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 jkm-4314/claude-code-skills --skill session-updategit clone --depth 1 https://github.com/jkm-4314/claude-code-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/jkm-4314/claude-code-skills/session-update)<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/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/jkm-4314/claude-code-skills/session-update"><img src="https://agentmods.dev/badge/skills/jkm-4314/claude-code-skills/session-update.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 | $0.00033 | $0.01326 |
| Opus 5.5 | $0.00013 | $0.00530 |
| Sonnet 5.5 | $0.00007 | $0.00265 |
| Haiku 4.5 | $0.00003 | $0.00133 |
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 1mo 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 — 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-startfirst 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):
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.
- 1mo ago First seen · 172 lines · 33 tokens per session scan A 84012ff7eabe
session-update is a skill published in the GitHub repository jkm-4314/claude-code-skills (4 stars, last pushed 5mo ago), licensed MIT. It adds 33 tokens to every session and 1,326 once invoked, about $0.0001 per session on Opus 5.5. 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
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'.
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…
nav-compact
Clear conversation context while preserving knowledge via context marker. Use when user says "clear context", "start fresh", "done with this task", or when approaching token limits.
hive-mind-advanced
Queen-led collective-intelligence coordination with consensus mechanisms and persistent shared memory. Use when orchestrating a large swarm of agents under a lead coordinator, building consensus across agents, or maintaining durable cross-agent memory.
creator-productivity
Task management and workspace memory for creative work sessions. Manages a TASKS.md file for project tracking, a two-tier memory system (CREATOR.md + creator-memory/), and a daily sprint structure. Use when organizing creative projects, tracking content tasks, or starting a focused work session.
memory-prune
Manual reviewable prune of stale memory entries. Lists project entries older than 30 days with content preview; Frank decides per-entry [keep | archive | pin]. Keeps MEMORY.md under the auto-load 200-line truncation. Use when MEMORY.md exceeds 180 lines or session-end after a heavy work week.