checkpoint

A memory-saving command that records important facts from the current conversation before you clear or shorten the chat.

In plain words
What is it for?
Use it before /clear or /compact to update Subrosa's stored memory, archive stale entries, and report whether the conversation is safe to remove.
Why use it?
It reduces the risk of losing user preferences, project context, decisions, and useful references during a context wipe.

Skill for Claude CodeCodex

Part of the subrosa plugin — 2 skills, 5 hooks shipped together

Install

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.

agentmods
npx agentmods add skills/ij5a/subrosa/checkpoint
Any agent
npx skills add ij5a/subrosa --skill checkpoint
Clone the repo
git clone --depth 1 https://github.com/ij5a/subrosa

Made for: Claude Code, Codex.

Or install subrosa, the plugin that ships this one along with the rest of its 2 skills, 5 hooks.

Per session 75 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,095 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00075 $0.02095
Opus 5 $0.00037 $0.01047
Sonnet 5 $0.00015 $0.00419
Haiku 4.5 $0.00007 $0.00210

Measured 3d ago against content hash d71daff323ad, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 3d 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.

skills/checkpoint/SKILL.md · 106 lines

How it starts

The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.

checkpoint: flush memory before a context wipe

The user is about to run /clear or /compact. Without a save, /clear loses this session and /compact can drop key details. Scan the conversation, save durable facts, and report whether it is safe to wipe.

MEMORY.md is generated from the facts database (~/.claude/subrosa/memory.db). Never hand-edit it. Write leaf files and register facts. The generator rebuilds the byte-budgeted index. Use the subrosa CLI for all commands (subrosa fact …, subrosa generate, subrosa search …). If subrosa is not on PATH, the plugin bootstrap installs it at ~/.claude/subrosa/bin/subrosa.

Procedure

  1. Scan the full conversation. Review every turn, not only the last. Classify each candidate as one of these four types:

    • user: role, preferences, knowledge, and working context
    • feedback: corrections and validated approaches. Include the reason for both.
    • project: ongoing work, deadlines, motivations, roles, and reasons
    • reference: pointers to external systems, dashboards, and ticket projects
  2. Apply the exclusion list strictly. Never save:

    • Code patterns, conventions, file paths, or architecture
    • Git history, commit hashes, blame info, or PR numbers
    • Debugging recipes. The fix is in code, and the reason is in the commit message.
    • Anything already covered by CLAUDE.md
    • Ephemeral state, such as task details, investigation chains, or bare ticket numbers
    • Routine activity logs. Save only what was surprising or non-obvious.

    These exclusions apply even when the user says, "save this." Ask what was non-obvious. Ask if they meant CLAUDE.md instead.

  3. Check existing memory before writing. Run subrosa fact list for curated facts. Run subrosa search "<keyword>" for the full transcript archive. Read related leaf files. For each candidate:

    • A correct similar fact exists: skip it.
    • A stale similar fact exists: update it in place.
    • No similar fact exists: write a new one.

Read the full file on GitHub · 106 lines

Changes

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.

  1. 3d ago First seen · 106 lines · 75 tokens per session scan A d71daff323ad

Subscribe to this mod's changes

checkpoint is a skill published in the GitHub repository ij5a/subrosa (7 stars, last pushed 3d ago), licensed MIT. It adds 75 tokens to every session and 2,095 once invoked, about $0.0004 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 2026-08-31.

Related

Other skills, from other repositories

writing-release-notes

Use when preparing, refreshing, backfilling, or redrafting a release-notes page under docs/releases/ before opening a normal review pull request.

pvliesdonk/markdown-vault-mcp · 35 tokens

code-review

Use before opening a pull request, marking one ready for review, or pushing further commits to a branch with an open pull request — or when asked to review a diff or a PR. Reviews the cumulative diff against the project's written commitments and reports evidence-grounded findings; works with any coding agent and needs…

pvliesdonk/markdown-vault-mcp · 68 tokens

authoring-issues-prs

Use when filing a bug, opening or creating a GitHub issue, drafting an epic or ticket, writing up a finding or review observation worth tracking, or opening a pull request for this repository. Routes the change to the right repo first (library / template / domain), picks the right issue form, links epic children as…

pvliesdonk/markdown-vault-mcp · 86 tokens

releasing

Use before any release work: the trunk release model, the unstable edge channel, the prepare/release/promotion machinery, release-notes pages, the pre-release artifact smoke test, and, when the plugin channel is enabled, the Claude Code plugin channel.

pvliesdonk/markdown-vault-mcp · 54 tokens

config-contract

Use when adding a domain configuration field, env var, Dockerfile extension, mcpb install-screen entry, or release-manifest stamp: the sentinel-based config and customization contract.

pvliesdonk/markdown-vault-mcp · 39 tokens

tool-registration

Use when adding, renaming, or documenting an MCP tool: the registration checklist, the getserverinfo tool, tool icons, and the public import-surface guard.

pvliesdonk/markdown-vault-mcp · 37 tokens