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/ij5a/subrosa/checkpointnpx skills add ij5a/subrosa --skill checkpointgit clone --depth 1 https://github.com/ij5a/subrosaWhat 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 | $0.00075 | $0.02095 |
| Opus 5 | $0.00037 | $0.01047 |
| Sonnet 5 | $0.00015 | $0.00419 |
| Haiku 4.5 | $0.00007 | $0.00210 |
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.
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
-
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
-
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.mdinstead. -
Check existing memory before writing. Run
subrosa fact listfor curated facts. Runsubrosa 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.
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.
- 3d ago First seen · 106 lines · 75 tokens per session scan A d71daff323ad
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.
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.
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…
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…
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.
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.
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.