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 agentmods add skills/mubit-ai/claude-plugins/checkpointnpx skills add mubit-ai/claude-plugins --skill checkpointgit clone --depth 1 https://github.com/mubit-ai/claude-pluginsWrote 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/mubit-ai/claude-plugins/checkpoint)<a href="https://agentmods.dev/skills/mubit-ai/claude-plugins/checkpoint"><img src="https://agentmods.dev/badge/skills/mubit-ai/claude-plugins/checkpoint.svg" alt="Measured on agentmods" 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 | $0.00063 | $0.00630 |
| Opus 5 | $0.00032 | $0.00315 |
| Sonnet 5 | $0.00013 | $0.00126 |
| Haiku 4.5 | $0.00006 | $0.00063 |
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.
How it starts
The opening of the file, as written. The whole thing — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Call mubit_checkpoint — POST /v2/control/checkpoint — with the state you are holding.
snapshot is the only required argument; label is a short name the user can ask for later
and is worth passing every time.
What goes in snapshot
It is stored verbatim and unsummarised. Nothing rewrites it, shortens it or extracts anything from it, which cuts both ways: whatever you write is exactly what a future reader gets, and a one-line headline restores nothing.
Write it for someone who has lost the conversation entirely — which is the only situation in which it will ever be read. What we were doing and why, what is finished, what is half-done and how far, the exact branch, file paths and commands in play, and the next concrete step. Prose is fine. Length is fine. This is the one write in the plugin where compressing is the mistake.
A checkpoint is run state, not knowledge
This is the distinction that decides whether to use this skill at all.
Run state is true now and false tomorrow: "mid-migration on feat/x, three files edited,
the codex suite still red on two dist tests". It is worthless in six months and nobody wants
it surfacing in an unrelated session. That is a checkpoint.
Knowledge is true regardless of which run learned it: "npm run verify deletes the
vendored server bundle", "this team wants small PRs". That is a lesson — save it with
/mubit-memory:remember, which classifies it and gives it a scope so it reaches later
sessions on purpose.
Getting this backwards costs something in both directions. A checkpoint used for knowledge buries a durable fact in a snapshot nobody will search for. A lesson used for run state turns memory into a session log, and every later recall pays for it.
When to call it
The PreCompact hook already checkpoints on the way into a compaction. That is the automatic
one, and it fires on the host's schedule — when the window fills — which is exactly the moment
nobody can ask for. This tool is the half a person asks for: before a destructive migration, a
history rewrite, a long refactor, or a deliberate /clear the user wants to walk back from.
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.
- 4d ago First seen · 50 lines · 63 tokens per session scan A c7e63f9fef01
checkpoint is a skill published in the GitHub repository mubit-ai/claude-plugins (13 stars, last pushed today), licensed Apache-2.0. It adds 63 tokens to every session and 630 once invoked, about $0.0003 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.
Other skills, from other repositories
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…
agent-memory
../../../engineering/agent-memory/skills/agent-memory/SKILL.md.
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…