sci-brain: Skill for Claude Code

.claude/skills/bump-version/SKILL.md

bump-version is a skill for Claude Code from QuantumBFS/sci-brain. It costs 75 tokens per session (1,430 once invoked), scanned A, original, MIT.

A release workflow for changing the version of the sci-brain plugin and publishing that release. A version identifies which plugin build users are installing.

In plain words
What is it for?
It bumps the three version records, creates a commit and annotated Git tag, pushes them, and creates a GitHub release.
Why use it?
It keeps the version listed in the marketplace, plugin manifest, and package file consistent so validation and publishing do not fail.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions .claude-plugin; mentions Claude Code.

This is QuantumBFS/sci-brain's own configuration. It tells Claude Code how to work on sci-brain itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything sci-brain configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python3 scripts/validate_skills.py.

Part of the sci-brain plugin — 17 skills shipped together

Reuse

Borrowing it

Nothing to install: this file belongs to QuantumBFS/sci-brain. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/QuantumBFS/sci-brain/main/.claude/skills/bump-version/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/QuantumBFS/sci-brain

Made for: Claude Code.

Or install sci-brain, the plugin that ships this one along with the rest of its 17 skills.

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 bump-version

README.md
[![agentmods](https://agentmods.dev/badge/skills/quantumbfs/sci-brain/bump-version/github.svg)](https://agentmods.dev/skills/quantumbfs/sci-brain/bump-version)
Your own site
<a href="https://agentmods.dev/skills/quantumbfs/sci-brain/bump-version"><img src="https://agentmods.dev/badge/skills/quantumbfs/sci-brain/bump-version/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for bump-version

Your own site · 80×15
<a href="https://agentmods.dev/skills/quantumbfs/sci-brain/bump-version"><img src="https://agentmods.dev/badge/skills/quantumbfs/sci-brain/bump-version.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 75 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,430 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00075 $0.01430
Opus 5.5 $0.00030 $0.00572
Sonnet 5.5 $0.00015 $0.00286
Haiku 4.5 $0.00007 $0.00143

Measured 1mo ago against content hash 9861f54531c6, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

bump-version 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 1mo 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/skills/bump-version/SKILL.md · 103 lines

How it starts

The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Bump Version

Overview

sci-brain is a Claude Code plugin. Its version is declared in three JSON files that must stay in lockstep — the marketplace reads it from marketplace.json, plugin tooling reads it from plugin.json, and npm/pi read it from package.json. CI (scripts/validate_skills.py) fails if they diverge, and .github/workflows/publish.yml refuses to publish unless the pushed tag equals v + package.json's version. A release is: bump all three files → commit → annotated tag → push → GitHub release.

Version Source of Truth

File Path to version
.claude-plugin/plugin.json .version
.claude-plugin/marketplace.json .plugins[0].version
package.json .version

All three MUST match. If they diverge, CI's version-sync check fails, the npm publish tag gate rejects the release, and the marketplace and the installed plugin report different versions.

When to Use

  • "tag a version", "bump version", "cut a release", "release v0.x"
  • After a batch of merged PRs that warrants a new release
  • Before announcing changes that downstream users need to pull

Do NOT use for:

  • Pre-release / draft tags (the workflow below assumes a real release)
  • Hotfix to an old branch — this skill assumes you tag from main

Bump Type → New Version

Read current version from .claude-plugin/plugin.json, then:

  • patch (X.Y.Z → X.Y.Z+1): bugfix, doc tweak, no behavior change
  • minor (X.Y.Z → X.Y+1.0): new skill, new feature, additive change
  • major (X.Y.Z → X+1.0.0): breaking change to a skill's contract / removed skill

If the user didn't specify, ask which bump type (patch/minor/major) before continuing.

Procedure

  1. Read current version from .claude-plugin/plugin.json and confirm marketplace.json and package.json match. If they already disagree, stop and flag it — don't paper over the drift.

  2. Edit all three files to the new version. Use the Edit tool, not sed, so the diff is reviewable.

Read the full file on GitHub · 103 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. 1mo ago First seen · 103 lines · 75 tokens per session scan A 9861f54531c6

Subscribe to this mod's changes

bump-version is a skill published in the GitHub repository QuantumBFS/sci-brain (101 stars, last pushed 23d ago), licensed MIT. It adds 75 tokens to every session and 1,430 once invoked, about $0.0003 per session on Opus 5.5. 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.