checkpoint is agent-read markdown (skill) from mubit-ai/plugins: Save a named verbatim snapshot of this run; use when the user is about to do something risky..
Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.
What the file says
Run the bundled script with the snapshot on stdin. It posts `POST /v2/control/checkpoint`
under this session's run, and nothing else:
```bash
node ${CLAUDE_PLUGIN_ROOT}/bin/admin.mjs checkpoint --data-dir "${MUBIT_CC_DATA_DIR:-${CLAUDE_PLUGIN_DATA}}" --label "<short name>" <<'SNAPSHOT'
<the snapshot>
SNAPSHOT
```
**`--data-dir "${MUBIT_CC_DATA_DIR:-${CLAUDE_PLUGIN_DATA}}"` is not optional.** A Bash tool
call does not inherit `CLAUDE_PLUGIN_DATA` — it arrives empty — so without the flag the script
has to guess which of several `mubit-memory*` directories the host is using, and either
refuses with `no_run` or acts on a run this session's hooks never touch. The host substitutes
`${CLAUDE_PLUGIN_DATA}` into this file before you read it, and the shell default around it
lets a session that pins `MUBIT_CC_DATA_DIR` keep its pin — the same order every hook resolves
in. Pass the whole expression straight through. Do not turn it into an `ENV=… node …` prefix:
that is no longer a `node` command and will stop for a permission prompt.
`--label` is required: a short name the user can ask for later. The snapshot is whatever is on
…
Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.
GET https://markdownregistry.com/api/v1/artifacts/art_mxcjtlu7xnegckr2
GET https://markdownregistry.com/api/v1/resolve?ref=mubit-ai/plugins/checkpoint
GET https://markdownregistry.com/api/v1/blob/3b0bad3348b84a0f7f3a30f4cad2da5e9806305e02a0243d6859c4b3584373b9
Your agent does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
mubit-ai/plugins · integrations/claude-code/skills/activity/SKILL.md · List or export what this instance holds for a run; use when the user wants the audit record, not an answer.
mubit-ai/plugins · integrations/claude-code/skills/auth/SKILL.md · Sign in to Mubit and store an API key; use when the plugin reports auth_failed or a key was rotated.
mubit-ai/plugins · integrations/claude-code/skills/dashboard/SKILL.md · Open the local Mubit dashboard — turns, what was injected into each, what it earned, and every lesson's record; use…
mubit-ai/plugins · integrations/claude-code/skills/doctor/SKILL.md · Diagnose connectivity, memory health and stuck ingest; use when memory looks empty or the status line shows a failure.
mubit-ai/plugins · integrations/claude-code/skills/forget/SKILL.md · Delete a lesson, or down-weight one that is merely wrong; use when asked, after saying it cannot be undone.
mubit-ai/plugins · integrations/claude-code/skills/handoff/SKILL.md · Hand work to another agent through Mubit, list the handoffs open in this run, or answer one with a verdict; use when a…
mubit-ai/plugins · integrations/claude-code/skills/import/SKILL.md · Backfill Mubit memory from the Claude Code and Codex transcripts already on this machine, so a fresh install knows what…
mubit-ai/plugins · integrations/claude-code/skills/memory-health/SKILL.md · Report what is actually stored: counts, staleness, contradictions; use when the question is whether anything was ever…
mubit-ai/plugins · integrations/claude-code/skills/pin/SKILL.md · Pin a constraint for the rest of this run, shown on every prompt; use when a rule ends with the task, and remember for…
mubit-ai/plugins · integrations/claude-code/skills/recall/SKILL.md · Search Mubit memory for lessons, rules, facts or past work; use when the injected memory is not enough.
mubit-ai/plugins · integrations/claude-code/skills/reflect/SKILL.md · Extract lessons from this session's activity now; use when the user wants them banked before session end or asks what…
mubit-ai/plugins · integrations/claude-code/skills/remember/SKILL.md · Save one durable lesson, rule or preference; use when the user states a standing preference or an approach fails in a…
jmagly/aiwg · agentic/code/addons/aiwg-utils/skills/checkpoint/SKILL.md · Create, list, or recover mid-workflow checkpoints so interrupted work resumes from a known-good position
shweta-mishra-ai/tokenmizer · .claude-plugin/skills/checkpoint/SKILL.md · Save the current session to TokenMizer graph memory. Creates a persistent checkpoint with all tasks, decisions, files…
ymm-oss/fsl · .claude/skills/checkpoint/SKILL.md · Reconcile and save the current FSL task state before compaction, clearing, handoff, or ending substantial work.
ymm-oss/fsl · .agents/skills/checkpoint/SKILL.md · Reconcile tasks/active.md with Git, changed files, and observed verification before compaction, clearing, or handoff.
chainreactors/ioa · skills/checkpoint/SKILL.md · Human-in-the-loop review protocol. Use when execution reaches an approval boundary that requires human judgment before…
qwerfunch/cladding · plugins/antigravity/skills/checkpoint/SKILL.md · Record a feature checkpoint event pinning the current git HEAD plus a spec digest, so a later rollback can restore the…
qwerfunch/cladding · plugins/codex/skills/checkpoint/SKILL.md · Record a feature checkpoint event pinning the current git HEAD plus a spec digest, so a later rollback can restore the…
