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.
npx skills add adamwang99/NEUTRON-EVO-OS --skill checkpointgit clone --depth 1 https://github.com/adamwang99/NEUTRON-EVO-OSWrote 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/adamwang99/neutron-evo-os/checkpoint)<a href="https://agentmods.dev/skills/adamwang99/neutron-evo-os/checkpoint"><img src="https://agentmods.dev/badge/skills/adamwang99/neutron-evo-os/checkpoint/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/adamwang99/neutron-evo-os/checkpoint"><img src="https://agentmods.dev/badge/skills/adamwang99/neutron-evo-os/checkpoint.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00766 |
| Opus 5 | $0.00000 | $0.00383 |
| Sonnet 5 | $0.00000 | $0.00153 |
| Haiku 4.5 | $0.00000 | $0.00077 |
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 10d 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 — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SKILL: Checkpoint — Session State Persistence
NEUTRON EVO OS v4.1.0 | CI tracking: skill router Context: Long-running agent sessions → context compression survival
Purpose
Dump current session state to disk so that:
- Compaction survives: After
/compact, agent reads checkpoint → knows "I was doing X" - Resume accurate: Human or AI resuming knows exact context, blockers, next step
- Dream Cycle feeds: Checkpoint becomes source for distillation
Usage
/checkpoint [optional focus]
Examples:
/checkpoint → full state dump
/checkpoint trading module → focus on trading module
/compact Continue the current task
Checkpoint Format
Written to memory/{date}.md in structured YAML-frontmatter style:
# Checkpoint — {timestamp}
> NEUTRON EVO OS v4.0.0 | Session: checkpoint
## State
- **Status**: in_progress | paused | blocked | complete
- **Task**: {what was being worked on}
- **Focus**: {optional focus area from agent}
- **Confidence**: {high|medium|low}
## Current Work
- Files modified: [list]
- Files created: [list]
- Last action: {description}
- Output: {summary of result}
## Blockers
- [ ] {blocker 1}
- [ ] {blocker 2}
## Next Steps (priority order)
1. {step 1}
2. {step 2}
3. {step 3}
## Decisions Made
- {decision 1} → reason
- {decision 2} → reason
## Notes
{Other relevant context}
Trigger Points (when to call /checkpoint)
| Situation | Trigger |
|---|---|
Before /compact |
REQUIRED |
Before /rewind |
REQUIRED |
| Every ~30 min in long sessions | RECOMMENDED |
| Before ending session | REQUIRED |
| When blocked for > 5 min | REQUIRED |
| When task completes | RECOMMENDED |
Checkpoint Chain
Agent starts task
↓
Every N minutes: /checkpoint
↓
Context approaches 80%: /compact + /checkpoint
↓
After compaction: reads checkpoint → restores context
↓
Task continues with full awareness
Auto-Checkpoint via Hook
The PreToolUse hook monitors for compaction commands and triggers auto-checkpoint.
See engine/checkpoint_cli.py for the CLI wrapper.
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 10d ago First seen · 113 lines · 0 tokens per session scan A 2fc76ac88e04
checkpoint is a skill published in the GitHub repository adamwang99/NEUTRON-EVO-OS (20 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 766 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 2026-08-30.
Other skills, from other repositories
metago-expert-knowledge-crystal-curator
A Chinese-language system for managing short-term conversation notes, long-term stored knowledge, and reusable skills. It covers saving, finding, updating, and retiring this information over time.
metago-developer-response
A response procedure for handling developer corrections or criticism. It calls for checking the relevant evidence, finding the cause of an error, correcting the answer, and recording the lesson for future cases.
metago-memory-manage
A Chinese-language framework for managing knowledge and memory in four layers: facts, stored information, learned patterns and harder-to-explain judgement.
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…