agentmods.dev

optimise-skill

A rubric-tuning tool for improving one written decision rule against examples whose outcomes are already known. A rubric is a set of criteria used to make repeatable judgments.

In plain words
What is it for?
Use it to tune skills that score or classify cases, such as triage or review-severity rubrics.
Why use it?
It helps adjust a recurring judgment process based on evidence, while checking that the revised rubric performs better on held-out examples and passes adversarial checks.

Skill for Claude CodeCodex

14 2mo ago A scan 110 tokens original MIT
View the source file yungbose/upskill
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 skills/yungbose/upskill/optimise-skill
Any agent
npx skills add yungbose/upskill --skill optimise-skill
Clone the repo
git clone --depth 1 https://github.com/yungbose/upskill

Made for: Claude Code, Codex.

Per session 110 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,570 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 $0.00110 $0.03570
Opus 5 $0.00055 $0.01785
Sonnet 5 $0.00022 $0.00714
Haiku 4.5 $0.00011 $0.00357

Measured 2d ago against content hash ff0230a60c80, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

optimise-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.

The scan reads SKILL.md. This mod also ships 53 executable files (scripts/adapter.py, scripts/attribute.py, scripts/claude_code_judge.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

optimise-skill/SKILL.md · 221 lines

How it starts

The opening of the file, as written. The whole thing — 221 lines — stays where its author put it; the contents beside it link to each section on GitHub.

optimise-skill

A decision-policy optimiser. It tunes ONE judge-shaped document (a rubric that makes a recurring, scorable decision) against an outcome-labelled corpus, accepting an edited rubric only when a held-out score strictly improves and adversarial gates pass. It adopts microsoft/SkillOpt (on OPRO foundations) as its optimiser_engine, vendored unedited under vendor/skillopt/; everything skill-specific lives in the rails outside it.

Announce at start: "I'm using optimise-skill to tune <target> against its corpus (autonomy: <preset>)."

It is behavioural-only. Tuning a skill's description: so Claude invokes it is a different job (different artifact, signal, lifecycle) and stays with the official skill-creator. See CHARTER.md for the full design and dev/papers.md for the SkillOpt/OPRO lineage.

Requirements

Run these from the optimise-skill/ directory:

  • Python 3.10+ (tested on 3.13) with PyYAML — pip install -r requirements.txt. PyYAML is the only runtime dependency; the vendored SkillOpt's heavier backends (openai, azure, ray, …) are optional and unused on the default path.
  • Live tuning picks a provider via the manifest's model: field:
    • model: claude (default) — needs the claude CLI + a Claude Max subscription (shells out to claude -p; billed against Max, not the metered API).
    • model: openai — for users without Max: pip install openai and set OPENAI_API_KEY (pay-as-you-go OpenAI billing; Azure OpenAI works similarly via SkillOpt's backend). Note: there is no Anthropic-HTTP-API backend, so using Claude here means the CLI/subscription, not an Anthropic API key.
  • Tests: pip install pytest && python3 -m pytest tests/ — runs with stub judges, no LLM required.

When to use — the durable decision rule

Apply this to any signal, any skill, before making it a target:

Is it a recurring decision made by ONE tunable text document, where each decision is scorable and you can counterfactually imagine the edited document scoring better, with enough volume to hold out?

Yes → an optimise-skill target. No → human-triage (one-off fixes, via a judge-shaped edit-queue) or monitoring (metrics).

Read the full file on GitHub · 221 lines

Files

What ships with it

60 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. 2d ago First seen · 221 lines · 110 tokens per session scan A ff0230a60c80

Subscribe to this mod's changes

optimise-skill is a skill published in the GitHub repository yungbose/upskill (14 stars, last pushed 2mo ago), licensed MIT. It adds 110 tokens to every session and 3,570 once invoked, about $0.0006 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 2026-08-30.

Code reviewData and AIDocumentsLLMagent-skillsai-agentsanthropicclaude-codeskill
Related

Other skills, from other repositories

image-to-code

Elite website image-to-code skill for Codex. For visually important web tasks, it must first generate the design image(s) itself, deeply analyze them, then implement the website to match them as closely as possible. In Codex, it must prefer large, readable, section-specific images instead of tiny compressed boards…

Leonxlnx/taste-skill · 116 tokens

autoreview

Pre-commit/ship code review: Codex default; optional Claude or Pi.

openclaw/clawhub · 20 tokens

convex-billing

Add Stripe billing/payments to the Convex app via @convex-dev/stripe (checkout + webhook + gating).

openclaw/clawhub · 29 tokens

edgeone skill scanner

Scan any agent skill for security risks before you install or use it. Powered by Tencent Zhuque Lab A.I.G (AI-Infra-Guard). 100% local static analysis — no file contents or credentials leave your device. Compatible with CodeBuddy, Cursor, Windsurf, Claude Code, OpenClaw and more. Triggers on: 这个 skill 安全吗, skill 安全扫描…

Tencent/AI-Infra-Guard · 148 tokens

dev-workflow

The complete development workflow for SkillHub contributors including local dev, staging validation, testing, and PR creation. Ensures agents follow the correct sequence of steps.

iflytek/skillhub · 35 tokens

convex-performance-audit

Audits Convex performance for reads, subscriptions, write contention, and function limits. Use for slow features, insights findings, OCC conflicts, or read amplification.

openclaw/clawhub · 38 tokens