DQIII8: Skill for Claude Code

.claude/skills/checkpoint/SKILL.md

checkpoint is a skill for Claude Code from senda-labs/DQIII8. It costs 29 tokens per session (696 once invoked), scanned B, original, MIT.

A checkpoint tool that verifies code quality, saves selected changes in a Git commit, and records the commit in a checkpoint log.

In plain words
What is it for?
Use it to create, verify, or list checkpoints and compare the current project with a saved checkpoint.
Why use it?
It creates a named restore point before risky changes or after a substantial block of work.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

This is senda-labs/DQIII8's own configuration. It tells Claude Code how to work on DQIII8 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 DQIII8 configures →

Part of the dqiii8 plugin — 22 skills, 14 commands, 17 agents shipped together

Reuse

Borrowing it

Nothing to install: this file belongs to senda-labs/DQIII8. 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/senda-labs/DQIII8/main/.claude/skills/checkpoint/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/senda-labs/DQIII8

Made for: Claude Code.

Or install dqiii8, the plugin that ships this one along with the rest of its 22 skills, 14 commands, 17 agents.

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 checkpoint

README.md
[![agentmods](https://agentmods.dev/badge/skills/senda-labs/dqiii8/checkpoint/github.svg)](https://agentmods.dev/skills/senda-labs/dqiii8/checkpoint)
Your own site
<a href="https://agentmods.dev/skills/senda-labs/dqiii8/checkpoint"><img src="https://agentmods.dev/badge/skills/senda-labs/dqiii8/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.

agentmods 80×15 button for checkpoint

Your own site · 80×15
<a href="https://agentmods.dev/skills/senda-labs/dqiii8/checkpoint"><img src="https://agentmods.dev/badge/skills/senda-labs/dqiii8/checkpoint.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 29 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 696 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00029 $0.00696
Opus 5 $0.00015 $0.00348
Sonnet 5 $0.00006 $0.00139
Haiku 4.5 $0.00003 $0.00070

Measured 10d ago against content hash 640033a34ae7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade B, and why

checkpoint scanned grade B 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 10d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

tail -20 .claude/checkpoints.log
.claude/skills/checkpoint/SKILL.md · 93 lines

How it starts

The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/checkpoint — Save and Verify Session State

Save or verify a named checkpoint using git + .claude/checkpoints.log.

Usage

/checkpoint create [name]    — Save current state
/checkpoint verify [name]    — Compare current state to checkpoint
/checkpoint list             — Show recent checkpoints

Create Checkpoint

When create [name] is called:

  1. Run /quality-gate quick check (black + pytest -x -q)
  2. Create a git commit with the checkpoint name:
    git add -p   # stage only intended changes
    git commit -m "checkpoint: [name]"
    
  3. Append to .claude/checkpoints.log (create it first if absent, otherwise verify/list fail on a fresh install):
    [ -f .claude/checkpoints.log ] || touch .claude/checkpoints.log
    echo "$(date +%Y-%m-%d-%H:%M) | [name] | $(git rev-parse --short HEAD)" >> .claude/checkpoints.log
    
  4. Report: CHECKPOINT CREATED: [name] @ [hash]

Verify Checkpoint

When verify [name] is called:

  1. Read the checkpoint hash from .claude/checkpoints.log
    [ -f .claude/checkpoints.log ] || touch .claude/checkpoints.log
    
  2. Compare current state:
    git diff [hash]..HEAD --stat
    git diff [hash]..HEAD -- '*.py' | head -60
    
  3. Report:
    CHECKPOINT COMPARISON: [name]
    ==============================
    Commits since: N
    Files changed: X added / Y modified / Z deleted
    Build: PASS / FAIL
    Tests: +N passed / -N failed
    

List Checkpoints

[ -f .claude/checkpoints.log ] || touch .claude/checkpoints.log
tail -20 .claude/checkpoints.log

Typical Workflow

/checkpoint create "before-p2a"
  → implement 5 skills + 3 commands
/checkpoint verify "before-p2a"
  → confirm only expected files changed
/checkpoint create "p2a-complete"

Arguments

  • create [name]: name must be [a-z0-9-_]+, max 40 chars
  • verify [name]: name from log, exact match
  • list: no args — shows last 20 entries

Notes

  • Checkpoints are git commits — they survive context compaction
  • Use before risky multi-file changes (P2, P3 batches)
  • If you compact the context afterwards, create the checkpoint first

Read the full file on GitHub · 93 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. 10d ago First seen · 93 lines · 29 tokens per session scan B 640033a34ae7

Subscribe to this mod's changes

checkpoint is a skill published in the GitHub repository senda-labs/DQIII8 (11 stars, last pushed 21d ago), licensed MIT. It adds 29 tokens to every session and 696 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.