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 HsuanYuLee/polaris --skill checkpointgit clone --depth 1 https://github.com/HsuanYuLee/polarisWrote 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/hsuanyulee/polaris/checkpoint)<a href="https://agentmods.dev/skills/hsuanyulee/polaris/checkpoint"><img src="https://agentmods.dev/badge/skills/hsuanyulee/polaris/checkpoint.svg" alt="Measured on agentmods" 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 | $0.00121 | $0.00717 |
| Opus 5 | $0.00060 | $0.00358 |
| Sonnet 5 | $0.00024 | $0.00143 |
| Haiku 4.5 | $0.00012 | $0.00072 |
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 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
Checkpoint
checkpoint 保存、恢復、列出長 session 的工作狀態，讓 context compression 或換 session
後能接回 branch、ticket、phase、next action。
Contract
Checkpoint 是 session continuity tool，不是 planning、triage、或 implementation skill。 它只寫 workspace memory / timeline 類的 local state，不替下游 skill 決定 scope，也不自動切 branch。
Mode Routing
| User says | Mode | Reference |
|---|---|---|
checkpoint, 存檔, save checkpoint, save state |
save | checkpoint-save-flow.md |
resume, 恢復, resume checkpoint, 接回去 |
resume | checkpoint-resume-list-flow.md |
list checkpoints, 列出存檔, show checkpoints |
list | checkpoint-resume-list-flow.md |
Ambiguous input defaults to save.
Reference Loading
| Situation | Load |
|---|---|
| Any run | polaris-project-dir.md, session-timeline.md |
| Save | checkpoint-save-flow.md, checkpoint-carry-forward-flow.md |
| Resume / list | checkpoint-resume-list-flow.md |
Hard Rules
- Save must capture branch, git status summary, ticket, todo disposition, phase, next action, and recent timeline context.
- 回報 checkpoint saved 前，carry-forward validation 必須通過。
- Resume verifies the checkpoint branch exists before suggesting a switch.
- 未取得使用者明確指示前，不切 branch、不 stash、不 rewrite memory。
- 不可默默丟掉 pending items；每項都要標記 done、carry-forward、或 dropped。
Completion
Save 回傳 branch、ticket、phase、next action、resume phrase。Resume 回傳 checkpoint timestamp、branch、ticket、可取得時的 current status、next action。List 回傳 recent checkpoint rows。
Step 2.5 — L2 Deterministic Check: cross-session-carry-forward
Save mode 的 carry-forward gate 由 checkpoint-carry-forward-flow.md 執行；必須呼叫
.claude/skills/checkpoint/scripts/check-carry-forward.sh，通過後才可回報 checkpoint saved。
What ships with it
7 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/checkpoint-carry-forward-flow.md 1.2 KB
- references/checkpoint-resume-list-flow.md 1.3 KB
- references/checkpoint-save-flow.md 1.7 KB
- references/polaris-project-dir.md 1.3 KB
- references/session-timeline.md 3.9 KB
- scripts/check-carry-forward.sh 14 KB runs code
- scripts/polaris-timeline.sh 7.4 KB runs code
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 · 79 lines · 121 tokens per session scan A 33a368e18c47
checkpoint is a skill published in the GitHub repository HsuanYuLee/polaris (5 stars, last pushed yesterday), licensed MIT. It adds 121 tokens to every session and 717 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
i-have-adhd
Shape output for a reader with ADHD: lead with the next action, number multi-step work, restate state across turns, suppress tangents, give specific time estimates, make wins visible. Invoke with /i-have-adhd; stays on until "stop adhd mode".
update-turbo
Update installed Turbo skills from the local repo with a dynamic changelog, conflict resolution for customized skills, and guided user experience. Use when the user asks to "update turbo", "update turbo skills", "reinstall turbo", or "upgrade turbo".
herdr
Control Herdr, the terminal multiplexer for coding agents. Use when the user mentions Herdr or another skill delegates pane control, including concise pane naming, inspection, commands, and agents. Integrates with vd:worktree, vd:codex-workflow, and vd:ultracook. Requires HERDRENV=1.
gws
Manage Google Workspace from the CLI: Gmail, Drive, Calendar, Sheets, Docs, Slides, Tasks, Chat, and audit reports via the official gws command, with multi-account support through per-account config dirs. Use when the user mentions gmail, drive, calendar, sheets, docs, workspace, gws, email, files, events, or names a…
superwhisper
Operate the official Superwhisper CLI and MCP to search or read dictation history, diagnose pronunciation and raw-versus-processed transcription errors, detect unwanted expansion of short utterances, inspect usage, build standups or commitment reviews, and manage vocabulary or snippets with approval. Use when the user…
bug-fix
Regression-first workflow for fixing a defect whose cause is known. Reproduce the confirmed defect, fix the root cause minimally, protect it with a regression test, and verify. If the root cause is still unknown, use the debugging skill first.