session-checkpoint

session-checkpoint is a skill for Claude Code, Codex from AlexZio00/sovereign-skills. It costs 44 tokens per session (12,858 once invoked), scanned C, original, MIT.

A session-saving skill that records the important context needed to continue work later. It extracts next steps, writes a handoff, updates memory, and checks that the saved information was preserved.

In plain words
What is it for?
Use it before ending a session, switching tasks, or saving progress for another session to resume.
Why use it?
It reduces the chance of losing decisions, unfinished work, or lessons when a session ends, changes tasks, or runs out of context.

Skill for Claude CodeCodex

Written for Claude Code and Codex: user-invocable in frontmatter, but also agents/openai.yaml present. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions subagents.

Part of the session-checkpoint plugin — 1 skill shipped together

Good fit Use it before ending a session, switching tasks, or saving progress for another session to resume.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/alexzio00/sovereign-skills/session-checkpoint
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.

Any agent
npx skills add AlexZio00/sovereign-skills --skill session-checkpoint
Clone the repo
git clone --depth 1 https://github.com/AlexZio00/sovereign-skills

Made for: Claude Code, Codex.

Or install session-checkpoint, the plugin that ships this one along with the rest of its 1 skill.

Wrote 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.

agentmods badge for session-checkpoint

README.md
[![agentmods](https://agentmods.dev/badge/skills/alexzio00/sovereign-skills/session-checkpoint/github.svg)](https://agentmods.dev/skills/alexzio00/sovereign-skills/session-checkpoint)
Your own site
<a href="https://agentmods.dev/skills/alexzio00/sovereign-skills/session-checkpoint"><img src="https://agentmods.dev/badge/skills/alexzio00/sovereign-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.

agentmods 80×15 button for session-checkpoint

Your own site · 80×15
<a href="https://agentmods.dev/skills/alexzio00/sovereign-skills/session-checkpoint"><img src="https://agentmods.dev/badge/skills/alexzio00/sovereign-skills/session-checkpoint.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 44 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 12,858 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00044 $0.12858
Opus 5 $0.00022 $0.06429
Sonnet 5 $0.00009 $0.02572
Haiku 4.5 $0.00004 $0.01286

Measured 4d ago against content hash 1e8d8ec47aea, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade C, and why

session-checkpoint scanned grade C with 1 finding 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 4d ago.

The scan reads SKILL.md. This mod also ships 5 executable files (scripts/ct_promotion_queue.py, scripts/handoff_attestation.py, scripts/test_ct_promotion_queue.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

To delete: rm -rf ~/.claude/.harness/snapshots/<skill-name>/<YYYY-MM-DD-*>/
session-checkpoint/SKILL.md · 764 lines

How it starts

The opening of the file, as written. The whole thing — 764 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Session Checkpoint

Dominant Variable

Has it been clearly identified in this session what the next session absolutely must know? If identification is incomplete, dive deeper into Phase 1 — compaction comes after that.

Key Assumptions

  1. Handoff file path is writablememory/session-handoff-LATEST.md. If broken: verify path then fail-fast (Error Recovery: tool_failure).
  2. MEMORY.md / context-log.md exist — Phase 3 storage targets. If broken: create files then proceed. If creation fails, report to user.
  3. Session conversation is sufficient for Phase 1 extraction — minimum 5+ exchanges. If broken: apply Discard If (session too short) or generate minimal handoff only.
  4. Reflexion extraction (Phase 1.7) is possible — conversation exists with failure/dissatisfaction signals. If broken: "no new lessons" handling.
  5. Transcript tool-call output may be truncated or terminal, not confirmed — a timed-out or killed tool call can leave a bare terminal signal in the transcript (e.g. an exit code like 143) with no corresponding stdout. That signal alone does not establish what actually happened. If broken: do not record it in the handoff or memory as a settled fact — tag it [UNVERIFIED] and name what's missing (e.g. "exit 143, no stdout captured").

Trigger

  • /session-checkpoint
  • "checkpoint"
  • "compact"
  • "체크포인트"
  • "핸드오프 저장"
  • "컴팩트 전에"

Discard If

  • Session has no code changes and no pending decisions → compaction unnecessary
  • Checkpoint already completed this session → duplicate run unnecessary
  • Only simple handoff update desired, not compaction → modify memory/session-handoff-LATEST.md directly

Core Principles

  • Handoff is single file only (memory/session-handoff-LATEST.md) — no version numbers
  • Completed items are deleted, only new items added
  • Next session should be able to start by reading this one file alone
  • Preservation verification mandatory before compaction

Phase 1: Deep Context Extraction

Read the full file on GitHub · 764 lines

Files

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.

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. 4d ago Changed · +15 lines 1e8d8ec47aea
  2. 12d ago First seen · 749 lines · 44 tokens per session scan C 38744e829758

Subscribe to this mod's changes

session-checkpoint is a skill published in the GitHub repository AlexZio00/sovereign-skills (128 stars, last pushed 4d ago), licensed MIT. It adds 44 tokens to every session and 12,858 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

retro

Mine review artifacts for recurring patterns and write project learnings.

backspace-shmackspace/claude-devkit · 14 tokens

nobrainer-review

Use when the owner says nb-review, deep-audit, deep-code-review, or deep-autoreview; explicitly requests an evidence-gated CLOSEOUT, adversarial BUGHUNT or RELEASEGATE; or needs final findings filtered to verified actionable defects. Use nobrainer-build for ordinary implementation and correction work.

nobrainer-tech/nobrainer-tech-skills · 67 tokens

use-cli-recall

A command-line tool for searching records of earlier coding sessions and checking the current code with fast file-search tools.

thkt/dotclaude · 26 tokens

fec-image-generation

A workflow for creating or editing images and diagrams, from posters and product mockups to academic graphics, illustrations, and system maps. For text-heavy technical diagrams, it can use editable sources such as Mermaid, SVG, HTML, or canvas before exporting an image.

bovinphang/frontend-craft · 256 tokens

nobrainer-wiki

Use when the owner says nb-wiki, nb-add, nb-get, nb-tidy, or llm-wiki; asks to create or query a wiki, save durable knowledge, or safely audit and maintain a Markdown knowledge base across projects or sessions; do not use for transient task state.

nobrainer-tech/nobrainer-tech-skills · 65 tokens

learning

Capture a durable project lesson in Agent Runway memory. Use when the developer says "learning", "remember this", "save this lesson", "add to memory", or when a completed task reveals a recurring decision, failure, convention, or guardrail that should influence future work.

adonai-labs/agent-runway · 58 tokens