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.
npx agentmods add commands/16wells/claude-project-setup/checkpointgit clone --depth 1 https://github.com/16wells/claude-project-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/16wells/claude-project-setup/checkpoint)<a href="https://agentmods.dev/commands/16wells/claude-project-setup/checkpoint"><img src="https://agentmods.dev/badge/commands/16wells/claude-project-setup/checkpoint.svg" alt="Measured on agentmods" 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 | $0.00025 | $0.00609 |
| Opus 5 | $0.00013 | $0.00304 |
| Sonnet 5 | $0.00005 | $0.00122 |
| Haiku 4.5 | $0.00003 | $0.00061 |
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 3d 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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
The user just asked for a checkpoint. The trigger-based discipline isn't enough right now — they want a full pass. Run it cleanly.
Step 1 — Refresh 01-context/state.md
Update every section that has changed since the last write. In particular:
- Active Sub-Project — confirm the active slug; update if focus has shifted.
- In-Progress Work — what's the next concrete step right now? Which surface? Which file?
- Awaiting Human Decision — what's actually blocking? Restate the question and the options on the table.
- Most Recent Commit — pull the latest SHA and subject from git; note what it landed and what it intentionally didn't.
- External Systems State — for technical projects, refresh the deployed-services / cloud-resources / secrets / scheduled-jobs / production-data tables to reflect reality.
- Open Risks / Known Mid-Recovery Items — any half-done work that hasn't landed yet.
- Resume Notes for the Next Agent — one or two bullets, the shortest "do this next" possible.
- Last updated — ISO timestamp + which surface you're on.
Keep the file under ~200 lines. If something doesn't fit there, it belongs in activity-log.md, the decisions log, or a deliverable file — move it.
Step 2 — Append to 01-context/activity-log.md
One concise entry covering everything since the last activity-log entry. Format per the template at the top of that file. Keep it tight — this file gets read at session start.
Step 3 — Route any new decisions or insights
- If anything settled or opened a new question that isn't yet in
01-context/decisions-log.md→ add it. - If you noticed a pattern, gotcha, or quirk that isn't yet in
01-context/insights.md→ add it. - Don't duplicate. If a decision is logged in decisions-log, just reference it from activity-log; don't restate it.
Step 4 — Stage, commit, push
git add -A
git commit -m "checkpoint: <short topic>"
git push
Use the user-provided topic from $ARGUMENTS if given; otherwise summarize the activity-log entry in 6–10 words.
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.
- 3d ago First seen · 52 lines · 25 tokens per session scan A 0c721824e6da
checkpoint is a command published in the GitHub repository 16wells/claude-project-setup (2 stars, last pushed 5d ago), licensed MIT. It adds 25 tokens to every session and 609 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.
Other commands, from other repositories
commit
Analyze Git changes and generate a conventional commit message following the Commitizen format.
commit
I'll analyze your changes and create a meaningful commit message.
undo
I'll help you rollback the last destructive operation performed by CCPlugins commands.
commit-message
Draft a Conventional Commit message from the staged git diff.
commit-pr
Create a git commit and open a pull request (creates a new branch first if on main/master).
ci-guard
Trigger the Commit & Branch Guard workflow on demand.