pneuma-skills: Command for Claude Code

.claude/commands/bump.md

bump is a command for Claude Code from pandazki/pneuma-skills. It costs 0 tokens per session (2,217 once invoked), scanned A, original, MIT.

A release command that synchronises the main branch, writes a changelog, updates top-level documentation, increases the software version, and pushes the changes.

In plain words
What is it for?
Use it to review commits, choose a Semantic Versioning increase, update release notes and documentation, and publish the version.
Why use it?
It groups the repeated steps of preparing a software release into one guided process.

Command for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions CLAUDE.md; mentions AGENTS.md; mentions Codex.

This is pandazki/pneuma-skills's own configuration. It tells Claude Code how to work on pneuma-skills 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 pneuma-skills configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is bash scripts/deploy-player.sh.

Reuse

Borrowing it

Nothing to install: this file belongs to pandazki/pneuma-skills. 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/pandazki/pneuma-skills/main/.claude/commands/bump.md
Clone the repo
git clone --depth 1 https://github.com/pandazki/pneuma-skills

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 bump

README.md
[![agentmods](https://agentmods.dev/badge/commands/pandazki/pneuma-skills/bump/github.svg)](https://agentmods.dev/commands/pandazki/pneuma-skills/bump)
Your own site
<a href="https://agentmods.dev/commands/pandazki/pneuma-skills/bump"><img src="https://agentmods.dev/badge/commands/pandazki/pneuma-skills/bump/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

Your own site · 80×15
<a href="https://agentmods.dev/commands/pandazki/pneuma-skills/bump"><img src="https://agentmods.dev/badge/commands/pandazki/pneuma-skills/bump.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
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 2,217 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.
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 $0.00000 $0.02217
Opus 5 $0.00000 $0.01108
Sonnet 5 $0.00000 $0.00443
Haiku 4.5 $0.00000 $0.00222

Measured 4d ago against content hash a82b0db88892, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

bump 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.

.claude/commands/bump.md · 196 lines

How it starts

The opening of the file, as written. The whole thing — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/bump — Version Bump & Release

Perform a full version bump: sync main, write changelog, refresh top-level docs, bump version, and push.

Steps

1. Sync main

git checkout main && git pull origin main

If the working tree is dirty, stop and ask the user to resolve it first.

2. Determine version bump

Review all commits since the last version tag to decide the bump level per Semantic Versioning:

  • patch (x.y.Z): bug fixes, minor improvements, doc updates
  • minor (x.Y.0): new features, new modes, new API endpoints, new viewer capabilities
  • major (X.0.0): breaking changes to contracts, CLI interface, or manifest format

Read the current version from package.json. Compute the new version. If unsure, ask the user.

3. Write CHANGELOG entry

Read CHANGELOG.md and the git log since the last version bump commit. Write a new version section at the top following the existing format:

## [X.Y.Z] - YYYY-MM-DD

### Added
- ...

### Fixed
- ...

### Improved
- ...

Rules:

  • Group changes by category (Added / Fixed / Improved / Changed / Removed)
  • Each bullet should be a concise, user-facing description — not a commit message copy
  • Bold the feature name, then describe what it does
  • Omit categories with no entries
  • Do NOT include chore/CI/version-bump commits

4. Refresh top-level docs

Review README.md and AGENTS.md against the current codebase state. Fix any contradictions, outdated info, or missing features. This is a holistic review, not just appending — trim stale content, update tables, fix version numbers.

AGENTS.md is the single source of agent instructions; CLAUDE.md is a one-line @AGENTS.md import — never write content into it.

Specifically check:

  • AGENTS.md **Version:** line → update to new version
  • AGENTS.md **Builtin Modes:** list → matches core/mode-loader.ts registrations
  • AGENTS.md tech stack table → matches package.json dependencies
  • AGENTS.md project structure tree → reflects any new/moved directories
  • AGENTS.md server API reference → includes any new endpoints
  • .claude/rules/*.md → add any newly discovered gotchas to the matching domain rule, remove resolved ones
  • README.md mode table → matches manifest descriptions
  • README.md CLI help section → matches actual CLI output
  • README.md feature list / roadmap → reflects current state

Read the full file on GitHub · 196 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 Changed · +5 lines a82b0db88892
  2. 11d ago First seen · 191 lines · 0 tokens per session scan A 0e4c43778f98

Subscribe to this mod's changes

bump is a command published in the GitHub repository pandazki/pneuma-skills (160 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,217 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 2026-08-30.