wrap-session

wrap-session is a skill for Claude Code from FarzamMohammadi/the-engineer. It costs 37 tokens per session (557 once invoked), scanned A, original, MIT.

A session-closing checklist for software work. It records what happened, updates the project’s current status, saves the changes, and prepares instructions for the next session.

In plain words
What is it for?
Updating project notes, logging completed work, committing changes, and writing a self-contained starting prompt for the next session.
Why use it?
It reduces the chance of losing context or leaving the next person unsure about the project’s state.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Good fit Updating project notes, logging completed work, committing changes, and writing a self-contained starting prompt for the next session.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/farzammohammadi/the-engineer/wrap-session
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 FarzamMohammadi/the-engineer --skill wrap-session
Clone the repo
git clone --depth 1 https://github.com/FarzamMohammadi/the-engineer

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 wrap-session

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/farzammohammadi/the-engineer/wrap-session"><img src="https://agentmods.dev/badge/skills/farzammohammadi/the-engineer/wrap-session.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 37 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 557 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 $0.00037 $0.00557
Opus 5 $0.00018 $0.00279
Sonnet 5 $0.00007 $0.00111
Haiku 4.5 $0.00004 $0.00056

Measured 9d ago against content hash 24be11d4fd18, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

wrap-session 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 9d 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/wrap-session/SKILL.md · 77 lines

How it starts

The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Wrap Session

End the current session cleanly so the next one picks up without losing a beat.


Step 1: Update docs/archived/implementation-docs/9-oss-ready/active.md

Read docs/archived/implementation-docs/9-oss-ready/active.md, then update the Status section to reflect:

  • What was just completed this session
  • What we're doing next session
  • Current state of the overall work

Keep the rest of active.md intact (Current Focus, What We're Doing, Deliverables). Only the Status section changes.


Step 2: Log the Session

  1. Check docs/archived/implementation-docs/9-oss-ready/sessions/ for the latest session number
  2. Create the next sequential file (e.g., 002.md, 003.md)

Format:

# Session [NNN] — [YYYY-MM-DD]

## What Happened

[2-4 sentences summarizing the session. Be succinct.]

## Decisions Made

[Numbered list of decisions, or "None" if purely execution work.]

## What's Next

[What the next session should start with.]

Step 3: Commit

Run /commit to stage and commit all changes from this session.


Step 4: Starter Prompt

Generate a starter prompt for the next session. This is a self-contained message the user can paste into a fresh chat to pick up exactly where this session ended.

The prompt should:

  • Tell the agent which files to read first (always start with docs/archived/implementation-docs/9-oss-ready/active.md, then the latest session log)
  • Include any phase-specific files relevant to the current work (read active.md to determine these)
  • State the project context in one sentence
  • State the working mode based on what we're actually doing (read active.md — it may be code, testing, design, review, etc.). Always include: collaborate deeply, use Q&A tool, never assume, never rush.
  • Say to pick up where the last session left off

Present it in a code block, ready to copy-paste.


Output

Present to the user:

  1. Summary of what was logged
  2. List of files updated/created
  3. The starter prompt in a code block

Read the full file on GitHub · 77 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. 9d ago First seen · 77 lines · 37 tokens per session scan A 24be11d4fd18

Subscribe to this mod's changes

wrap-session is a skill published in the GitHub repository FarzamMohammadi/the-engineer (12 stars, last pushed 1mo ago), licensed MIT. It adds 37 tokens to every session and 557 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 2026-08-30.

Related

Other skills, from other repositories