update-skill

update-skill is a command for Claude Code from ncssm-robotics/ftc-claude. It costs 10 tokens per session (921 once invoked), scanned A, original, MIT.

A command that creates changelog entries from the changes made to an FTC skill’s files.

In plain words
What is it for?
Run /update-skill with a skill name to record added, changed, fixed, or removed items in its Unreleased changelog section.
Why use it?
It turns a code diff into categorized release notes without changing the skill’s version number.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

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/ncssm-robotics/ftc-claude/update-skill
Clone the repo
git clone --depth 1 https://github.com/ncssm-robotics/ftc-claude

Made for: Claude Code.

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 update-skill

README.md
[![agentmods](https://agentmods.dev/badge/commands/ncssm-robotics/ftc-claude/update-skill.svg)](https://agentmods.dev/commands/ncssm-robotics/ftc-claude/update-skill)
Your own site
<a href="https://agentmods.dev/commands/ncssm-robotics/ftc-claude/update-skill"><img src="https://agentmods.dev/badge/commands/ncssm-robotics/ftc-claude/update-skill.svg" alt="Measured on agentmods" height="20"></a>
Per session 10 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 921 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 5.1 $0.00010 $0.00921
Opus 5 $0.00005 $0.00461
Sonnet 5 $0.00002 $0.00184
Haiku 4.5 $0.00001 $0.00092

Measured 6d ago against content hash 55e4230abb6f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

update-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 6d 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.

.claude/commands/update-skill.md · 140 lines

How it starts

The opening of the file, as written. The whole thing — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Update Skill Command

Analyzes git changes and generates properly formatted changelog entries for a skill.

Important: This command only creates changelog entries. Version bumping is handled automatically by the release process when the PR is merged.

Usage

/update-skill <skill-name>

Arguments:

  • skill-name: Name of the skill to update (must exist in plugins/)

Examples

/update-skill pinpoint
/update-skill pedro-pathing
/update-skill decode

Process

When this command is invoked:

  1. Validate the skill exists

    • Check plugins/<skill-name>/ directory exists
    • Check CHANGELOG.md exists in the plugin directory
    • Check ## [Unreleased] section exists in CHANGELOG.md
  2. Analyze git changes

    • Run git status plugins/<skill-name>/ to see modified files
    • Run git diff plugins/<skill-name>/ to see specific changes
    • Identify new files, modified files, and deleted files
  3. Categorize changes into changelog categories:

    • Added - New files, new features, new sections
    • Changed - Modified behavior, updated documentation
    • Fixed - Bug fixes, corrections
    • Removed - Deleted features, removed sections
    • Deprecated - Features marked for removal
    • Security - Security-related fixes
  4. Generate proposed entries

    • Create concise, descriptive entries for each change
    • Use imperative mood ("Add X" not "Added X")
    • Group related changes together
  5. Present to user for confirmation

    • Show proposed entries
    • Allow user to edit, add, or remove entries
    • Confirm before writing
  6. Update CHANGELOG.md

    • Append entries to ## [Unreleased] section
    • Preserve existing unreleased entries
    • Maintain proper formatting

Output Example

Analyzing changes for skill: pinpoint

Git status shows:
  modified: skills/pinpoint/SKILL.md (47 lines changed)
  new file: skills/pinpoint/scripts/calibrate.py

Proposed changelog entries:

### Added
- Calibration script for automated pod offset calculation

### Changed
- Updated Quick Start section with calibration workflow
- Added troubleshooting section for IMU drift issues

Confirm these entries? [Y/n/edit]

Read the full file on GitHub · 140 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. 6d ago First seen · 140 lines · 10 tokens per session scan A 55e4230abb6f

Subscribe to this mod's changes

update-skill is a command published in the GitHub repository ncssm-robotics/ftc-claude (4 stars, last pushed 7mo ago), licensed MIT. It adds 10 tokens to every session and 921 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 2026-08-31.