arc: Skill for Claude Code

.claude/skills/session-save/SKILL.md

session-save is a skill for Claude Code from teejayen/arc. It costs 45 tokens per session (654 once invoked), scanned A, original, MIT.

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 Code

Written for Claude Code: allowed-tools in frontmatter.

This is teejayen/arc's own configuration. It tells Claude Code how to work on arc itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything arc configures →

View source ↗ teejayen/arc
Reuse

Borrowing it

Nothing to install: this file belongs to teejayen/arc. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/teejayen/arc/main/.claude/skills/session-save/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/teejayen/arc

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-save

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/teejayen/arc/session-save"><img src="https://agentmods.dev/badge/skills/teejayen/arc/session-save.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
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. 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 $0.00045 $0.00654
Opus 5.5 $0.00018 $0.00262
Sonnet 5.5 $0.00009 $0.00131
Haiku 4.5 $0.00005 $0.00065

Measured 2mo ago against content hash af68d54ef134, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 2mo 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.

.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. 2mo ago 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 9mo ago), licensed MIT. It adds 45 tokens to every session and 654 once invoked, about $0.0002 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.

Related

session-save compared with skills from other repositories

session-save next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
session-saveteejayen/arcSkill59mo agoMITA45Claude Code
create-prprisma/ormSkill48kyesterdayApache-2.0A48Claude Code, Codex
git-commitThinkInAIXYZ/deepchatSkill6.4kyesterdayApache-2.0A15Claude Code, Codex
repo-syncdavidondrej/skillsSkill4.3k3d agoMITA25Claude Code, Codex
engineer-bot-opsmakecindy/cindySkill9.3kyesterdayApache-2.0A57Claude Code, Codex
mcore-split-prNVIDIA/skillsSkill3.9kyesterdayApache-2.0A25Claude Code
git-commit-writermergisi/awesome-openclaw-agentsSkill4.1k2d agoMITA53Claude Code, Codex