erstan-skill-optimizer

erstan-skill-optimizer is a skill for Claude Code, Codex from erstanai/erstan-agent-tools-beta. It costs 68 tokens per session (879 once invoked), scanned A, original, Apache-2.0.

Instructions for improving an existing Erstan Skill while preserving its business rules and complete package. Optimization means proposing targeted improvements based on how the Skill has run.

In plain words
What is it for?
Reviewing run evidence, clarifying reusable procedures, adding deterministic actions, and improving recovery and reliability.
Why use it?
They help reduce unnecessary context and tool use while avoiding unverified changes or accidental live updates.

Skill for Claude CodeCodex

Written for Claude Code and Codex: shipped in a Claude Code plugin, but also agents/openai.yaml present.

Part of the erstan-beta plugin — 7 skills, 1 MCP server shipped together

Good fit Reviewing run evidence, clarifying reusable procedures, adding deterministic actions, and improving recovery and reliability.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/erstanai/erstan-agent-tools-beta/erstan-skill-optimizer
Install

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.

Any agent
npx skills add erstanai/erstan-agent-tools-beta --skill erstan-skill-optimizer
Clone the repo
git clone --depth 1 https://github.com/erstanai/erstan-agent-tools-beta

Made for: Claude Code, Codex.

Or install erstan-beta, the plugin that ships this one along with the rest of its 7 skills, 1 MCP server.

Wrote 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.

agentmods badge for erstan-skill-optimizer

README.md
[![agentmods](https://agentmods.dev/badge/skills/erstanai/erstan-agent-tools-beta/erstan-skill-optimizer.svg)](https://agentmods.dev/skills/erstanai/erstan-agent-tools-beta/erstan-skill-optimizer)
Your own site
<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>
Per session 68 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 879 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 7d ago against content hash 003f9a985040, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

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.

plugins/erstan-beta/skills/erstan-skill-optimizer/SKILL.md · 77 lines

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

  1. Establish the requested stage: analysis, local candidate, server validation, live package update, or publication. Do not combine stages.
  2. Call list_agent_skills when discovery is required, then get_agent_skill for the exact workspace Skill ID. It cannot retrieve a system:<key> Skill. Record the immutable package name, current version, lifecycle status, complete packageJson, files, and action declarations.
  3. 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.
  4. 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.
  5. Separate Skill findings from Agent routing/policy, platform persistence/context/export, and connector/provider defects. Do not encode platform workarounds as universal domain instructions.
  6. 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.
  7. Call validate_agent_skill with the complete candidate. Compare the returned normalized packageJson with the submitted package and stop on a dropped/coerced file, path, action, runtime, language, or side-effect field.
  8. Stop at the validated proposal unless a workspace update is explicitly authorized. Re-read immediately before an authorized update and use the latest currentVersion as expectedVersion.
  9. A published Skill has no isolated draft fork: update_agent_skill changes its live package immediately. Require explicit live-change authorization; a request to optimize, preview, validate, or create a proposal is not enough.
  10. Call publish_agent_skill only after separate publication approval for an exact validated draft version.

Read the full file on GitHub · 77 lines

Files

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.

Changes

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.

  1. 7d ago First seen · 77 lines · 68 tokens per session scan A 003f9a985040

Subscribe to this mod's changes

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.

Related

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.

microsoft/agent-framework · 65 tokens

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…

omnigent-ai/omnigent · 84 tokens

haiku

When writing a haiku for this bot, follow these conventions.

agno-agi/agno · 0 tokens

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".

microsoft/skills · 78 tokens

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.

microsoft/skills · 46 tokens

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.

callstack/agent-device · 55 tokens