session-cut

session-cut is a skill for Claude Code, Codex from brenbuilds1/cutweight. It costs 71 tokens per session (387 once invoked), scanned A, original, MIT.

A guide for deciding when to end a long coding-agent session and start a fresh one. It explains when to use /clear, /compact, or a handoff note for continuing the same work.

In plain words
What is it for?
Use it to spot session fatigue, choose between clearing and compacting, and prepare a short handoff before continuing work in a new session.
Why use it?
Long conversations resend more context and can make the agent slower, forgetful, or distracted. Cutting at the right time reduces that accumulated context and preserves the important decisions.

Skill for Claude CodeCodex

Written for Claude Code and Codex: shipped in a Claude Code plugin, but also agents/openai.yaml present.

Part of the cutweight plugin — 5 skills shipped together

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/brenbuilds1/cutweight/session-cut
Any agent
npx skills add brenbuilds1/cutweight --skill session-cut
Clone the repo
git clone --depth 1 https://github.com/brenbuilds1/cutweight

Made for: Claude Code, Codex.

Or install cutweight, the plugin that ships this one along with the rest of its 5 skills.

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-cut

README.md
[![agentmods](https://agentmods.dev/badge/skills/brenbuilds1/cutweight/session-cut.svg)](https://agentmods.dev/skills/brenbuilds1/cutweight/session-cut)
Your own site
<a href="https://agentmods.dev/skills/brenbuilds1/cutweight/session-cut"><img src="https://agentmods.dev/badge/skills/brenbuilds1/cutweight/session-cut.svg" alt="Measured on agentmods" height="20"></a>
Per session 71 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 387 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 5.1 $0.00071 $0.00387
Opus 5 $0.00036 $0.00193
Sonnet 5 $0.00014 $0.00077
Haiku 4.5 $0.00007 $0.00039

Measured 5d ago against content hash 6cd5c0694bf2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

session-cut 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 5d 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.

skills/session-cut/SKILL.md · 44 lines

What it actually says

Session Cut

Every message you send re-sends the conversation so far. The longer the session, the heavier each message gets, and the older context starts working against you. Knowing when to cut a session saves more tokens than any single trim.

The Calls

  • One task, one session. Starting an unrelated task in an old session makes the new task carry the old one's weight.
  • /clear between unrelated tasks. It is the cheapest reset there is.
  • /compact only to continue the SAME task past context limits. Compaction is a summary; treat it as lossy, because it is.
  • Fresh session with a handoff note beats a compacted haze. Before you clear, have the agent write five lines: what was done, what is next, which files matter. Paste that into the new session.

The Tells

Cut the session when:

  • The agent re-reads files it already read this session.
  • It forgets or contradicts a decision made earlier in the session.
  • Replies slow down or drift off the task you actually asked for.
  • The work left is unrelated to the transcript behind it.

Hard Rules

  • Never /compact as a reflex. Ask first: is this the same task?
  • The handoff note gets written before the clear, not remembered after.
  • If the agent is fighting the context instead of the problem, cut the session. Reset.
Files

What ships with it

1 file 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. 5d ago First seen · 44 lines · 71 tokens per session scan A 6cd5c0694bf2

Subscribe to this mod's changes

session-cut is a skill published in the GitHub repository brenbuilds1/cutweight (2 stars, last pushed 1mo ago), licensed MIT. It adds 71 tokens to every session and 387 once invoked, about $0.0004 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

save-progress

Save current project task progress to local task state file for cross-session continuity. Use when the user asks to save progress, uses an equivalent localized trigger phrase, the session is interrupted, or the user wants to resume work later. Writes to .claude/project-task-state.json so next session can load it via…

KimYx0207/Meta_Kim · 65 tokens

daily-journal

A passive daily work journal that Claude keeps FOR you so you never have to write it yourself. Append short entries after meaningful work (what was done, what you focused on, artifacts touched) to 01-daily/journal/YYYY-MM-DD.md. Run a guided reflection at night or in the morning. Use when you run /daily-journal, say…

huytieu/COG-second-brain · 107 tokens

general

Handle everyday conversation, answer questions, manage files, take notes, run scripts, and maintain persistent memory across sessions. Use when the user asks a general question, requests file operations, wants to brainstorm ideas, needs to-do tracking, asks you to remember something, or requests skill search and…

0xranx/golembot · 61 tokens

project-memory-keeper

Analyzes the last session to log progress, extract lessons learned, and save them to the project memory instructions.

GulajavaMinistudio/awesome-copilot-id · 27 tokens

Promote

Take a slice of the current conversation and promote it to a durable vault artifact — concept note, project update, person profile, or doctrine entry. Pairs with /close. /close writes the daily note (transient outcome record); /promote elevates specific insights to permanent vault content the framework can refer back…

wrg32786/aigent-os · 68 tokens

open

Boot the session, load context from the vault, and surface what matters.

wrg32786/aigent-os · 16 tokens