What is repo-checkpoint?

A repository-local checkpoint workflow for Git projects that records current work and handoff details in a Markdown file.

Use it to save progress, capture files and remaining tasks, and prepare a handoff before closing a session.

It preserves the important context when a coding session ends so another agent or later session can resume the work.

repo-checkpoint — Skill for Claude Code and Codex by hotalexnet

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 hotalexnet/agent-checkpoint --skill repo-checkpoint

Clone the repo

git clone --depth 1 https://github.com/hotalexnet/agent-checkpoint

Made for: Claude Code, Codex.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/hotalexnet/agent-checkpoint/repo-checkpoint/github.svg)](https://agentmods.dev/skills/hotalexnet/agent-checkpoint/repo-checkpoint)

Your own site

<a href="https://agentmods.dev/skills/hotalexnet/agent-checkpoint/repo-checkpoint"><img src="https://agentmods.dev/badge/skills/hotalexnet/agent-checkpoint/repo-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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/hotalexnet/agent-checkpoint/repo-checkpoint"><img src="https://agentmods.dev/badge/skills/hotalexnet/agent-checkpoint/repo-checkpoint.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 68 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 546 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. 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.

Model	Per session	Once invoked
Fable 5.1	$0.00068	$0.00546
Opus 5.5	$0.00027	$0.00218
Sonnet 5.5	$0.00014	$0.00109
Haiku 4.5	$0.00007	$0.00055

Measured 1mo ago against content hash 099a4f8b9210, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

repo-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.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/redact.py, scripts/save_checkpoint.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

repo-checkpoint/SKILL.md · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.

repo Checkpoint

Use this skill inside a git repository.

Why this skill exists

Conversation state is fragile. A repo-local markdown checkpoint is not.

This skill writes a timestamped markdown handoff under the fixed repo-local directory .agents/checkpoints/ so the next session can recover from any programming agent: Codex/OpenAI CLI, Claude Code, opencode, or a generic shell agent. The checkpoint belongs to the repository, not to a particular tool.

what the user actually wanted
what constraints mattered
what files were in play
what remains next

Use save_checkpoint.py --current when maintaining one active lane; it atomically updates current.md without replacing historical snapshots. New checkpoints carry expiry and base-commit metadata, and common credentials are redacted before write.

Mandatory first step

From the target repo root, run:

python3 ~/.agents/skills/repo-checkpoint/scripts/save_checkpoint.py --title "<short-title>" --agent "<codex|claude-code|opencode|other>"

If the skill is vendored into the repo instead of installed globally, run the same script from the vendored path.

Workflow

Create the scaffold first. Do not invent the path manually.
Replace every TODO with concrete current-session state.
Treat Agent Handoff and Key Chat Context as first-class data:
- which agent wrote the checkpoint
- which agent should be able to resume it
- where to start without relying on hidden conversation memory
- user goal
- explicit constraints
- scope changes
- rejected paths
- exact wording worth preserving
Keep Files In Play, Verification, and Next Step executable.
End with the checkpoint path and tell the user that any supported agent can run repo-resume from the same repo next time.

Output contract

Keep these top-level sections exactly:

## Agent Handoff
## Session Goal
## Current State
## Key Chat Context
## Files In Play
## Verification
## Next Step
## Resume Recipe
## Git Snapshot

Read the full file on GitHub · 69 lines

Files

What ships with it

2 files 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.

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.

1mo ago Changed · +4 lines 099a4f8b9210
2mo ago First seen · 65 lines · 68 tokens per session scan A 31aa3fb65113

Subscribe to this mod's changes

repo-checkpoint is a skill published in the GitHub repository hotalexnet/agent-checkpoint (14 stars, last pushed 1mo ago), licensed MIT. It adds 68 tokens to every session and 546 once invoked, about $0.0003 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 2026-08-30.

Claude Code Commits Git and workflow agent-tool ai-agent checkpoint codex coding-agent

autofix-pr

Watch a pull request and fix it from a worktree of its own - CI failures, review feedback from trusted authors and merge conflicts are fixed, pushed to the PR branch and answered on the PR under the user's git and gh identity. Usage - /autofix-pr [ | ] [--once] [--every ] [--no-reply] [--yes] [instructions]…

QwenLM/qwen-code · 123 tokens

cw-land

Use when turning verified Codewhale work into commits, branches, or a merge: choosing direct-main vs. worktree vs. integration branch, preserving contributor credit, and honoring the gate artifact before merging.

Hmbown/Codewhale · 44 tokens

cuga-contributor-workflows

Run CUGA contributor workflows: Conventional Commits, create pull requests against origin with gh and PR templates, ruff check/format via uv, and the required design-impact, area, and readability labels before every push and pull request. Use when the user says commit, create a commit, push, create PR, pull request…

cuga-project/cuga-agent · 92 tokens

repo-checkpoint