files 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.
- 8d ago First seen · 67 lines · 64 tokens per session scan A 248318a54115
erstan-run-operator is a skill published in the GitHub repository erstanai/erstan-agent-tools-beta (0 stars, last pushed 10d ago), licensed Apache-2.0. It adds 64 tokens to every session and 803 once invoked, about $0.0003 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
foundry-config-setup
Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.
deploy-docker-compose
Run the Omnigent server as a Docker compose stack (server + Postgres) on any Docker host — your laptop, a VPS, EC2 by hand, or as the base layer of any container-platform deploy. Invoke when the user wants to build the image, bring up the compose stack, debug the stack on a host they already have, or extend the stack…
haiku
When writing a haiku for this bot, follow these conventions.
azure-mgmt-botservice-dotnet
Azure Resource Manager SDK for Bot Service in .NET. Management plane operations for creating and managing Azure Bot resources, channels (Teams, DirectLine, Slack), and connection settings. Triggers: "Bot Service", "BotResource", "Azure Bot", "DirectLine channel", "Teams channel", "bot management .NET", "create bot".
fastapi-router-py
Create FastAPI routers with CRUD operations, authentication dependencies, and proper response models. Use when building REST API endpoints, creating new routes, implementing CRUD operations, or adding authenticated endpoints in FastAPI applications.
dogfood
Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.