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/VersoXBT/claude-initial-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/versoxbt/claude-initial-setup/checkpoint)<a href="https://agentmods.dev/commands/versoxbt/claude-initial-setup/checkpoint"><img src="https://agentmods.dev/badge/commands/versoxbt/claude-initial-setup/checkpoint/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/versoxbt/claude-initial-setup/checkpoint"><img src="https://agentmods.dev/badge/commands/versoxbt/claude-initial-setup/checkpoint.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 | $0.00008 | $0.00510 |
| Opus 5.5 | $0.00003 | $0.00204 |
| Sonnet 5.5 | $0.00002 | $0.00102 |
| Haiku 4.5 | $0.00001 | $0.00051 |
Grade A, and why
checkpoint 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.
How it starts
The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Checkpoint
Review current changes and create a well-structured git commit to save progress.
Steps
-
Check the current state:
- Run
git statusto see all modified, staged, and untracked files. - Run
git diffto review unstaged changes. - Run
git diff --stagedto review already-staged changes.
- Run
-
Review changes for commit readiness:
- Verify no debugging code (console.log, print statements, debugger).
- Verify no hardcoded secrets (API keys, passwords, tokens).
- Verify no temporary files or build artifacts are included.
- Check that
.gitignorecovers files that should not be committed.
-
Group changes logically:
- If changes span multiple concerns (feature + refactor + fix), consider splitting into multiple commits.
- Each commit should represent a single logical change.
- Stage only the files related to one logical change at a time.
-
Stage relevant files:
- Use
git add <specific-files>rather thangit add .to avoid committing unintended files. - Double-check staged files with
git diff --staged. - Exclude any files that contain sensitive data.
- Use
-
Write a descriptive commit message:
- Use conventional commit format:
<type>: <description>. - Types: feat, fix, refactor, docs, test, chore, perf, ci.
- Keep the subject line under 72 characters.
- Add a body for complex changes explaining the "why" not the "what".
- Use conventional commit format:
-
Create the commit:
- Run
git commitwith the prepared message. - Verify the commit was created successfully with
git log -1.
- Run
-
If there are remaining changes for a separate concern:
- Repeat steps 4-6 for the next logical group.
If Pre-Commit Hooks Fail
- Read the hook output to understand what failed.
- Fix the reported issues (lint errors, type errors, test failures).
- Stage the fixes and create a new commit — do not amend the previous commit.
If Sensitive Files Are Accidentally Staged
- Unstage them immediately with
git reset HEAD <file>. - Add the file pattern to
.gitignore. - If already committed, remove from history and rotate any exposed secrets.
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.
- 1mo ago First seen · 60 lines · 8 tokens per session scan A b9251497b7d1
checkpoint is a command published in the GitHub repository VersoXBT/claude-initial-setup (4 stars, last pushed 5mo ago), licensed MIT. It adds 8 tokens to every session and 510 once invoked, about $0.0000 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 2026-08-31.
Other commands, from other repositories
block-no-verify
Set up PreToolUse hook to block --no-verify and other git bypass flags in Claude Code projects.
commit
A command that checks staged Git changes and creates a commit from them.
wrap-up
End-of-session handoff — summarize, verify, and stage so you can review and commit.
work-commit-push-pr
Pointer: Claude Code ships a native /commit-push-pr that owns the commit + push + PR macro. This command adds the foundation's pre-flight gate and convention sources on top — it does not re-implement the macro.
work-commit
Prepare and perform a clean commit following conventions.
work-flow-feature
Complete workflow for developing a new feature, from exploration to merge.