autonomous-ai-agency: Skill for Claude Code

.agents/skills/checkpoint-strategy/SKILL.md

checkpoint-strategy is a skill for Claude Code, Codex from strikersam/autonomous-ai-agency. It costs 0 tokens per session (978 once invoked), scanned A, original, MIT.

A planning skill for saving and checking recovery points during large language model training. A checkpoint is a saved copy of a training run that can be used to continue after a failure.

In plain words
What is it for?
Use it to design checkpoint policies, choose a restart point after training problems, balance storage against recovery safety, or move training between machines or cloud providers.
Why use it?
It helps reduce lost compute after a loss spike, hardware change, or other interruption by deciding what to save, how often to save it, and which copy to resume from.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is strikersam/autonomous-ai-agency's own configuration. It tells Claude Code and Codex how to work on autonomous-ai-agency itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything autonomous-ai-agency configures →

Reuse

Borrowing it

Nothing to install: this file belongs to strikersam/autonomous-ai-agency. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/strikersam/autonomous-ai-agency/master/.agents/skills/checkpoint-strategy/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/strikersam/autonomous-ai-agency

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-strategy

README.md
[![agentmods](https://agentmods.dev/badge/skills/strikersam/autonomous-ai-agency/checkpoint-strategy/github.svg)](https://agentmods.dev/skills/strikersam/autonomous-ai-agency/checkpoint-strategy)
Your own site
<a href="https://agentmods.dev/skills/strikersam/autonomous-ai-agency/checkpoint-strategy"><img src="https://agentmods.dev/badge/skills/strikersam/autonomous-ai-agency/checkpoint-strategy/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.

agentmods 80×15 button for checkpoint-strategy

Your own site · 80×15
<a href="https://agentmods.dev/skills/strikersam/autonomous-ai-agency/checkpoint-strategy"><img src="https://agentmods.dev/badge/skills/strikersam/autonomous-ai-agency/checkpoint-strategy.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 978 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 5.1 $0.00000 $0.00978
Opus 5 $0.00000 $0.00489
Sonnet 5 $0.00000 $0.00196
Haiku 4.5 $0.00000 $0.00098

Measured 12d ago against content hash c40bb423abf9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

checkpoint-strategy 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 12d 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.

.agents/skills/checkpoint-strategy/SKILL.md · 116 lines

How it starts

The opening of the file, as written. The whole thing — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill: checkpoint-strategy

Purpose

Design and validate checkpointing strategies for LLM training runs. One of the most painful lessons from building LLMs from scratch: losing 12 hours of compute to a spike you can't roll back from.

Trigger

Use when:

  • Starting a new training run (set checkpointing policy upfront)
  • After a loss spike — determine best checkpoint to resume from
  • Evaluating storage vs safety tradeoffs for checkpoint frequency
  • Migrating training across hardware or cloud providers

Background

From practitioners:

"Checkpointing feels like overhead until you need it. Then it's the only thing that matters. Save more often than you think you need to, in at least two formats."

Key lessons:

  1. Step-based checkpointing > epoch-based — LLM epochs are often thousands of hours
  2. Save optimizer state — resuming without optimizer state restarts Adam's momentum from zero
  3. Rolling window — keep last N checkpoints, not just the best; spikes happen after "best"
  4. Two formats — full checkpoint for resuming, sharded for fast loading at inference
  5. Validate before deleting — always verify a checkpoint loads before removing older ones

Usage

/checkpoint-strategy [total_steps] [step_duration_seconds] [storage_budget_gb] [--model_size_gb N]

Checkpoint Policy Templates

Conservative (Recommended for First Runs)

checkpoint_policy:
  frequency: every_500_steps
  keep_last: 10
  keep_milestone: [1000, 5000, 10000, 25000, ...]  # powers of 2 * 1000
  save_optimizer: true
  save_formats:
    - full_state_dict    # for resuming
    - safetensors        # for inference/sharing
  validate_on_save: true
  async_save: true       # don't block training

Aggressive (Long Runs with Stable Training)

checkpoint_policy:
  frequency: every_2000_steps  
  keep_last: 5
  keep_milestone: [10000, 50000, 100000]
  save_optimizer: true
  emergency_save_on: 
    - loss_spike_detected    # triggers immediate save before rollback
    - gradient_norm_exceeded

Read the full file on GitHub · 116 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. 12d ago First seen · 116 lines · 0 tokens per session scan A c40bb423abf9

Subscribe to this mod's changes

checkpoint-strategy is a skill published in the GitHub repository strikersam/autonomous-ai-agency (8 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 978 tokens. 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.