upgrade-skill

upgrade-skill is a command for coding agents from BumgeunSong/skill-up. It costs 28 tokens per session (1,247 once invoked), scanned A, original, MIT.

A test-driven improvement workflow for skills, where TDD means testing expected behavior before making changes. It creates realistic scenarios, checks whether the skill is discoverable, improves it, and tests it again.

In plain words
What is it for?
Evaluating and improving an existing skill through scenario tests, discoverability checks, revisions, and follow-up testing.
Why use it?
It reveals whether a skill activates in the right situations and gives useful results. It also helps identify gaps instead of relying only on a manual review.

Command

Part of the skill-up plugin — 3 skills, 1 command, 2 hooks shipped together

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/bumgeunsong/skill-up/upgrade-skill
Clone the repo
git clone --depth 1 https://github.com/BumgeunSong/skill-up

Or install skill-up, the plugin that ships this one along with the rest of its 3 skills, 1 command, 2 hooks.

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 upgrade-skill

README.md
[![agentmods](https://agentmods.dev/badge/commands/bumgeunsong/skill-up/upgrade-skill.svg)](https://agentmods.dev/commands/bumgeunsong/skill-up/upgrade-skill)
Your own site
<a href="https://agentmods.dev/commands/bumgeunsong/skill-up/upgrade-skill"><img src="https://agentmods.dev/badge/commands/bumgeunsong/skill-up/upgrade-skill.svg" alt="Measured on agentmods" height="20"></a>
Per session 28 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,247 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 $0.00028 $0.01247
Opus 5 $0.00014 $0.00624
Sonnet 5 $0.00006 $0.00249
Haiku 4.5 $0.00003 $0.00125

Measured 4d ago against content hash 5d4a0d5a66c5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

upgrade-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 4d 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/skill-up/commands/upgrade-skill.md · 191 lines

How it starts

The opening of the file, as written. The whole thing — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Upgrade Skill

Systematically improve a skill through test-driven evaluation and enhancement.

REQUIRED BACKGROUND: First invoke skill-up:writing-skills skill for TDD methodology applied to skills. See testing-skills-with-subagents.md in that skill's directory for pressure scenario templates.

Quick Reference

Step Action
1 Find and read the target skill
2 Create pressure scenario tests (RED)
3 Run baseline test without skill context
4 Evaluate discoverability (CSO check)
5 Identify gaps and improvements
6 Apply improvements (GREEN)
7 Re-test to verify (REFACTOR)
8 Update upgraded: true in stats

Workflow

1. Locate Skill

Skill locations (check in order):
~/.claude/skills/{skill-name}/SKILL.md
~/.claude/plugins/**/skills/{skill-name}/SKILL.md
.claude/skills/{skill-name}/SKILL.md

If skill not found, report and exit.

2. Create Pressure Scenario Test

Generate 2-3 realistic scenarios that would trigger this skill:

Good scenario template:

SCENARIO: [Realistic situation where skill should apply]

Context:
- [Specific constraint 1]
- [Specific constraint 2]
- [Time/resource pressure]

Task: [What agent must do]

Success criteria:
- [ ] Agent recognizes skill applies
- [ ] Agent follows skill correctly
- [ ] Agent produces expected outcome

Pressure types to combine (pick 3+):

  • Time pressure
  • Sunk cost
  • Authority override
  • Exhaustion
  • Pragmatic shortcuts

3. Run Baseline Test (RED Phase)

Spawn a subagent WITHOUT skill context:

  • Give scenario only
  • Document what agent does naturally
  • Capture rationalizations verbatim

4. Evaluate Discoverability (CSO Check)

Check skill's search optimization:

Check Pass/Fail
Description starts with "Use when..."
Description has specific triggers
Keywords match search terms
Name is verb-first, descriptive
No workflow summary in description

Read the full file on GitHub · 191 lines

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. 4d ago First seen · 191 lines · 28 tokens per session scan A 5d4a0d5a66c5

Subscribe to this mod's changes

upgrade-skill is a command published in the GitHub repository BumgeunSong/skill-up (11 stars, last pushed 7mo ago), licensed MIT. It adds 28 tokens to every session and 1,247 once invoked, about $0.0001 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.