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.
curl -O https://raw.githubusercontent.com/strikersam/autonomous-ai-agency/master/.agents/skills/checkpoint-strategy/SKILL.mdgit clone --depth 1 https://github.com/strikersam/autonomous-ai-agencyWrote 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.
[](https://agentmods.dev/skills/strikersam/autonomous-ai-agency/checkpoint-strategy)<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.
<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>- NVIDIA SkillSpector pass
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 | $0.00000 | $0.00978 |
| Opus 5 | $0.00000 | $0.00489 |
| Sonnet 5 | $0.00000 | $0.00196 |
| Haiku 4.5 | $0.00000 | $0.00098 |
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.
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:
- Step-based checkpointing > epoch-based — LLM epochs are often thousands of hours
- Save optimizer state — resuming without optimizer state restarts Adam's momentum from zero
- Rolling window — keep last N checkpoints, not just the best; spikes happen after "best"
- Two formats — full checkpoint for resuming, sharded for fast loading at inference
- 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
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.
- 12d ago First seen · 116 lines · 0 tokens per session scan A c40bb423abf9
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.
Other skills, from other repositories
guardrails-ai-setup
Guardrails AI validation framework setup for LLM applications. Implement input/output validation, safety checks, and structured output enforcement.
mem0-integration
Mem0 memory layer integration for AI agents. Implement persistent, semantic memory for long-term context retention and personalization.
vector-memory
HNSW vector search for pattern similarity retrieval and knowledge graph maintenance with PageRank scoring, community detection, and 3-tier memory management.
chroma-integration
Chroma local vector database setup and operations for development and production.
few-shot-example-gen
Few-shot example generation and optimization for improved LLM performance.
huggingface-classifier
Hugging Face transformer model fine-tuning and inference for intent classification.