optimize-skill

A command for reviewing and improving an agent skill's instructions. It checks how clearly the skill is triggered, how much text it uses, and whether its outputs work as intended.

In plain words
What is it for?
Use it to optimize a named skill, apply focused instruction edits, move supporting material into references, and report remaining evaluation gaps.
Why use it?
It helps find unclear or wasteful instructions that may cause an agent to use a skill at the wrong time or misunderstand its task.

Command for Cursor

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.

agentmods
npx agentmods add commands/rhyanvargas/agentic-development-starter-kit/optimize-skill
Clone the repo
git clone --depth 1 https://github.com/rhyanvargas/agentic-development-starter-kit

Made for: Cursor.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 208 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00000 $0.00208
Opus 5 $0.00000 $0.00104
Sonnet 5 $0.00000 $0.00042
Haiku 4.5 $0.00000 $0.00021

Measured 2d ago against content hash 491587189df8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

optimize-skill 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 2d 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.

.cursor/commands/optimize-skill.md · 23 lines

What it actually says

/optimize-skill

Optimize an Agent Skill for trigger accuracy, clarity, and token cost.

Skill

Read and follow skills/skill-optimizer (or .agents/skills/skill-optimizer in adopter apps).

Usage

/optimize-skill
/optimize-skill skills/spec-driven-workflow
/optimize-skill .agents/skills/my-company-skill

Behavior

  1. Locate the target skill directory (ask if unclear).
  2. Run the skill-optimizer gates (validate, description, lean body, progressive disclosure, trigger + output evals).
  3. Apply lean edits; move kit-meta/rationale into references/ with hard when-to-load conditions.
  4. Report what changed and any remaining eval gaps. For a full with/without output pass, hand off to /run-skill-evals (that command must end with Recommended next actions from skill-optimizerreferences/eval-loop.md).
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. 2d ago First seen · 23 lines · 0 tokens per session scan A 491587189df8

Subscribe to this mod's changes

optimize-skill is a command published in the GitHub repository rhyanvargas/agentic-development-starter-kit (2 stars, last pushed 9d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 208 tokens. 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.