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
## Step 0 — resolve the binary
No environment variable carries this plugin's path under Codex. Codex lists each skill with the
absolute path of its `SKILL.md`; **this file** is at `<plugin-root>/skills/checkpoint/SKILL.md`, so
the binary is two directories above it:
```
<plugin-root>/bin/admin.mjs
```
Resolve that to an absolute path from this file's own location and use it in every command
below. Do not write `${CLAUDE_PLUGIN_ROOT}`: Codex sets no plugin-root variable of any
spelling, so the shell expands it to nothing and `node /bin/admin.mjs` fails with ENOENT.
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 <plugin-root>/bin/admin.mjs checkpoint --label "<short name>" <<'SNAPSHOT'
<the snapshot>
SNAPSHOT
```
`--label` is required: a short name the user can ask for later. The snapshot is whatever is on
stdin (`--file <path>` reads it from a file instead). The script prints the checkpoint id it
was given back; relay it. It does not call an MCP tool — `mubit_checkpoint` left the default
tool surface so that a session pays nothing to list it, and this script is how the skill
…
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_o25eko3qserzpjx6
GET https://markdownregistry.com/api/v1/resolve?ref=mubit-ai/plugins/checkpoint
GET https://markdownregistry.com/api/v1/blob/71a9dd68bd888fbe2bba0bcb8c2cc59cf8f2637fa24c95e45a55183ba7ed7080
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/checkpoint/SKILL.md · Save a named verbatim snapshot of this run; use when the user is about to do something risky.
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…
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…
