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 skills add majiayu000/claude-skill-registry --skill ac-checkpoint-managergit clone --depth 1 https://github.com/majiayu000/claude-skill-registryWrote 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/skills/majiayu000/claude-skill-registry/ac-checkpoint-manager)<a href="https://agentmods.dev/skills/majiayu000/claude-skill-registry/ac-checkpoint-manager"><img src="https://agentmods.dev/badge/skills/majiayu000/claude-skill-registry/ac-checkpoint-manager/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/skills/majiayu000/claude-skill-registry/ac-checkpoint-manager"><img src="https://agentmods.dev/badge/skills/majiayu000/claude-skill-registry/ac-checkpoint-manager.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00030 | $0.00379 |
| Opus 5 | $0.00015 | $0.00189 |
| Sonnet 5 | $0.00006 | $0.00076 |
| Haiku 4.5 | $0.00003 | $0.00038 |
Grade A, and why
ac-checkpoint-manager 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 13d 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.
What it actually says
AC Checkpoint Manager
Manage checkpoints for safe rollback during autonomous development.
Purpose
Creates and manages checkpoints that enable rollback to known-good states, providing safety during autonomous operation.
Quick Start
from scripts.checkpoint_manager import CheckpointManager
manager = CheckpointManager(project_dir)
checkpoint = await manager.create_checkpoint("before-refactor")
await manager.restore_checkpoint(checkpoint.id)
Checkpoint Types
- Auto: Created automatically at key points
- Manual: Created on explicit request
- Feature: Created after each feature completion
- Session: Created at session boundaries
Checkpoint Structure
.claude/checkpoints/
├── checkpoint-20240115-100000/
│ ├── metadata.json
│ ├── feature_list.json
│ ├── execution-state.json
│ └── git-ref.txt
├── checkpoint-20240115-110000/
│ └── ...
Auto-Checkpoint Points
- Before starting new feature
- After completing feature
- Before risky operations
- At context compaction
Workflow
1. CREATE → Snapshot current state
2. STORE → Save files and git ref
3. VALIDATE → Verify checkpoint integrity
4. (on rollback)
5. RESTORE → Restore from checkpoint
6. VERIFY → Confirm restoration
Integration
- Used by:
ac-state-trackerfor state recovery - Used by:
ac-task-executorbefore risky operations
API Reference
See scripts/checkpoint_manager.py for full implementation.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 13d ago First seen · 70 lines · 30 tokens per session scan A 55d21b72f57b
ac-checkpoint-manager is a skill published in the GitHub repository majiayu000/claude-skill-registry (604 stars, last pushed yesterday), licensed MIT. It adds 30 tokens to every session and 379 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
neo-pr
Use this skill when the user asks to create, draft, review, format, or generate a Pull Request (PR) title and description, specify target or source branches for a repository, or convert git branch diffs into concise, high-impact, non-AI-slop PR content.
git-pr-create
Open a GitHub pull request for the current branch using gh — conventional title, repo-template-aware body, auto-derived labels, push if needed. Use for every PR-creation request no matter how casual: "create/open/make/raise a PR", "PR this", "PR please", "send PR", "/git-pr-create", "open pull request", "ship this"…
git-commit
Run git commit using Angular conventional commit format. Use when the user asks to commit, create a commit, /git-commit, or save changes to git. Also trigger on "snapshot this", "save my work", "check in changes", "wrap up", "ship this locally", or whenever the user finishes a logical unit of work and the tree is…
spec-dispatch
Run an OpenSpec change's tasks in parallel — read the task queue, plan file-disjoint waves, dispatch one agent per task, verify, tick the boxes, commit. Use when the user says "dispatch the tasks", "run these tasks in parallel", "fan out the change", "/spec-dispatch", "implement this change with agents", or wants an…
git-branches-cleanup
Delete local git branches whose remote tracking branch is gone or whose changes are already merged into the base branch. Use when the user asks to clean up branches, prune branches, delete stale branches, or /git-branches-cleanup. Also trigger on "tidy git branches", "remove old branches", "I'm done with these…
iso-push
Push committed work, open a PR against dev, and land it with a merge commit so no commit is ever rewritten or duplicated. Use when invoked as /iso-push [--pr] [--cascade test|prod] [--no-merge] [--stay], or when asked to push a branch, open a PR against dev, or promote dev to test or prod. Requires a dev or develop…