Agent skill

Checkpoint

by ipea in ipea/geobr

Save a structured state snapshot the next session can resume from — active plan, decisions and why, file pointers with line numbers, open questions, next 1-3 actions, and what to deliberately forget.

No licenceAuto-check: notesTesting & QA

Install Checkpoint

skills CLI
$ npx skills add ipea/geobr --skill checkpoint -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install ipea/geobr checkpoint --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/ipea/geobr.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/checkpoint .claude/skills/checkpoint && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
checkpoint
GitHub stars
959
Token cost
~1.4k tokens
SKILL.md length
369 words
Files
1
Skills in repo
9
Repo updated
First seen
Licence
None found

At a glance

Save a structured state snapshot the next session can resume from — active plan, decisions and why, file pointers with line numbers, open questions, next 1-3 actions, and what to deliberately forget.

  • Works in 4 steps: Gather state → Write the checkpoint → Propose memory updates (skip with… → …
  • The user says checkpoint
  • SKILL.md covers When to use, Phase 1 — Gather state, Phase 2 — Write the checkpoint and Phase 3 — Propose memory…, plus 3 more sections
  • Calls git

What it does

Checkpoint is an agent skill from ipea/geobr. Save a structured state snapshot the next session can resume from — active plan, decisions and why, file pointers with line numbers, open questions, next 1-3 actions, and what to deliberately forget. Use before a break, a model switch, a collaborator handoff, or when context is approaching auto-compaction. Use when the user says "checkpoint", "save state", "where am I", "compress", "distil this session", "wrap up for handoff", "before we hit auto-compact".

Its SKILL.md is about 1.4k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Testing & QA. The repository describes itself as: Easy access to official spatial data sets of Brazil in R and Python.

When your agent uses it

  • The user says checkpoint
  • Distil this session
  • Wrap up for handoff
  • Before we hit auto-compact

Example prompts

  • “checkpoint”
  • “save state”
  • “where am I”
  • “/checkpoint”

Requirements

  • Python 3
  • Pre-approved tools (allowed-tools): Read, Write, Glob, Grep, Bash

Workflow steps

4 steps, taken from the step headings in SKILL.md.

  1. Gather state
  2. Write the checkpoint
  3. Propose memory updates (skip with --no-memory)
  4. Report

What it can do on your machine

Read from SKILL.md and the folder at commit 0969f92. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Read
    • Write
    • Glob
    • Grep
    • Bash

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • git

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Checkpoint loads about 1.4k tokens when it runs. Until then it costs about 118 tokens; SKILL.md has 369 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~118
When it runs · the whole SKILL.md, loaded when a task matches
~1.4k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NotePre-approves every shell command (allowed-tools: Bash)SKILL.md
    allowed-tools: Read, Write, Glob, Grep, Bash

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

Without a licence we can't republish the file, so here is its outline and opening line. It has 369 words (~1,441 tokens).

“problem at two moments. The stop-point shape is adapted from Hugo Sant'Anna's clo-author v4.2.0; the "discarded as noise" section is from Breunig's long-context failure modes (dbreunig.com/2025/06/22/how-contexts-fail-and-how-to-fix-them.html) — naming failed hypotheses explicitly stops them being re-quoted by a future session. -->”

— opening of SKILL.md by ipea
name
checkpoint
allowed-tools
Read, Write, Glob, Grep, Bash
author
geobr
version
2.0.0
argument-hint
[short-topic-slug] [--no-memory]
disable-model-invocation
true

Read the full SKILL.md on GitHub

Files

Just SKILL.md in .claude/skills/checkpoint of ipea/geobr.

Open the folder on GitHubat commit 0969f92

Compare with similar skills

Checkpoint next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Checkpoint compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Checkpoint this skillipea/geobr959—~1.4kAutomated safety check: NotesNone
Web Application Testinganthropics/skills180k51 repos~966Automated safety check: PassApache-2.0
Diagnosing Bugsfossasia/eventyay-interpretation1.6k31 repos~2.1kAutomated safety check: PassApache-2.0
TDDfossasia/eventyay-interpretation1.6k28 repos~1.1kAutomated safety check: PassApache-2.0
TDD WorkflowhellangleZ/burn-in-cceverywhere-ralph11211 repos~2.4kAutomated safety check: PassNone
TDDsanity-io/sanity6.4k20 repos~1kAutomated safety check: PassMIT

Similar skills

  • Web Application Testing

    anthropics/skills

    Official

    Tests local web applications with Python Playwright scripts, checking frontend behavior, capturing screenshots and reading browser console logs.

    180k GitHub starsUsed in 51 repos~966 tokens
    Testing & QAAuto-check passed
  • Diagnosing Bugs

    fossasia/eventyay-interpretation

    Diagnosis loop for hard bugs and performance regressions. An agent skill from fossasia/eventyay-interpretation.

    1.6k GitHub starsUsed in 31 repos~2.1k tokens
    Testing & QAAuto-check passed
  • TDD

    fossasia/eventyay-interpretation

    Test-driven development. An agent skill from fossasia/eventyay-interpretation.

    1.6k GitHub starsUsed in 28 repos~1.1k tokens
    Testing & QAAuto-check passed
  • TDD Workflow

    hellangleZ/burn-in-cceverywhere-ralph

    A skill your agent uses when writing new features, fixing bugs, or refactoring code.

    112 GitHub starsUsed in 11 repos~2.4k tokens
    Testing & QAAuto-check passed
  • TDD

    sanity-io/sanity

    Official

    Test-driven development with red-green-refactor loop. An agent skill from sanity-io/sanity.

    6.4k GitHub starsUsed in 20 repos~1k tokens
    Testing & QAAuto-check passed
  • Context Driven Development

    Ibrahim-3d/orchestrator-supaconductor

    A skill your agent uses when working with Conductor's context-driven development methodology, managing project context artifacts, or understanding the relationship between product.md, tech-stack.md…

    380 GitHub starsUsed in 8 repos~2.9k tokens
    Testing & QAAuto-check passed

More from ipea/geobr

All 9 skills in this repo
  • Learn

    ipea/geobr

    Extract reusable knowledge from the current session into a persistent skill.

    959 GitHub starsUsed in 2 repos~1.2k tokens
    Auto-check: notes
  • Deep Audit

    ipea/geobr

    Deep consistency audit of the geobr repository — configuration, documentation, and the two packages.

    959 GitHub stars~1.8k tokensUpdated 10 days ago
    Auto-check: notes
  • Diagnose

    ipea/geobr

    Root-cause a failing or wrong geobr call with a disciplined check-the-environment-first loop instead of guessing.

    959 GitHub stars~1.5k tokensUpdated 10 days ago
    Auto-check passed
  • Parity Check

    ipea/geobr

    Check R↔Python API parity across geobr's two packages — which read functions exist on one side but not the other, and where matched functions disagree on argument names, defaults, or the metadata…

    959 GitHub stars~1.4k tokensUpdated 10 days ago
    Auto-check: notes
  • Run the Python package release gate for geobr — sync the locked environment, run the offline and network test suites, build the distribution, and review the source against the Python conventions.

    959 GitHub stars~1.4k tokensUpdated 10 days ago
    Auto-check: notes
  • R Package Check

    ipea/geobr

    Run the full R package release gate — regenerate docs, run the test suite, run R CMD check --as-cran, and triage every ERROR / WARNING / NOTE against CRAN policy before a release or submission.

    959 GitHub stars~1.5k tokensUpdated 10 days ago
    Auto-check: notes

Categories

Questions about Checkpoint

What does Checkpoint do?

Save a structured state snapshot the next session can resume from — active plan, decisions and why, file pointers with line numbers, open questions, next 1-3 actions, and what to deliberately forget. Checkpoint is an agent skill from ipea/geobr. Save a structured state snapshot the next session can resume from — active plan, decisions and why, file pointers with line numbers, open questions, next 1-3 actions, and what to deliberately forget.

When should I use Checkpoint?

Checkpoint fits situations like: the user says checkpoint; distil this session; wrap up for handoff; before we hit auto-compact.

How do I install Checkpoint in Claude Code?

Run `npx skills add ipea/geobr --skill checkpoint -a claude-code`. Or copy the skill folder (.claude/skills/checkpoint in ipea/geobr) into .claude/skills/checkpoint in your project. Claude Code loads it when a task matches its description.

How do I install Checkpoint in Codex?

Run `npx skills add ipea/geobr --skill checkpoint -a codex`. Or copy the skill folder (.claude/skills/checkpoint in ipea/geobr) into .agents/skills/checkpoint in your project. Codex loads it when a task matches its description.

Can I use Checkpoint in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add ipea/geobr --skill checkpoint -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/checkpoint, .gemini/skills/checkpoint, .github/skills/checkpoint and .opencode/skills/checkpoint in your project.

What does Checkpoint need to run?

Going by SKILL.md and its folder, Checkpoint needs the command-line tools its instructions call (git). Our summary lists: Python 3. Its frontmatter pre-approves these tools: Read, Write, Glob, Grep, Bash.

Does Checkpoint access the network?

SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Checkpoint safe to install?

Our automated static check of SKILL.md found notes only (pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.

What licence does Checkpoint use?

No licence was found for Checkpoint or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.

How many tokens does Checkpoint use?

About 1.4k tokens (SKILL.md is roughly 5.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Checkpoint?

Skills that share tags, products or a category with Checkpoint: Web Application Testing (anthropics/skills, 180k stars), Diagnosing Bugs (fossasia/eventyay-interpretation, 1.6k stars), TDD (fossasia/eventyay-interpretation, 1.6k stars) and TDD Workflow (hellangleZ/burn-in-cceverywhere-ralph, 112 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Checkpoint?

ipea (a GitHub organization) maintains it in ipea/geobr, which has 959 GitHub stars. The repository holds 9 skills in this directory. The repository was last updated on September 27, 2026.

Source: ipea/geobr on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.