session-close

session-close is a skill for Claude Code from parisgroup-ai/imersao-ia-setup. It costs 104 tokens per session (2,517 once invoked), scanned B, original, MIT.

An end-of-session workflow that records useful decisions and results, reviews work, closes tasks, and updates project memory.

In plain words
What is it for?
It is for wrapping up work by updating Git, task records, memory files, and a session journal with what changed, what was learned, and what remains.
Why use it?
It reduces knowledge loss when a coding session ends or another agent later continues the project.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: reads .claude/ paths; mentions CLAUDE.md.

Part of the imersao plugin — 74 skills, 7 commands shipped together

Good fit It is for wrapping up work by updating Git, task records, memory files, and a session journal with what changed, what was learned, and what remains.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/parisgroup-ai/imersao-ia-setup/session-close
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.

Any agent
npx skills add parisgroup-ai/imersao-ia-setup --skill session-close
Clone the repo
git clone --depth 1 https://github.com/parisgroup-ai/imersao-ia-setup

Made for: Claude Code.

Or install imersao, the plugin that ships this one along with the rest of its 74 skills, 7 commands.

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-close

README.md
[![agentmods](https://agentmods.dev/badge/skills/parisgroup-ai/imersao-ia-setup/session-close/github.svg)](https://agentmods.dev/skills/parisgroup-ai/imersao-ia-setup/session-close)
Your own site
<a href="https://agentmods.dev/skills/parisgroup-ai/imersao-ia-setup/session-close"><img src="https://agentmods.dev/badge/skills/parisgroup-ai/imersao-ia-setup/session-close/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-close

Your own site · 80×15
<a href="https://agentmods.dev/skills/parisgroup-ai/imersao-ia-setup/session-close"><img src="https://agentmods.dev/badge/skills/parisgroup-ai/imersao-ia-setup/session-close.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 104 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,517 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00104 $0.02517
Opus 5.5 $0.00042 $0.01007
Sonnet 5.5 $0.00021 $0.00503
Haiku 4.5 $0.00010 $0.00252

Measured 20d ago against content hash 5d945d1a0261, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

session-close 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 20d 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.

cat .claude/session-journal.md 2>/dev/null
plugins/imersao/skills/session-close/SKILL.md · 360 lines

How it starts

The opening of the file, as written. The whole thing — 360 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Session Close

Structured end-of-session ritual that prevents knowledge loss by persisting everything worth keeping before the conversation ends. Works on any project.

The goal: when the next session starts (possibly weeks later, possibly by a different Claude instance), it should have full context of what happened, what was learned, and what's left to do.


Philosophy

Sessions are ephemeral — conversations get cleared, context gets lost. But the work product of a session lives in three places:

  1. Git — commits, diffs, branches (already persistent)
  2. Task system — TaskNotes, issues, project boards (needs updating)
  3. Memory — CLAUDE.md, auto-memory, session briefs (needs capturing)

This skill ensures #2 and #3 are up to date before the session ends.


Session Journal (Continuous Memory)

Throughout the session, important information should be appended to .claude/session-journal.md in the project root. This file acts as a scratch pad that survives even if the user closes the terminal without running /session-close.

What goes in the journal

Append a timestamped entry whenever:

  • A significant decision is made
  • A bug is found or fixed (with commit hash)
  • A pattern or pitfall is discovered
  • A task is completed or created
  • An insight worth remembering emerges

Format

## Session [DATE]

- [HH:MM] Started: [goal]
- [HH:MM] Fixed BUG-XXXX: [description] (commit `abc1234`)
- [HH:MM] Learned: [insight]
- [HH:MM] Created TASK-YYYY: [description]
- [HH:MM] Decision: [what was decided and why]

This file is gitignored (it's working state, not deliverable). The /session-close skill reads it and distributes the content to the right persistent locations.


The Close Sequence

/session-close
     │
     ▼
┌─────────────────────┐
│ 1. Reconstruct      │  Read git log, session journal, task changes
│    Session           │  Build narrative of what happened
└──────────┬──────────┘
           │
     ▼
┌─────────────────────┐
│ 2. Review Work      │  Validate commits against quality standards
│    (/reviewer lite) │  Flag concerns, not block
└──────────┬──────────┘
           │
     ▼
┌─────────────────────┐
│ 3. Close Tasks &    │  Mark completed TaskNotes as done
│    Open Pending     │  TaskCreate for every pending/suggested item
└──────────┬──────────┘
           │
     ▼
┌─────────────────────┐
│ 4. Persist Memory   │  Update CLAUDE.md with learnings
│                     │  Update auto-memory topic files
│                     │  Write session brief for next session
└──────────┬──────────┘
           │
     ▼
┌─────────────────────┐
│ 5. Commit & Report  │  Auto-commit memory/task changes
│                     │  Print session summary
└─────────────────────┘

Read the full file on GitHub · 360 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. 20d ago First seen · 360 lines · 104 tokens per session scan B 5d945d1a0261

Subscribe to this mod's changes

session-close is a skill published in the GitHub repository parisgroup-ai/imersao-ia-setup (1 stars, last pushed 19d ago), licensed MIT. It adds 104 tokens to every session and 2,517 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-10-06.

Related

Other skills, from other repositories

client-context-system

Sets up a complete per-client workspace in Cowork with isolated context, preferences, deliverable templates, running notes, decision log, and automatic status reporting. For consultants, agencies, and professional services. Useful when onboarding a new client, during engagement kickoffs, for organizing existing client…

EAIconsulting/cowork-skills-library · 105 tokens

predictable-revenue

Build a scalable outbound B2B sales machine with specialized roles (SDR, AE, CSM). Use when the user mentions "outbound sales", "Cold Calling 2.0", "cold email sequences", "sales pipeline", "SDR process", "sales development", "build an outbound sales team", or "fill my pipeline". Also trigger when setting up a B2B…

wondelai/skills · 152 tokens

traction-eos

Implement the Entrepreneurial Operating System (EOS) to align vision and execution across a company. Use when the user mentions "EOS", "Entrepreneurial Operating System", "V/TO", "quarterly rocks", "Level 10 meetings", "accountability chart", "IDS process", "my company feels chaotic", "we keep having the same…

wondelai/skills · 147 tokens

team-topologies

Organize business and technology teams for fast flow using Skelton & Pais's "Team Topologies". Use when the user mentions "team topologies", "Conway's law", "platform team", "stream-aligned team", "team boundaries", "cognitive load", "how should we split teams", "who owns this service", "team dependencies", or…

wondelai/skills · 155 tokens

handoff

Write a short handoff note for the next chat or a teammate, with what is done, what is open, what comes next and what was rejected and why. Saves it to project memory so the next chat sees it at the start, and prints it so it can be pasted into a message or a pull request. Use when the user ends a piece of work…

Avijit07x/claude-db · 87 tokens

wenlan-handoff

End a work session. Stores durable captures, writes a narrative session log, and automatically applies typed item-level deltas to the current Space Brief. Invoked as /wenlan-handoff.

wenlan-app/wenlan · 43 tokens