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-optimizergit 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-optimizer)<a href="https://agentmods.dev/skills/erstanai/erstan-agent-tools-beta/erstan-skill-optimizer"><img src="https://agentmods.dev/badge/skills/erstanai/erstan-agent-tools-beta/erstan-skill-optimizer.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 | $0.00068 | $0.00879 |
| Opus 5 | $0.00034 | $0.00439 |
| Sonnet 5 | $0.00014 | $0.00176 |
| Haiku 4.5 | $0.00007 | $0.00088 |
Grade A, and why
erstan-skill-optimizer 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Erstan Skill optimizer
Produce a complete, reviewable Skill package candidate that improves reusable behavior while preserving business rules, related files, action metadata, and lifecycle safety. Optimization is proposal-only unless the user explicitly authorizes a live workspace update or later publication.
Required protocol
Read the Skill optimization protocol before proposing or applying a package change.
Workflow
- Establish the requested stage: analysis, local candidate, server validation, live package update, or publication. Do not combine stages.
- Call
list_agent_skillswhen discovery is required, thenget_agent_skillfor the exact workspace Skill ID. It cannot retrieve asystem:<key>Skill. Record the immutable package name, current version, lifecycle status, completepackageJson, files, and action declarations. - Correlate run evidence by Agent ID, executed Agent version, and bound Skill ID. When an export contains the exact executed Skill prompt but not a Skill version, compare content cautiously and record that historical package identity remains unverified.
- Inspect
SKILL.md, every related text file, and every executable action as one package. Identify repeated instructions, irrelevant always-loaded context, ambiguous tool arguments, missing batching/recovery/reconciliation, and deterministic work better owned by a sandbox action. - Separate Skill findings from Agent routing/policy, platform persistence/context/export, and connector/provider defects. Do not encode platform workarounds as universal domain instructions.
- Build a complete candidate package and structured diff. Tie every changed file or action field to evidence, an expected outcome, and a regression check. Preserve unmodified files, action identities, runtime/language, entry paths, timeouts, and side-effect declarations.
- Call
validate_agent_skillwith the complete candidate. Compare the returned normalizedpackageJsonwith the submitted package and stop on a dropped/coerced file, path, action, runtime, language, or side-effect field. - Stop at the validated proposal unless a workspace update is explicitly
authorized. Re-read immediately before an authorized update and use the
latest
currentVersionasexpectedVersion. - A published Skill has no isolated draft fork:
update_agent_skillchanges its live package immediately. Require explicit live-change authorization; a request to optimize, preview, validate, or create a proposal is not enough. - Call
publish_agent_skillonly after separate publication approval for an exact validated draft version.
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 · 77 lines · 68 tokens per session scan A 003f9a985040
erstan-skill-optimizer is a skill published in the GitHub repository erstanai/erstan-agent-tools-beta (0 stars, last pushed 8d ago), licensed Apache-2.0. It adds 68 tokens to every session and 879 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.