checkpoint

checkpoint is a skill for Claude Code from hamzaPixl/pixl-ai. It costs 47 tokens per session (1,317 once invoked), scanned B, original, MIT.

A save-and-restore system for a coding session, including Git state, unfinished changes, tasks, decisions, and remaining work.

In plain words
What is it for?
Use it to save a named checkpoint, list saved checkpoints, or restore the latest or a selected checkpoint.
Why use it?
It prevents losing track of work when switching tasks, pausing a session, or returning later.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the pixl-crew plugin — 93 skills, 14 agents, 6 hooks shipped together

Good fit Use it to save a named checkpoint, list saved checkpoints, or restore the latest or a selected checkpoint.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/hamzapixl/pixl-ai/checkpoint
Install

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.

Any agent
npx skills add hamzaPixl/pixl-ai --skill checkpoint
Clone the repo
git clone --depth 1 https://github.com/hamzaPixl/pixl-ai

Made for: Claude Code.

Or install pixl-crew, the plugin that ships this one along with the rest of its 93 skills, 14 agents, 6 hooks.

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/hamzapixl/pixl-ai/checkpoint/github.svg)](https://agentmods.dev/skills/hamzapixl/pixl-ai/checkpoint)
Your own site
<a href="https://agentmods.dev/skills/hamzapixl/pixl-ai/checkpoint"><img src="https://agentmods.dev/badge/skills/hamzapixl/pixl-ai/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/hamzapixl/pixl-ai/checkpoint"><img src="https://agentmods.dev/badge/skills/hamzapixl/pixl-ai/checkpoint.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 47 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,317 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 $0.00047 $0.01317
Opus 5 $0.00023 $0.00659
Sonnet 5 $0.00009 $0.00263
Haiku 4.5 $0.00005 $0.00132

Measured 9d ago against content hash 86ea0bb7a6fb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, 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 9d 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.

DECISIONS=$(tail -20 .claude/memory/decisions.jsonl)
packages/crew/skills/checkpoint/SKILL.md · 174 lines

How it starts

The opening of the file, as written. The whole thing — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Overview

Unified state capture that saves everything needed to resume work exactly where you left off. Combines git state, task progress, and session decisions into a single checkpoint.

How this differs from other skills:

  • /task-persist — saves task list only. This skill saves full working context (git + tasks + decisions).
  • /session-wrap — captures session summary for handoff. This skill saves restorable state, not just a narrative.
  • /strategic-compact — manages context window. This skill manages cross-session state.

Mode Detection

/checkpoint save            → save checkpoint with auto-generated name
/checkpoint save billing    → save checkpoint named "billing"
/checkpoint restore         → restore most recent checkpoint
/checkpoint restore billing → restore checkpoint named "billing"
/checkpoint list            → list all saved checkpoints

Save Mode

Step 1: Capture Git State

BRANCH=$(git branch --show-current)
COMMIT=$(git rev-parse --short HEAD)
STATUS=$(git status --porcelain)
STASH_NEEDED=$([ -n "$STATUS" ] && echo "true" || echo "false")

If there are uncommitted changes:

git stash push -m "checkpoint: ${NAME:-auto}-$(date +%s)"
STASH_REF=$(git stash list | head -1 | cut -d: -f1)

Step 2: Capture Task State

# From task-state.json if it exists
TASK_STATE=""
if [ -f ".context/task-state.json" ]; then
  TASK_STATE=$(cat .context/task-state.json)
fi

Step 3: Capture Decisions

# Recent decisions from memory
DECISIONS=""
if [ -f ".claude/memory/decisions.jsonl" ]; then
  DECISIONS=$(tail -20 .claude/memory/decisions.jsonl)
fi

Step 4: Capture Remaining Work

Summarize what's left to do based on:

  • Open tasks in task state
  • Uncommitted changes context
  • Current branch purpose (from branch name)

Step 5: Write Checkpoint

CHECKPOINT_DIR="${CLAUDE_PLUGIN_DATA:-${HOME}/.pixl/plugin-data}/checkpoints"
mkdir -p "$CHECKPOINT_DIR"

NAME="${1:-$(date +%Y%m%d-%H%M%S)}"

cat > "$CHECKPOINT_DIR/${NAME}.json" <<EOF
{
  "name": "${NAME}",
  "created": "$(date -u +%Y-%m-%dT%H:%M:%SZ)",
  "git": {
    "branch": "${BRANCH}",
    "commit": "${COMMIT}",
    "stash_ref": "${STASH_REF:-null}",
    "has_uncommitted": ${STASH_NEEDED}
  },
  "tasks": ${TASK_STATE:-null},
  "decisions": [${DECISIONS}],
  "remaining_work": "<summarized by Claude>",
  "project_dir": "$(pwd)"
}
EOF

Read the full file on GitHub · 174 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. 9d ago First seen · 174 lines · 47 tokens per session scan B 86ea0bb7a6fb

Subscribe to this mod's changes

checkpoint is a skill published in the GitHub repository hamzaPixl/pixl-ai (2 stars, last pushed 4mo ago), licensed MIT. It adds 47 tokens to every session and 1,317 once invoked, about $0.0002 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 2026-08-31.