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 skills add randommonicle/claude-skills --skill checkpoint-loggit clone --depth 1 https://github.com/randommonicle/claude-skillsWrote 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/skills/randommonicle/claude-skills/checkpoint-log)<a href="https://agentmods.dev/skills/randommonicle/claude-skills/checkpoint-log"><img src="https://agentmods.dev/badge/skills/randommonicle/claude-skills/checkpoint-log/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/skills/randommonicle/claude-skills/checkpoint-log"><img src="https://agentmods.dev/badge/skills/randommonicle/claude-skills/checkpoint-log.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 | $0.00113 | $0.00925 |
| Opus 5 | $0.00056 | $0.00463 |
| Sonnet 5 | $0.00023 | $0.00185 |
| Haiku 4.5 | $0.00011 | $0.00093 |
Grade A, and why
checkpoint-log 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 10d 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Checkpoint log
A handover note is written at the end of a session, so a session that dies unexpectedly takes its unwritten detail with it, and the next session inherits a compressed summary it has to re-derive. This skill moves the record to the commit boundary: every commit in a multi-commit unit carries a short checkpoint note, so the repository sits at a documented, resumable checkpoint after every commit. Layer: leaf (commit seam). Admitted by review rather than by the misses log — see Provenance — so candidate-tier until fires accumulate.
The rule
A multi-commit work unit keeps a live log entry per commit, staged with that commit, and closes only after an explicit item-by-item walk of its checklist.
How to apply
- The file.
WORKLOG.mdin the project root, append-only, one##heading per work unit. A project with an established worklog location uses that instead, consistently. - The unit opens with two things: a one-line goal, and the checklist of planned commits or tasks as checkboxes. plan-first produces this list; copying it here makes progress visible in the file, not only in chat.
- The per-commit entry is written before the commit and staged with the code: two to four sentences — what the commit did, the key decision and why it went that way, any deviation from the plan, any finding worth keeping. Tick the checklist item in the same edit. Long evidence goes in the commit body or the project's docs, never the log.
- Why inside the commit: any commit can then be checked out cold and the log explains how the work got there; a later session resumes from the last entry without re-deriving, and the closing summary is written from the log alone.
- Closing the unit: walk the checklist explicitly, item by item, before declaring it done — including the wiring steps that are easiest to skip: registrations and DI bindings, route tables and exports, config and environment entries, gitignore entries, migration catalog queries (db-migration-verification), doc updates, and deferred-item anchors planted where promised (flag-deferred-items). Only then write the closing summary from the log: what was built, what deviated, what was deferred and where its anchor is.
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.
- 10d ago First seen · 66 lines · 113 tokens per session scan A 3c742d12936b
checkpoint-log is a skill published in the GitHub repository randommonicle/claude-skills (23 stars, last pushed 3d ago), licensed Apache-2.0. It adds 113 tokens to every session and 925 once invoked, about $0.0006 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
create-pr
Creates a GitHub PR with a Linear-ticket-prefixed title and a decision-led, narrative description for prisma-next. Use when the user wants to create a pull request, open a PR, or submit changes for review.
git-commit
Generate well-formatted git commit messages following conventional commit standards.
repo-sync
Manage repo-sync on macOS for shared documents and team context. Use when asked what repo-sync does, to automatically sync a repo, add a repo to repo-sync, stop syncing or un-sync a repo, check sync health, configure repo-sync, uninstall it, or install and maintain its bundled agent skill. Ordinary one-time Git pulls…
mcore-split-pr
Split a PR into multiple PRs to reduce the number of required CODEOWNERS reviewer groups.
contributing
How to contribute to evlog, covering commit and PR conventions, changesets, the Definition of Done, testing rules, and the authored skills that walk through building a new adapter, enricher, framework integration, or map rule. Load this for any question about contributing, opening a PR, or adding something to the…
strict-tdd
Strict RED->GREEN->REFACTOR test-driven development with enforcement. Never write production code before a failing test. Atomic commits per TDD cycle.