Skip to content
Agentmart
Submit a tool

wrap

Session closing ritual — update item state in tasks/current.md before ending.

Skill by delarooster

IndexedMIT
Write a review

Chalk Labs

Need help deploying wrap?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/delarooster-wrap

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Session closing ritual — update item state in tasks/current.md before ending. Records state, never session narrative. Use when user says "wrap up", "close session", "end session", or at end of a work session.

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/wrap

What's inside

Skill name
wrap
Description
Session closing ritual — update item state in tasks/current.md before ending. Records state, never session narrative. Use when user says "wrap up", "close session", "end session", or at end of a work session.
License
MIT
Compatibility
opencode
Metadata
writes: item state only, never session narrative · trigger: end-of-session · writes-to: tasks/current.md
Instructions
90 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

You are closing this session. Update the **state** in `tasks/current.md`. Follow these steps exactly.

## The contract for `tasks/current.md`

Read this before touching the file. It overrides any instinct to be thorough.

`current.md` carries **item state and nothing else**: what is queued, what is in flight,
what is blocked. It is not a session journal and it is not a place to be comprehensive.

- **Never append a `## Session <date>` section.** Session narrative belongs in
  `tasks/archive/`, written by `/clean`, not by this skill.
- **Never write a paragraph.** A queue entry is one line. If an item needs explaining, the
  explanation goes in its story file or its backlog item.
- **Update in place. Do not append narrative.** The steps below name the only things that
  may be added: a queue entry, a decision row, an open-question line. Everything else is
  narrative, and narrative is what makes this file grow session over session. If it got
  meaningfully longer and none of those three things was added, this skill did the wrong
  thing.

Leaving detail out does not lose it. It is already in the story file, the backlog item,
the PR body, or the decision register, which is where someone will actually look.

## Step 1 — Git state snapshot

Run:
```
git status
git log --oneline -5
```

Record the current state: branch, any uncommitted/staged files, last 5 commits.

## Step 2 — Mark completed tasks

In `tasks/current.md`, update any task checkboxes that were completed this session from `[ ]` to `[x]`. Do not mark tasks complete if they were only partially done.

## Step 3 — Append to the decision register

For every decision made this session that isn't already logged, append a row to the
decision register.

Find it before writing to it. Repositories in this workspace disagree on casing, so check
for `tasks/DECISIONS.md` and `tasks/decisions.md` both, and match whichever the project
already uses rather than creating a second one beside it. On a case-sensitive filesystem,
guessing creates a duplicate register that nothing reads. If the project has neither, use
the Decision Log table in `tasks/current.md`:

```
| [today's date] | [decision] | [rationale] |
```

Only log decisions that affect direction, architecture, or approach — not implementation details.

## Step 4 — Update next action

Add or replace a single `**Next:**` line wherever the file tracks what happens next: an
in-progress phase section if the project uses them, otherwise directly under the queue. A
queue-only `current.md` has no phase sections, so do not create one to hold this line:

```
**Next:** [concrete action — specific enough that a cold session can start immediately]
```

One line only. Replace any existing Next entry.

## Step 5 — Surface open questions

If there are unresolved questions or blockers from this session, append them under a `## Open Questions` section (create it if it doesn't exist):

```
- [question or blocker] — context: [why it matters]
```

Remove any questions that were resolved this session.

## Step 6 — Confirm

Report back:
- Files modified
- Tasks marked complete
- Decisions logged
- Next action set
- Open questions updated

Do not summarize the whole session. Do not rewrite sections that didn't change. Do not add
a section these steps do not name. If your edit made `tasks/current.md` meaningfully longer
without adding a queue entry, a decision row, or an open question, revert it and write
less.

From delarooster/skills, MIT.

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Sep 19, 2026 (1 month ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from delarooster

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get wrap running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying wrap?

CallGet help
Cite this page

wrap skill. Agent Mart. https://agentmart.dev/skills/delarooster-wrap (last updated 2026-10-24)