close-session

close-session is a skill for Claude Code, Codex from itsribbZ/Godspeed. It costs 61 tokens per session (3,446 once invoked), scanned B, original, MIT.

A session-ending tool that records completed work, decisions, useful lessons, and context for the next coding session. It works with an initialization tool that loads this saved context later.

In plain words
What is it for?
Use it when finishing work to save a concise handoff, update shared project memory, verify checkpoints, and record lessons from the session.
Why use it?
It reduces the need to reconstruct what happened after a long session and helps prevent important decisions or project context from being lost.

Skill for Claude CodeCodex

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the godspeed plugin — 18 skills, 3 commands, 1 agent, 5 hooks 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/itsribbz/godspeed/close-session
Any agent
npx skills add itsribbZ/Godspeed --skill close-session
Clone the repo
git clone --depth 1 https://github.com/itsribbZ/Godspeed

Made for: Claude Code, Codex.

Or install godspeed, the plugin that ships this one along with the rest of its 18 skills, 3 commands, 1 agent, 5 hooks.

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 close-session

README.md
[![agentmods](https://agentmods.dev/badge/skills/itsribbz/godspeed/close-session.svg)](https://agentmods.dev/skills/itsribbz/godspeed/close-session)
Your own site
<a href="https://agentmods.dev/skills/itsribbz/godspeed/close-session"><img src="https://agentmods.dev/badge/skills/itsribbz/godspeed/close-session.svg" alt="Measured on agentmods" height="20"></a>
Per session 61 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,446 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00061 $0.03446
Opus 5 $0.00030 $0.01723
Sonnet 5 $0.00012 $0.00689
Haiku 4.5 $0.00006 $0.00345

Measured 4d ago against content hash bdcc1f48c3c2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

close-session scanned grade B with 1 finding 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 4d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

TICK=$(cat ~/.claude/telemetry/brain/godspeed_count.txt 2>/dev/null || echo 0)
plugins/godspeed/skills/close-session/SKILL.md · 307 lines

How it starts

The opening of the file, as written. The whole thing — 307 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Close Session v2.0

Init loads context. Close-session saves it. Together: lossless session loop.

Context-discipline (v2.2 — 2026-04-17): Close-session writes summaries from what's already in the conversation. It does NOT re-load source material. Without this discipline, long sessions push main-session context past 200K and force the [1m] model variant, which requires /extra-usage billing. The rules below keep close-session inside the standard 200K window.

Context-Discipline Rules (v2.2)

  1. Phase 1 session audit — scan the scrollback you already have. Don't re-Read any file already touched this session — use what's in context.
  2. Phase 4 memory updates — Edit files in-place with targeted file:line anchors. Do NOT Read a file end-to-end just to understand where to append — use Grep to find the insertion point, then Edit.
  3. Phase 4c skill _learnings.md checks — always grep-first, never bulk-read:
    grep -c "^###" ~/.claude/skills/<skill>/_learnings.md   # entry count
    tail -40 ~/.claude/skills/<skill>/_learnings.md        # recent entries only
    
    Only Read the full file if a regression is suspected.
  4. Project docs sync — if a project's canonical docs are >10K tokens, Edit them with targeted file:line anchors. Don't Read the whole file to understand context.

Bottom line: close-session writes summaries, it does NOT re-load session source material. Everything needed is already in the conversation context.

Trigger

"close session", "end session", "wrap up", "save session", "done for today", "session done"

Phase 1: Session Audit

Scan the conversation for:

  1. Work Completed — features built, bugs fixed, code written, files created/modified
  2. Decisions Made — design choices, architecture decisions, approach changes
  3. Bugs Found/Fixed — new bugs discovered, existing bugs resolved
  4. Research Done — outputs from any research / analysis skill used this session
  5. Tools Created/Updated — new scripts, skill improvements, workflow changes
  6. Unfinished Work — started but not completed, mid-progress state
  7. Next Steps — planned next actions, logical continuations
  8. User Feedback — corrections, preferences, guidance that should persist

Read the full file on GitHub · 307 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. 4d ago First seen · 307 lines · 61 tokens per session scan B bdcc1f48c3c2

Subscribe to this mod's changes

close-session is a skill published in the GitHub repository itsribbZ/Godspeed (1 stars, last pushed 2mo ago), licensed MIT. It adds 61 tokens to every session and 3,446 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.