checkpoint

checkpoint is a skill for Claude Code, Codex from svy04/ballast. It costs 71 tokens per session (957 once invoked), scanned A, original, MIT.

A workflow for keeping a short return note and a one-time handoff note for unfinished agent work. The notes explain the current state and the next action so another session can continue quickly.

In plain words
What is it for?
Use it when major work finishes, a session is ending, instructions must be passed to the next session, or paused work needs to be resumed.
Why use it?
It avoids spending time reconstructing decisions and progress from missing or lengthy conversation history.

Skill for Claude CodeCodex

Part of the ballast plugin — 16 skills, 4 hooks shipped together

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.

agentmods
npx agentmods add skills/svy04/ballast/checkpoint
Any agent
npx skills add svy04/ballast --skill checkpoint
Clone the repo
git clone --depth 1 https://github.com/svy04/ballast

Made for: Claude Code, Codex.

Or install ballast, the plugin that ships this one along with the rest of its 16 skills, 4 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/svy04/ballast/checkpoint.svg)](https://agentmods.dev/skills/svy04/ballast/checkpoint)
Your own site
<a href="https://agentmods.dev/skills/svy04/ballast/checkpoint"><img src="https://agentmods.dev/badge/skills/svy04/ballast/checkpoint.svg" alt="Measured on agentmods" height="20"></a>
Per session 71 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 957 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00071 $0.00957
Opus 5 $0.00036 $0.00478
Sonnet 5 $0.00014 $0.00191
Haiku 4.5 $0.00007 $0.00096

Measured 5d ago against content hash e351d800b0af, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 5d 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.

skills/checkpoint/SKILL.md · 64 lines

How it starts

The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Checkpoint — return in thirty seconds

A session ends; the work doesn't. Whoever returns — the user after a week, or a fresh session after a context reset — faces scrollback that no longer exists and a directory that doesn't explain itself. Reconstruction eats the first twenty minutes and gets details wrong. This skill keeps one file that makes return instant, and a second file that carries orders across the gap without letting them go stale.

CHECKPOINT.md — the return point

Update memory/CHECKPOINT.md whenever a large unit of work completes or the session is winding down. Five sections, always in this order:

# Checkpoint — <goal> — <YYYY-MM-DD HH:MM>

## The story so far
<Thirty seconds of reading, no more. What this work is and where it
stands, told to someone with zero context.>

## Decided
<Decisions confirmed since the last checkpoint — one line each, with
ledger ids where they exist.>

## Waiting on the user
<Decisions only the user can make, and the readings in force from
OPEN-QUESTIONS that are due a question — one line each, so they get asked
here, at the break, not mid-flow. Empty is a valid and welcome state.>

## Next first action
<ONE line, executable immediately without reading anything else.>

## Tried
<Approaches attempted that did not work, one line each with why.>

Rules:

  • Next first action is the load-bearing line. A cold session must be able to execute it before reading a single other file: concrete verb, concrete object, no prerequisite. "Continue the analysis" fails this test; "run the export script against the staging list and diff the counts" passes.
  • Tried is a map of dead ends. An approach that failed and went unrecorded will be attempted again, in good faith, by a session that has no way to know better. One line per dead end — what was tried, why it didn't work.
  • Archive on every update. Before overwriting, copy the outgoing version to memory/checkpoints/{YYYYMMDD-HHMM}-<short-title>.md. That directory is append-only and sorts itself by filename — the full trail of how the work moved, at zero extra cost.
  • Index each file the first time it appears. When this skill first creates memory/CHECKPOINT.md, memory/checkpoints/, or memory/HANDOFF.md, add a row for it to the File map in memory/00-INDEX.md — a file missing from the map is a file the next session never opens.

Read the full file on GitHub · 64 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. 5d ago First seen · 64 lines · 71 tokens per session scan A e351d800b0af

Subscribe to this mod's changes

checkpoint is a skill published in the GitHub repository svy04/ballast (71 stars, last pushed 10d ago), licensed MIT. It adds 71 tokens to every session and 957 once invoked, about $0.0004 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.

Related

Other skills, from other repositories

alive:system-cleanup

The world feels messy. Stale tasks, orphan folders, v2 remnants, unsaved sessions — entropy is accumulating and needs to be addressed before it compounds. Scans across all walnuts, then surfaces issues one at a time.

alivecontext/alive · 52 tokens

alive:world

The human doesn't know what to work on, or wants to see everything at once. They need the big picture — what's active, what's stale, what needs attention. Renders a live world view grouped by ALIVE domain, then routes to open, tidy, find, history, or map.

alivecontext/alive · 63 tokens

alive:bundle

Create, share, and graduate bundles — the unit of focused work within a walnut. Manages the full bundle lifecycle from creation through sharing to graduation.

alivecontext/alive · 34 tokens

alive:settings

The human wants to adjust how the system behaves — not what it contains, but how it feels. Voice, rhythm, preferences, walnut-level config, full permissions toggleable, named squirrel config, action logging toggle. The system adapting to them. Routes to preferences.yaml or walnut config.yaml depending on scope. For…

alivecontext/alive · 84 tokens

cco-budget

Configure token budget limits, auto-compact settings, and view current budget status (model-aware — Claude 5 lineup, Opus 5 default fallback, full 1M context at standard price).

egorfedorov/claude-context-optimizer · 43 tokens

smart-loader

Automatically suggests optimal files to preload based on the user's task description and historical context patterns. Activates when the user starts a new task, mentions reading files, or when session context is being set up.

egorfedorov/claude-context-optimizer · 43 tokens