checkpoint

checkpoint is a skill for Claude Code, Codex from tianhanz/ears. It costs 48 tokens per session (1,334 once invoked), scanned A, original, MIT.

A skill that saves current task progress in a structured YAML checkpoint file. YAML is a human-readable format for storing organised information.

In plain words
What is it for?
Use it before closing a session, during long technical work, before complex or destructive changes, after major progress, or when you need to resume with a /checkpoint command.
Why use it?
It preserves decisions, experiments, parameters, blockers, and next steps when a session ends, loses context, or approaches a risky operation.

Skill for Claude CodeCodex

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

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.

agentmods badge for checkpoint

README.md
[![agentmods](https://agentmods.dev/badge/skills/tianhanz/ears/checkpoint.svg)](https://agentmods.dev/skills/tianhanz/ears/checkpoint)
Your own site
<a href="https://agentmods.dev/skills/tianhanz/ears/checkpoint"><img src="https://agentmods.dev/badge/skills/tianhanz/ears/checkpoint.svg" alt="Measured on agentmods" height="20"></a>
Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,334 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 $0.00048 $0.01334
Opus 5 $0.00024 $0.00667
Sonnet 5 $0.00010 $0.00267
Haiku 4.5 $0.00005 $0.00133

Measured 4d ago against content hash f1211f41f98a, 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 4d 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 · 170 lines

How it starts

The opening of the file, as written. The whole thing — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Checkpoint Skill

Save current task progress to a structured YAML checkpoint file that survives context loss.

When to Use

  • Session ending: Before closing session or switching tasks
  • Context window full: Approaching token limit
  • Significant progress: Completed a major phase or experiment
  • Before risky operations: Before destructive changes or complex merges
  • Manual checkpoint: User explicitly requests /checkpoint

Step 1 — Gather current state

Review conversation history and files to extract:

Phase tracking:

  • What phase are we in? (e.g., parameter_extraction, mesh_generation, convergence_testing, debugging, implementation)
  • What phases are completed?
  • What phases are next?

Critical state:

  • Parameters: Extracted values with sources (paper page/table or "estimated from X") and confidence levels
  • Experiments: What's been tried? Status (pending/in_progress/completed/failed/diverged), results paths, failure reasons
  • Decisions: Key choices made, rationale, alternatives considered
  • Custom state: Task-specific data (meshes, models, datasets, API endpoints, etc.)

Blockers:

  • Open questions blocking progress
  • Decisions needed
  • Assumptions made that need verification

Artifacts: Critical files (configs, results, scripts) with roles

Resume instructions: Specific commands to run next session, conditions to verify

Step 2 — Determine checkpoint filename

BRANCH=$(git branch --show-current)
TIMESTAMP=$(date -u +"%Y%m%d-%H%M%S")
CHECKPOINT_FILE=".claude/checkpoints/${BRANCH}-${TIMESTAMP}.yaml"
mkdir -p .claude/checkpoints

Step 3 — Write checkpoint YAML

Quality bar:

  • Every parameter must have source (paper page/table or "estimated from X")
  • Every failed experiment must have reason (not just "didn't work")
  • Every decision must have rationale
  • Resume instructions must be actionable (specific commands or file checks, not vague "continue work")

Example checkpoint:

Read the full file on GitHub · 170 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. 4d ago First seen · 170 lines · 48 tokens per session scan A f1211f41f98a

Subscribe to this mod's changes

checkpoint is a skill published in the GitHub repository tianhanz/ears (5 stars, last pushed 4mo ago), licensed MIT. It adds 48 tokens to every session and 1,334 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 2026-08-31.

Related

Other skills, from other repositories

Effective Memory

The essential habits for an AI agent with memory — session bookends, learning triggers, verification, safety, and the operational discipline that turns raw recall into compounding intelligence. Pinned, always-injected.

plur-ai/plur · 44 tokens

s-continue

Cheaper and faster than /compact. Restores previous session context from Claude Code AND Codex transcripts by reading them directly — no LLM calls, no token cost. Also auto-loads a handoff written by /s-compact, if one exists. Triggers on "s-continue", "restore context", "what was I doing", "pick up where I left off"…

ww-w-ai/super-token-saver · 95 tokens

project-memory

Generate a project-specific context file from a brief so an AI assistant remembers your editorial constraints, voice, audience, and quality bar across sessions.

ur-grue/autopunk-media-skills · 31 tokens

sync

Fast save-point: sync all session-context files and MEMORY.md with current progress. Zero questions, zero delay. Use when user says /sync, save progress, save state, sync context, or /sync --full for capability inventory.

anombyte93/atlas-session-lifecycle · 49 tokens

handoff-more

Pull older handoffs from .claude/handoffhistory/ into the current session's context. Requires the scripts/hooks installed by this repo's ./install.sh — the history it reads only exists once those are in place. Use when the auto-loaded handoffcurrent.md is thin (placeholder Notes, missing context the user is…

Sting25/claude-code-handoff · 110 tokens

mk:session-continuation

Persists and restores mid-session workflow progress across context resets. Use when resuming workflows, saving state, or handling context compaction. Triggers on: handoff, save state, resume workflow.

ngocsangyem/MeowKit · 47 tokens