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.
git clone --depth 1 https://github.com/runnithan/claudex-setupWrote 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.
[](https://agentmods.dev/commands/runnithan/claudex-setup/changelog-claude)<a href="https://agentmods.dev/commands/runnithan/claudex-setup/changelog-claude"><img src="https://agentmods.dev/badge/commands/runnithan/claudex-setup/changelog-claude/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.
<a href="https://agentmods.dev/commands/runnithan/claudex-setup/changelog-claude"><img src="https://agentmods.dev/badge/commands/runnithan/claudex-setup/changelog-claude.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00050 | $0.03141 |
| Opus 5.5 | $0.00020 | $0.01256 |
| Sonnet 5.5 | $0.00010 | $0.00628 |
| Haiku 4.5 | $0.00005 | $0.00314 |
Grade A, and why
changelog-claude scanned grade A with 1 finding 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 5d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
`curl`, never WebFetch: WebFetch answers through a small model, and the raw file is the evidence How it starts
The opening of the file, as written. The whole thing — 190 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/changelog-claude: keep the global Claude Code setup current with the changelog
Claude Code ships several times a week, and the global setup (the dotfiles repo behind
~/.claude) only catches up when the owner happens to read a release. This command reads every
release since the last run, decides for each entry whether it changes what the setup should look
like, and applies the changes the owner approves. Scope is the global setup: a tracked
project's .claude/ is /optimise's job, and mining lessons is /extract-lessons'.
Sibling of /top-tips: same hub, same ledger discipline, same per-item walkthrough. Runs from
any directory.
0. Inputs and locations
$ARGUMENTS:--since <version>overrides the ledger watermark for this run (the ledger still advances at the end);--dry-runtriages and reports, edits nothing, leaves the ledger alone.- Hub (the claudex-setup checkout):
git rev-parse --show-toplevelwhen that directory holdsprojects/README.md; otherwise two directories above the target ofreadlink -f ~/.claude/commands/changelog-claude.md. If neither resolves, stop and ask. - Ledger:
<hub>/projects/changelog-claude-ledger.md. Frontmatter:watermark(the newest release already triaged),platform_notes_since(ISO date),windows_claude_home(the other machine's~/.claude, empty when there is none). Missing file: create it from the §5 template with the watermark at the tenth most recent release, and say so in the report. - Config root:
CLAUDE_ROOT="$(dirname "$(readlink -f ~/.claude/CLAUDE.md)")", the dotfiles repo whenCLAUDE.mdis a symlink into one, else~/.claudeitself. Files that matter:CLAUDE.md,settings.json,windows/settings.json(the other OS's variant, if present),settings.local.json,keybindings.json,skills/(ignoregsd-*),hooks/. - Versions:
claude --versionagainst the newest## x.y.zheading in the changelog. Whenwindows_claude_homeis set, also read the Windows install's version from WSL withcd /mnt/c && cmd.exe /c claude --version(cmd.exe refuses a WSL working directory): the two are separate installs that update separately, so the WSL version says nothing about Windows. $SCRATCHbelow is the session scratchpad directory named in your system prompt.
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.
- 5d ago Changed · +9 lines c5e649363a5d
- 22d ago Changed · +7 lines 8ac5fd1685fd
- 1mo ago First seen · 174 lines · 50 tokens per session scan A e81336ffee1f
changelog-claude is a command published in the GitHub repository runnithan/claudex-setup (1 stars, last pushed 5d ago), licensed MIT. It adds 50 tokens to every session and 3,141 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-13.
Other commands, from other repositories
changelog
Generate a changelog entry from git commits since the last tag using conventional commit format.
land-and-deploy
Merge PR, wait for CI, verify deploy, run canary — the complete landing pipeline.
release-notes
Generate release notes in multiple formats from git commits.
ship
Comprehensive pre-deployment verification to ensure release readiness.
ship-csk
DoD gate + commit proposal (waits for approval).
ship
Deliver completed work with validation and documentation.