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-agent-buildergit 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-agent-builder)<a href="https://agentmods.dev/skills/erstanai/erstan-agent-tools-beta/erstan-agent-builder"><img src="https://agentmods.dev/badge/skills/erstanai/erstan-agent-tools-beta/erstan-agent-builder.svg" alt="Measured on agentmods" 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 | $0.00063 | $0.00778 |
| Opus 5 | $0.00032 | $0.00389 |
| Sonnet 5 | $0.00013 | $0.00156 |
| Haiku 4.5 | $0.00006 | $0.00078 |
Grade A, and why
erstan-agent-builder 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 7d 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Erstan Agent builder
Build against the live Erstan authoring contract. Treat creation, update, testing, and publication as separate lifecycle actions.
Reference
Read lifecycle and graph rules before creating or changing a graph. The live guide, node catalog, and tool schemas remain authoritative when that reference differs.
Workflow
- Establish the intended Agent behavior, owner team, inputs, outputs, tool and Skill needs, and whether the request authorizes only a proposal, a saved draft, a live preview, or publication.
- Call
get_agent_builder_guide, thenget_agent_node_catalogwith the detail needed for every proposed node. Calllist_agent_toolsandlist_agent_skillsbefore choosing bindings. Never invent a node field, action type, tool, Skill ID, connection ID, or policy value. - For an existing Agent, call
get_agentand retain its complete graph,currentVersion, published state, and opaquerevision. Preserve unrelated metadata, nodes, edges, positions, and bindings. - Assemble the complete candidate graph. Use canonical node types and an
explicit top-level
data.toolPolicyon every tool-capable AI node. Pin every capability required for deterministic or write-capable work. - Run
validate_agentagainst the candidate or saved draft before a write when the live schema supports that path. Resolve errors within the requested scope. Report unrelated pre-existing errors instead of silently expanding the change. - Use
create_agentfor a new draft orupdate_agentwith the latestrevisionfor an existing draft. Re-read or use the returned revision after every successful mutation. - Validate the persisted draft. Treat
valid: falseas a failed validation even when the MCP call itself succeeded. - Call
test_agentonly when the user explicitly authorizes a live preview. Preview uses real tools and may create external effects. - Call
publish_agentonly after an explicit publication request, successful validation, and a final check that the exact current revision is intended. Never describe a draft as published unless the tool confirms publication.
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.
- 7d ago First seen · 64 lines · 63 tokens per session scan A 7d33356d17c3
erstan-agent-builder is a skill published in the GitHub repository erstanai/erstan-agent-tools-beta (0 stars, last pushed 9d ago), licensed Apache-2.0. It adds 63 tokens to every session and 778 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.
haiku
When writing a haiku for this bot, follow these conventions.
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…
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.