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.
git clone --depth 1 https://github.com/bakabaka91/claude-batonWrote 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/commands/bakabaka91/claude-baton/memo-checkpoint)<a href="https://agentmods.dev/commands/bakabaka91/claude-baton/memo-checkpoint"><img src="https://agentmods.dev/badge/commands/bakabaka91/claude-baton/memo-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/commands/bakabaka91/claude-baton/memo-checkpoint"><img src="https://agentmods.dev/badge/commands/bakabaka91/claude-baton/memo-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 | $0.00557 |
| Opus 5 | $0.00000 | $0.00279 |
| Sonnet 5 | $0.00000 | $0.00111 |
| Haiku 4.5 | $0.00000 | $0.00056 |
Grade A, and why
memo-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 8d 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.
What it actually says
Save session state before context loss.
Important: Run all git commands exactly as written below — do NOT add -C flags or path arguments. The working directory is already the project root.
Steps
-
Detect the project from the current working directory.
-
Capture git state by running these bash commands:
git branch --show-currentgit status --shortgit diff --name-only HEADgit log --oneline -10(this becomes the git_snapshot)
-
Check if any plan documents exist (PLAN.md, docs/*.md specs, roadmaps). If one is being actively worked on, note the file path and the current phase/step (e.g. "docs/v2-plan.md Phase 2 Step 3").
-
Summarize the session state from the conversation context:
- what_was_built: what was accomplished this session
- current_state: where things stand now
- next_steps: what should happen next
- decisions: key choices made and WHY
- blockers: anything blocking progress
- plan_reference: file path and section of the active plan document (e.g. "docs/v2-plan.md Phase 2 Step 3"), or omit if no plan is active
- learnings: review the conversation for corrections, failures, and wrong assumptions. For each, write a short actionable statement. Examples:
- "User corrected: always run tests before committing"
- "Assumed API returns array but it returns object"
- "Build failed because forgot to update imports after rename" If nothing went wrong this session, use an empty array.
-
Call the
save_checkpointMCP tool with all fields:- what_was_built
- current_state
- next_steps
- decisions
- blockers
- plan_reference (from step 3, if applicable)
- branch (from step 2)
- uncommitted_files (array of lines from git status --short)
- git_snapshot (from git log --oneline -10)
- learnings (array of strings from step 4)
-
Print structured confirmation:
💾 Checkpoint saved — safe to /compact or /clear
🌿 Branch: [branch name]
📍 State: [current_state summary]
🎯 Next: [next_steps]
📝 Uncommitted: [count] files
📜 Commits this session:
[List commits made during THIS conversation from your context — or "No commits this session" if none were made]
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.
- 8d ago First seen · 55 lines · 0 tokens per session scan A 297319b26fcf
memo-checkpoint is a command published in the GitHub repository bakabaka91/claude-baton (25 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 557 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 2026-09-01.
Other commands, from other repositories
sync
Sync memories with git remote (deprecated - SQLite is now authoritative).
unforgit
Show Unforgit repository-memory status and suggest the next useful action.
unforgit-curate
Review and improve Unforgit memory quality.
unforgit-health
Inspect Unforgit memory health.
unforgit-recall
Search Unforgit memory for context relevant to the user's current request.
session-report
Capture what changed this session and why, scoped to the current branch. Read by ship verbs when synthesizing the commit message; deleted after a successful commit.