Install
$ agentstack add skill-useaitechdad-agent-skills-brief-pause ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo 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.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
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 →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 diffit:git log --oneline -10. Put the relevant range in Done (e.g. "since6e9d902"). - 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
- 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 "" "" ``
- Print the file path to the user.
- One-line hint: "Open a fresh Claude Code session here and say
/brief-resumeto 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.mdor 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.
- Author: useaitechdad
- Source: useaitechdad/agent-skills
- License: Apache-2.0
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.