end SKILL.md skillA

end from gptme/gptme-contrib is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add gptme/gptme-contrib/end@v1.0.0

Pins v1.0.0 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
gptme/gptme-contrib
Path
skills/end/SKILL.md
Versions recorded
3
Latest version
v1.0.0, committed Oct 21, 2026
First version recorded
Aug 23, 2026
Size
11,401 bytes
Repository stars
15
License
MIT

Wrap up the session safely: gate on uncommitted/unpushed work and missing journal, refuse to end if anything is unsaved, write the closing summary, then exit the harness when the session was light (stay alive for review when it was substantial). Invoke as /end (Claude Code, Codex) or /skill:end (gptme).

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# /end — wrap up, or refuse to

The skill is a **gate, then a closeout, then (maybe) an exit**. It exists so
"I'm done" is a checked claim, not a feeling. Three rules:

1. **Refuse to end with unsaved work.** Uncommitted files you touched, unpushed
   commits, dirty worktrees, or a missing journal entry → you are *not* done.
2. **Closeout is short and stands alone.** The last message must make sense to
   someone who reads only it.
3. **Exit only when it's cheap to come back.** Light session → exit the harness.
   Substantial session → stay alive so the human can review before the context
   is gone. (`--exit` / `--stay` override.)

## Arguments

`$ARGUMENTS` — optional flags:

| Flag | Effect |
|---|---|
| *(none)* | check → closeout → exit iff `CLEAN_LIGHT` |
| `--exit` | check → closeout → exit even if `CLEAN_SUBSTANTIAL` |
| `--stay` | check → closeout → never exit |
| `--dry-run` | run the check and report; change nothing, exit nothing |

## Step 1 — Run the gate (always)

```bash
# SKILL_DIR: $CLAUDE_SKILL_DIR in Claude Code; otherwise the directory of this
# SKILL.md (e.g. gptme-contrib/skills/end or ~/.codex/skills/end).
python3 "$SKILL_DIR/scripts/end-check.py"
```
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add gptme/gptme-contrib/end@sha256:1da25291085ce366

The line at the top of this page pins the label v1.0.0, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_tsmedr7qvyjsgvre.svg)](https://markdownregistry.com/a/art_tsmedr7qvyjsgvre)

4 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 3 versions of this file, between Aug 23, 2026 and Oct 21, 2026, about one every 30 days.

versioncommittedcommitsizeaudit
v1.0.0 latest2026-10-21 5a45506 11,401 BA view · diff
v1.0.02026-09-19 7d055e6 10,076 BA view · diff
v1.0.02026-08-23 88e4663 8,388 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (11401 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

gptme/gptme-contrib · 15 stars · license MIT · pushed 2026-10-22 · branch master

API

GET https://markdownregistry.com/api/v1/artifacts/art_tsmedr7qvyjsgvre
GET https://markdownregistry.com/api/v1/resolve?ref=gptme/gptme-contrib/end
GET https://markdownregistry.com/api/v1/blob/1da25291085ce3666885cdb73c7388c439458755c921969fbf25a6a8c86ebd94

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from gptme/gptme-contrib

DESIGN.md@packages/gptmail/src/gptmail DESIGN.md file
gptme/gptme-contrib · packages/gptmail/src/gptmail/DESIGN.md
git:20261002.b812a00 · audit A · 15 stars
DESIGN.md@packages/gptme-dashboard DESIGN.md file
gptme/gptme-contrib · packages/gptme-dashboard/DESIGN.md
git:20260313.e78e913 · audit A · 15 stars
agent-onboarding SKILL.md skill
gptme/gptme-contrib · skills/agent-onboarding/SKILL.md · Comprehensive framework for effective gptme agent onboarding that builds user trust, communicates capabilities clearly…
v1.0.0 · audit A · 15 stars
agentic-presentation SKILL.md skill
gptme/gptme-contrib · skills/agentic-presentation/SKILL.md · Generate an offline, single-file HTML presentation from structured slide JSON. Use when turning notes, research, demos…
v0.1.0 · audit A · 15 stars
artifact-publishing SKILL.md skill
gptme/gptme-contrib · skills/artifact-publishing/SKILL.md · Workflow for publishing HTML artifacts (demos, visualizations, interactive content) to the web. Enables agents to share…
v1.0.0 · audit A · 15 stars
code-review-helper SKILL.md skill
gptme/gptme-contrib · skills/code-review-helper/SKILL.md · Systematic code review workflows with bundled utilities for analyzing code quality, detecting patterns, and providing…
v1.0.0 · audit A · 15 stars
financial-advisor SKILL.md skill
gptme/gptme-contrib · skills/financial-advisor/SKILL.md · Calibrates LLM financial advice by gathering context in research-backed order (time horizon, debt status, emergency…
v1.0.0 · audit A · 15 stars
gptme-wrapped SKILL.md skill
gptme/gptme-contrib · skills/gptme-wrapped/SKILL.md · Analyze your gptme conversation history for insights like token usage, costs, model preferences, and usage patterns —…
v1.0.0 · audit A · 15 stars
hold-to-talk SKILL.md skill
gptme/gptme-contrib · skills/hold-to-talk/SKILL.md · Experimental single-turn voice input for gptme: capture or read audio, transcribe locally with faster-whisper, and…
v0.2.0 · audit A · 15 stars
home-assistant SKILL.md skill
gptme/gptme-contrib · skills/home-assistant/SKILL.md · Query a Home Assistant instance for presence, sensor data, calendar events, and cameras
v1.0.0 · audit A · 15 stars
html-artifact-qa SKILL.md skill
gptme/gptme-contrib · skills/html-artifact-qa/SKILL.md · Use when a user asks a complex, multi-part, or deeply technical question that benefits from interactive HTML output…
v0.1.0 · audit B · 15 stars
journal SKILL.md skill
gptme/gptme-contrib · skills/journal/SKILL.md · Create or backfill append-only agent journal entries under the day the work happened, especially when writing after…
git:20260928.2953102 · audit A · 15 stars

Every file in gptme/gptme-contrib

Other files named end

end SKILL.md skill
jantichy/claude · skills/end/SKILL.md · Skill se použije, když uživatel zadá "/end", nebo chce před koncem či kompaktací session zapsat všechno, co se v ní…
git:20261013.f48f78d · audit A · 40 stars
end SKILL.md skill
conorbronsdon/agent-context-os · .agents/skills/end/SKILL.md · Close this context workspace through the canonical reviewed handoff workflow. Use only when the user explicitly invokes…
git:20260924.d5194b0 · audit A · 29 stars
end SKILL.md skill
pche-broken-artist/forge-of-thought · .claude/skills/end/SKILL.md · End a session — what lives only in the conversation, what is unsaved, what a shutdown would lose
git:20261019.2b9222e · audit B · 3 stars

Browse by kind, by grade A, or by owner.