session-update

session-update is a skill for Claude Code from jkm-4314/claude-code-skills. It costs 33 tokens per session (1,326 once invoked), scanned A, original, MIT.

A session checkpoint tool that records current work in a project's session log. It is designed for use before clearing a conversation or handing work to another agent.

In plain words
What is it for?
Use it to update today's SESSION_LOG.md entry with work completed since the last checkpoint and the current repository state.
Why use it?
It preserves decisions, reasoning, blockers, and uncommitted progress that Git history alone does not capture.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Good fit Use it to update today's SESSION_LOG.md entry with work completed since the…

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jkm-4314/claude-code-skills/session-update
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 jkm-4314/claude-code-skills --skill session-update
Clone the repo
git clone --depth 1 https://github.com/jkm-4314/claude-code-skills

Made for: Claude Code.

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-update

README.md
[![agentmods](https://agentmods.dev/badge/skills/jkm-4314/claude-code-skills/session-update.svg)](https://agentmods.dev/skills/jkm-4314/claude-code-skills/session-update)
Your own site
<a href="https://agentmods.dev/skills/jkm-4314/claude-code-skills/session-update"><img src="https://agentmods.dev/badge/skills/jkm-4314/claude-code-skills/session-update.svg" alt="Measured on agentmods" height="20"></a>
Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,326 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00033 $0.01326
Opus 5 $0.00016 $0.00663
Sonnet 5 $0.00007 $0.00265
Haiku 4.5 $0.00003 $0.00133

Measured 7d ago against content hash 84012ff7eabe, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

session-update 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 7d 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.

session-update/SKILL.md · 172 lines

How it starts

The opening of the file, as written. The whole thing — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Session Update (Checkpoint)

You are capturing work-in-progress into today's SESSION_LOG.md entry before context is cleared or handed off. The goal: preserve what THIS Claude instance knows — decisions, reasoning, blockers, dead-end approaches — before it's lost. Git alone can't recover any of that.

Primary use case: run this right before /clear. Secondary: mid-session checkpoint after a chunk of work.

Step 1: Verify Today's Entry Exists

Read .claude/SESSION_LOG.md. Find the top entry.

If top entry's date == today (MM-DD-YYYY format; legacy YYYY-MM-DD is equivalent): continue to Step 2.

If no today entry: tell the user:

"No session-start stub exists for today. Run /session-start first to create today's entry, then re-run session-update."

Stop. Do not create the entry here — that's session-start's job.

Step 2: Determine Scope of "New Work"

Look inside today's entry for a tracking marker of the form:

<!-- last-update: <git-hash> -->
  • If present: new work = commits since <git-hash> + current uncommitted changes + this conversation's work not yet in the entry.
  • If absent: new work = commits since today's start that aren't obviously reflected in the entry + current uncommitted changes + this conversation's work.

Collect inputs:

# Current HEAD (for the new marker)
git rev-parse --short HEAD

# Commits since last marker (if marker exists):
git log --oneline --all <marker-hash>..HEAD

# Or commits since today's start (if no marker):
git log --oneline --all --since="6am"

# Uncommitted state
git status --short
git diff --stat

Also mine this conversation's context for things git won't show:

  • Decisions made and why (especially alternatives rejected)
  • Approaches tried that didn't work (dead ends)
  • Blockers discovered
  • WIP reasoning — what was about to happen next

Step 3: Draft Section Additions

Draft bullets/rows for these four sections (merge into whatever already exists in the entry — don't replace):

Read the full file on GitHub · 172 lines

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. 7d ago First seen · 172 lines · 33 tokens per session scan A 84012ff7eabe

Subscribe to this mod's changes

session-update is a skill published in the GitHub repository jkm-4314/claude-code-skills (4 stars, last pushed 3mo ago), licensed MIT. It adds 33 tokens to every session and 1,326 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

shipkit-work-memory

Log session progress and save resume state. Infers from conversation and git. Triggers: 'log progress', 'session summary', 'checkpoint', 'save progress', 'end session'.

stefan-stepzero/shipkit · 42 tokens

shipkit-claude-md

Update CLAUDE.md with learnings, preferences, or project context. Use when user says "update claude.md", "add to claude.md", or wants to persist something.

stefan-stepzero/shipkit · 45 tokens

compact-manual

Claude Code skill for deterministic context compaction. Compresses the current Claude Code session to the clipboard for a manual rewind+paste workflow. A deterministic alternative to /compact that extracts literal dialog and truncates only tool outputs — no LLM summarization. Use when the user says 'compact the…

mario-hernandez/claude-compact-manual · 81 tokens

session-manager

A fallback skill for recording development sessions and restoring project context from an Obsidian vault, a folder of linked notes. It handles explicit resume, handoff, status, and end-of-session requests when automatic capture is unavailable.

Enakoneschniy/claude-dev-stack · 108 tokens

pause

Use when you need the Codex Copilot equivalent of Claude Copilot /pause: preserve current work state in tc and memory before context switching.

Everyone-Needs-A-Copilot/claude-copilot · 31 tokens

reflect

Use when you need the Codex Copilot equivalent of Claude Copilot /reflect: capture lessons, decisions, and improvement notes after a work session.

Everyone-Needs-A-Copilot/claude-copilot · 32 tokens