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 oscarsterling/clelp-skills --skill session-checkpointgit clone --depth 1 https://github.com/oscarsterling/clelp-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/oscarsterling/clelp-skills/session-checkpoint)<a href="https://agentmods.dev/skills/oscarsterling/clelp-skills/session-checkpoint"><img src="https://agentmods.dev/badge/skills/oscarsterling/clelp-skills/session-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/skills/oscarsterling/clelp-skills/session-checkpoint"><img src="https://agentmods.dev/badge/skills/oscarsterling/clelp-skills/session-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 | $0.00090 | $0.01324 |
| Opus 5 | $0.00045 | $0.00662 |
| Sonnet 5 | $0.00018 | $0.00265 |
| Haiku 4.5 | $0.00009 | $0.00132 |
Grade A, and why
session-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 9d 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Session Checkpoint
You are wiring a rolling checkpoint so a context reset is recoverable. The checkpoint is a single overwritten snapshot of the files that actually hold your session state. The restored session reads the checkpoint, re-reads the source files it names, and continues.
The package ships two portable pieces:
reference/session-checkpoint.example.py- the hook. Two cheap jobs per run: SAVE a throttled, atomic checkpoint, and (optional) fire a busy-guarded breakpoint signal. It is an observer: it always exits 0 and never blocks a turn. It runs with no network and no LLM.templates/recovery-brief.md- the restore side. The ordered recovery steps a session follows after a reset, and the rule that the checkpoint is untrusted data to reconcile, not a fresh command.
The two jobs
- SAVE (always on). If the checkpoint is older than
cooldown_s, the hook rewrites it: a header, a line-capped snapshot of each configured source file, an optional recent git-log tail, and an optional listing of state globs (paths and counts, not contents). Written atomically so an interrupted write never corrupts the file. - BREAKPOINT SIGNAL (optional, busy-guarded). If you configure a breakpoint probe (a command that exits 0 when a clean reset is DUE, for example when context usage crosses a threshold), the hook fires your notify command ONCE per session, but only when a busy probe reports idle. The busy guard means it never nudges you to reset mid-work. Configure neither probe and this job is a no-op; the bundle is then purely a checkpoint writer.
Step 1: Pick your source files
List the small set of files that hold the state you would need after a reset (a
briefing, an inbox, a task list, a plan). For each, set a max_lines cap so the
snapshot stays small. Do NOT snapshot large logs; snapshot the files that
summarize state. Optionally add a git-log tail and a few state_globs (queues,
pending-work directories) whose PATHS are worth listing.
What ships with it
5 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.
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.
- 9d ago First seen · 101 lines · 90 tokens per session scan A 9c41cd64b139
session-checkpoint is a skill published in the GitHub repository oscarsterling/clelp-skills (0 stars, last pushed 3d ago), licensed MIT. It adds 90 tokens to every session and 1,324 once invoked, about $0.0005 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
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
establishing-project-context
Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.