session-save

A session-saving workflow for recording the current conversation in a dated Markdown file and updating its state in GitHub. Markdown is a plain-text format commonly used for notes and documentation.

In plain words
What is it for?
Use it when wrapping up a conversation, saving progress, switching topics, or running the session command.
Why use it?
It prevents important decisions, completed work, and open questions from being lost when a conversation ends or the topic changes.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/teejayen/arc/session-save
Any agent
npx skills add teejayen/arc --skill session-save
Clone the repo
git clone --depth 1 https://github.com/teejayen/arc

Made for: Claude Code, Codex.

Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 654 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00045 $0.00654
Opus 5 $0.00023 $0.00327
Sonnet 5 $0.00009 $0.00131
Haiku 4.5 $0.00005 $0.00065

Measured yesterday against content hash af68d54ef134, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

session-save 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 yesterday.

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.

.claude/skills/session-save/SKILL.md · 108 lines

How it starts

The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Session Save

Save the current conversation session and update state files.

When to Use

  • User says "let's wrap up", "save this", "I'm done", or runs /session
  • Natural end of a conversation thread
  • Before switching to a significantly different topic

Execution Steps

Step 1: Gather context

date "+%Y-%m-%d %H:%M"

Step 2: Create session file

Location: sessions/YYYY-MM-DD-HHMM-topic.md

---
title: "Session: [Brief descriptive title]"
created: YYYY-MM-DD
tags: [session, relevant-area-tags]
---

# Session: [Brief title]

**Date:** YYYY-MM-DD HH:MM
**Topics:** keyword, keyword, keyword

## Summary
[2-3 paragraphs - what was explored, problems discussed, thinking developed]

## What Got Done
- Concrete outcome 1
- Concrete outcome 2
[Be specific: "Created areas/project/analysis.md" not "discussed project"]

## Key Insights
- Insight that emerged from the conversation
- Pattern noticed or connection made

## Decisions Made
[Remove section if none]
- Decision with brief rationale

## Open Questions
[Remove section if none]
- Question still needing resolution

## Next
[Remove section if none]
- Follow-up to explore

## Related
- [[relevant-notes]]

Step 3: Update journal.jsonl

Append to state/journal.jsonl:

{"t": "YYYY-MM-DDTHH:MM", "topics": ["topic1", "topic2"], "energy": "high|medium|low", "areas": ["area1", "area2"], "summary": "One-line session summary"}

Step 4: Update focus.md if needed

If priorities shifted during the session, update state/focus.md to reflect current thinking.

Step 5: Update session-context.json

Write to state/session-context.json:

{
  "last_session": "YYYY-MM-DD HH:MM",
  "last_topic": "topic",
  "open_threads": ["thread1", "thread2"],
  "next_suggested": "What to pick up next time"
}

Step 6: Git commit and push

git add -A
git commit -m "Session: [topic] - YYYY-MM-DD HH:MM"
git push

Step 7: Quote send-off (optional)

If quotes.md exists, pick a random quote:

Read the full file on GitHub · 108 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. yesterday First seen · 108 lines · 45 tokens per session scan A af68d54ef134

Subscribe to this mod's changes

session-save is a skill published in the GitHub repository teejayen/arc (5 stars, last pushed 7mo ago), licensed MIT. It adds 45 tokens to every session and 654 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

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens