AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified Apache-2.0 Self-run

Brief Pause

skill-useaitechdad-agent-skills-brief-pause · by useaitechdad

Use when the user wants to checkpoint the current session for a fresh continuation — they've worked to a natural stop, or context is filling up, and want a markdown file the next session can read to pick up cleanly. Triggered by phrases like "checkpoint this", "pause and write a brief", "brief for next session", "I'm at a stop point", "save state for resumption".

No reviews yet
0 installs
9 views
0.0% view→install

Install

$ agentstack add skill-useaitechdad-agent-skills-brief-pause

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-useaitechdad-agent-skills-brief-pause)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
2mo ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Brief Pause? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

brief-pause — checkpoint this session for a clean continuation

You are writing a markdown file that captures the current state of this session so a fresh Claude Code session can pick up without losing context.

Where to save

~/.claude/projects//briefs/brief-.md

Compute the paths yourself — no shell needed for the slug:

  • ` = current working directory with every / replaced by - (e.g. cwd /Users/you/code/myapp → slug -Users-you-code-myapp`). You already know the cwd from your environment.
  • briefs dir = /.claude/projects//briefs (absolute, your real home path).

You do need one shell call — the timestamp, since Claude has no clock:

date +%Y-%m-%d-%H%M%S   # local time — keeps the filename stamp consistent with the log stamp

The filename is brief-.md. Write it with the Write tool (it creates the briefs dir if missing) — don't shell out to create the file.

Before writing — capture git state (if this is a git repo)

Run git rev-parse --is-inside-work-tree 2>/dev/null first. If it's a git repo:

  • If there are uncommitted changes, offer to commit them at a logical checkpoint before pausing — git history is the exact record the next session reads; the brief only points at it. Don't force it, but a clean working tree + a referenced SHA range beats a brief describing uncommitted WIP.
  • Capture the SHA range since the last brief so the next session can git log/git diff it: git log --oneline -10. Put the relevant range in Done (e.g. "since 6e9d902").
  • Note anything not committed (intentional WIP) explicitly under Open.

What to write

Keep it tight — aim for ~25-40 lines. Distill, don't dump.

# Brief — 

**Flavor**: pause
**Created**: 
**Project**: 
**Read first**: `CLAUDE.md`, then [the SPECIFIC docs this work touches — scan the repo and name them; e.g. `docs/sync-design.md`, a spec, a feature README. Don't leave this as a bare `CLAUDE.md` placeholder.]

## Situation

## Done
- 
- 

## Do next
- 
- 

## Open
- 

## Verify before continuing
- 

After writing

  1. Append the log entry via the shared helper (owns the format + trim + file pruning — don't hand-format the line). Pass the absolute briefs dir and the file you just wrote:

``bash ~/.claude/skills/_brief-shared/append-log.sh "" pause "" "" ``

  1. Print the file path to the user.
  2. One-line hint: "Open a fresh Claude Code session here and say /brief-resume to continue."

What NOT to include

  • Don't dump the entire chat history — distill.
  • Don't include reasoning chains, deliberation, or alternatives that were rejected.
  • Don't include secrets / tokens / API keys — leave placeholders.
  • Don't restate things the next session will discover from CLAUDE.md or other read-first docs.
  • Don't recommend things you haven't actually verified.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.