agentmods.dev

session-end

session-end is a skill for Claude Code from jkm-4314/claude-code-skills. It costs 27 tokens per session (1,631 once invoked), scanned A, original, MIT.

A session handoff tool for recording what happened during a coding session. It compares the day's Git commits and file changes with the session log before finalising the handoff.

In plain words
What is it for?
Wrapping up a work session, updating the day's session record, and summarising relevant repository changes. The input does not specify the complete format of the final handoff.
Why use it?
It helps preserve project context when work stops or moves to another session. It can also reveal commits made by someone else or outside the current session.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: reads .claude/ paths; mentions CLAUDE.md.

not rated 4repo 5mo ago A scan 27 tokens original MIT

Good fit Wrapping up a work session, updating the day's session record, and summarising relevant repository changes. The input does not specify the complete format of the final handoff.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jkm-4314/claude-code-skills/session-end
View source ↗ jkm-4314/claude-code-skills
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 jkm-4314/claude-code-skills --skill session-end
Clone the repo
git clone --depth 1 https://github.com/jkm-4314/claude-code-skills

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-end

README.md
[![agentmods](https://agentmods.dev/badge/skills/jkm-4314/claude-code-skills/session-end/github.svg)](https://agentmods.dev/skills/jkm-4314/claude-code-skills/session-end)
Your own site
<a href="https://agentmods.dev/skills/jkm-4314/claude-code-skills/session-end"><img src="https://agentmods.dev/badge/skills/jkm-4314/claude-code-skills/session-end/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-end

Your own site · 80×15
<a href="https://agentmods.dev/skills/jkm-4314/claude-code-skills/session-end"><img src="https://agentmods.dev/badge/skills/jkm-4314/claude-code-skills/session-end.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 27 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,631 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 $0.00027 $0.01631
Opus 5.5 $0.00011 $0.00652
Sonnet 5.5 $0.00005 $0.00326
Haiku 4.5 $0.00003 $0.00163

Measured 1mo ago against content hash ad876a500e99, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

session-end 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 1mo 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.

session-end/SKILL.md · 175 lines

How it starts

The opening of the file, as written. The whole thing — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Session End Handoff

You are finalizing a work session to preserve context for future sessions. Follow these steps.

Override note: This is the generic global version. If this project has a project-level session-end skill (in .claude/skills/session-end/), that version runs instead of this one and may include project-specific app shutdown logic.

Step 1: Git-Grounded Reconciliation

Run:

git log --since="6am" --oneline --all
git diff --stat

Cross-reference commits against this Claude session's own work. Flag any commits that THIS session didn't make (other agents, manual commits, or earlier context-cleared sub-sessions). For unfamiliar commits, briefly read the changed files so you can describe them accurately.

Step 2: Detect Today's Session Entry

Read the top of .claude/SESSION_LOG.md.

If the top entry's date matches today's date (stub from session-start, or an already-finalized entry being appended to):

  • Continue to Step 3 to finalize / augment it.

If no entry exists for today (user worked informally without running session-start):

  • Ask: "No session-start entry exists for today. Options:
    1. Create a retroactive entry for today's work
    2. Skip log creation — just run housekeeping (ROADMAP / DECISIONS / MISTAKES / pruning)
    3. Do nothing"
  • If they pick (1): create a new entry at the top with today's date and next session number, then continue to Step 3.
  • If they pick (2): jump to Step 5.
  • If they pick (3): stop.

Step 3: Finalize Today's Entry

Check today's entry for a <!-- last-update: <hash> --> marker. Its presence signals that session-update has been run during the day and the entry already has substantive content — in that case, session-end is a lightweight finalization. Its absence means you're reconstructing from scratch against git history.

Path A: Entry has been updated during the day (marker present OR sections populated)

Most content is already captured. Focus on:

  1. "What title best describes today's session?" (replaces [In Progress])
  2. "One-line focus for the session?"
  3. Quick cross-check against git reconciliation:
    • Compare the commits from Step 1 against ### Files Modified and ### What Was Accomplished. Anything missing? Ask the user briefly.
  4. "Any final decisions, blockers, or notes to add?"
  5. Remove the <!-- last-update: ... --> marker — the session is being finalized, marker no longer needed.

Read the full file on GitHub · 175 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. 1mo ago First seen · 175 lines · 27 tokens per session scan A ad876a500e99

Subscribe to this mod's changes

session-end is a skill published in the GitHub repository jkm-4314/claude-code-skills (4 stars, last pushed 5mo ago), licensed MIT. It adds 27 tokens to every session and 1,631 once invoked, about $0.0001 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.

Claude CodeGit and workflowai-toolsanthropicclaude-skillscodexdeveloper-tools
Related

Other skills, from other repositories

vienen-las-visitas

Use before work crosses to another person or system — opening a pull request, pushing a shared branch, requesting review, handing off to another agent, a demo, or a release. NOT for ordinary intermediate commits; this is the boundary-crossing gate, not a per-commit ritual.

mcasillas17/mexican-mom · 63 tokens

git-master

MUST USE for ANY git operations: atomic commits, rebase/squash/fixup, and history search (blame, bisect, log -S, reflog). Load it before running git yourself, or pass loadskills=['git-master'] to the task that commits. Triggers: 'commit', 'rebase', 'squash', 'who wrote', 'when was X added', 'find the commit that'.

code-yeongyu/oh-my-openagent · 93 tokens

oss-contribution-research

Research and prepare an outside contribution to an open-source repo, then stop at a queue item for a human to approve: policy check, intake, duplicate check, reproduction, patch, the repo's own checks, an independent critic rerun, and a disclosed, hashed draft of the exact text to post. Use this skill whenever the…

rampstackco/claude-skills · 200 tokens

get-unpublished-changes

Compare HEAD with the latest published npm versions and list all unpublished changes by release layer. Triggers: unpublished changes, changelog, what changed, whats new.

code-yeongyu/oh-my-openagent · 38 tokens

bitbucket-workflow

Bitbucket best practices for pull requests, Pipelines CI/CD, Jira integration, and Atlassian ecosystem workflows.

Mindrally/skills · 27 tokens

github-workflow

GitHub best practices for pull requests, code reviews, issues, Actions workflows, and repository management.

Mindrally/skills · 23 tokens