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-skill-managergit 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-skill-manager)<a href="https://agentmods.dev/skills/erstanai/erstan-agent-tools-beta/erstan-skill-manager"><img src="https://agentmods.dev/badge/skills/erstanai/erstan-agent-tools-beta/erstan-skill-manager/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-skill-manager"><img src="https://agentmods.dev/badge/skills/erstanai/erstan-agent-tools-beta/erstan-skill-manager.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 | $0.00067 | $0.00835 |
| Opus 5 | $0.00034 | $0.00417 |
| Sonnet 5 | $0.00013 | $0.00167 |
| Haiku 4.5 | $0.00007 | $0.00084 |
Grade A, and why
erstan-skill-manager 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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Erstan Skill manager
Manage complete Skill packages with explicit lifecycle decisions and optimistic version guards. Do not assume that an edit to a published Skill is isolated from its live package.
Reference
Read package and lifecycle rules before a create, update, or publication.
Workflow
- Establish whether the request is local review, server validation, draft creation, update, or publication. Do not combine these stages implicitly.
- Build or inspect the complete package: required
SKILL.md, every related text file by relative path, and declared sandbox action metadata. Before submission, reject absolute, traversal, or reserved paths; case-insensitive path or action-key collisions; unsupported runtime or language values; and anysideEffectsvalue other than exactlynoneorexternal. - Call
validate_agent_skillbefore persistence. Retain the submitted package and compare it with returnedpackageJson, including entry path, every file path/content/language, and every action key, runtime, entry path, language, side-effects declaration, and timeout. Stop and report any dropped file or action, rewritten unsafe path, collapsed collision, or coerced runtime, language, orsideEffectsvalue. Metadata synchronization may be expected, but security-relevant structural changes require a corrected package and a new validation. Validation does not save or execute the package. - For a new Skill, call
create_agent_skillonce and treat the result as a draft. The tool has no idempotency key. After a timeout or lost response, search workspace Skills withlist_agent_skills, inspect candidates withget_agent_skill, and reconcile the immutablepackageNameand complete package before any retry. Stop when the result is ambiguous. - For an existing workspace Skill, call
get_agent_skillimmediately before editing and inspect its lifecycle status. Use this tool only with workspace Skill IDs; it cannot readsystem:<key>refs. Preserve files and actions outside the requested change and pass the returned current version asexpectedVersiontoupdate_agent_skill.- If the Skill is a draft, update it within the authorized scope.
- If it is published, explain that
update_agent_skillchanges the live package immediately; there is no isolated draft fork. Require explicit authorization for that live change. If the user requested a draft, preview, or review-only change, do not update it.
- If a version conflict occurs, re-read once, reconcile non-overlapping changes, revalidate the complete merged package, and retry once. Stop on overlap or another conflict.
- Call
publish_agent_skillonly after explicit user approval, successful validation, and a fresh current version. Publication is separate from create and update. - Report the Skill ID, version, lifecycle status, validation results, and any action still requiring human approval.
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 · 70 lines · 67 tokens per session scan A 2faeb7e2d35c
erstan-skill-manager 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 67 tokens to every session and 835 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.