loop-briefing
/loop-briefing
Notify the user via Pushover when an autonomous Claude Code /loop is BLOCKED and needs human input/decision, or has FINISHED with no meaningful work remaining. Renders a full monospace incident-report PNG (session/project/branch/git-status/commits/details, iPhone-13-mini tuned) and sends a short action-focused message - emergency+receipt for blocked, high-priority for done. Use this proactively during a /loop at the moment you must stop and ask, or when you are about to stop scheduling further wakeups. Do NOT use for routine progress. TRIGGERS - loop blocked, loop done, loop needs input, notif
- Author
- terrylica ↗
- Repository
- cc-skills ↗
- Licence
- MIT
- Last repository change
- 25.10.2026
Assessment and security
- Files in this package
- 1
- Scripts
- 0
- HTML comments
- 0
- URLs in SKILL.md
- 0
No signals detected. Repository changed on 25.10.2026, without references to retired models or APIs.
MIT, open: use and modify while retaining author attribution.
What it does and when to use it
Notify the user via Pushover when an autonomous Claude Code /loop is BLOCKED and needs human input/decision, or has FINISHED with no meaningful work remaining. Renders a full monospace incident-report PNG (session/project/branch/git-status/commits/details, iPhone-13-mini tuned) and sends a short action-focused message - emergency+receipt for blocked, high-priority for done. Use this proactively during a /loop at the moment you must stop and ask, or when you are about to stop scheduling further wakeups. Do NOT use for routine progress. TRIGGERS - loop blocked, loop done, loop needs input, notif
Original author description
Notify the user via Pushover when an autonomous Claude Code /loop is BLOCKED and needs human input/decision, or has FINISHED with no meaningful work remaining. Renders a full monospace incident-report PNG (session/project/branch/git-status/commits/details, iPhone-13-mini tuned) and sends a short action-focused message - emergency+receipt for blocked, high-priority for done. Use this proactively during a /loop at the moment you must stop and ask, or when you are about to stop scheduling further wakeups. Do NOT use for routine progress. TRIGGERS - loop blocked, loop done, loop needs input, notif
How it works
- When to fire (the two-situation rule)
- Post-Execution Reflection
SKILL.md preview
--- name: loop-briefing description: Notify the user via Pushover when an autonomous Claude Code /loop is BLOCKED and needs human input/decision, or has FINISHED with no meaningful work remaining. Renders a full monospace incident-report PNG (session/project/branch/git-status/commits/details, iPhone-13-mini tuned) and sends a short action-focused message - emergency+receipt for blocked, high-priority for done. Use this proactively during a /loop at the moment you must stop and ask, or when you are about to stop scheduling further wakeups. Do NOT use for routine progress. TRIGGERS - loop blocked, loop done, loop needs input, notify when blocked, loop finished, stop the loop and notify, autonomous loop briefing. --- # loop-briefing > **Self-Evolving Skill**: This skill improves through use. If instructions are wrong, parameters drifted, or a workaround was needed — fix this file immediately, don't defer. Only update for real, reproducible issues. The original goal skill: a contextually-invoked briefing for autonomous `/loop` runs. Built on the TS core `pushover_core.ts loop-brief`, which gathers context (project, cwd, branch, `git status`, recent commits, plus any details you pass), renders it (Satori → PNG), and sends it (emergency+receipt for blocked, high-priority for done). ```bash # BLOCKED — needs a decision now (emergency, alarms until you ack): env -u HTTPS_PROXY -u HTTP_PROXY bun "$(cc-plugin-root pushover-commander)/skills/_lib/pushover_core.ts" loop-brief \ --kind blocked --reason "must choose auth method" --body /tmp/decision_options.txt # DONE — no meaningful work remains (high priority, no alarm): env -u HTTPS_PROXY -u HTTP_PROXY bun "$(cc-plugin-root pushover-commander)/skills/_lib/pushover_core.ts" loop-brief \ --kind done --reason "all tasks complete, matrix exhausted" ``` ## When to fire (the two-situation rule) 1. **Blocked** — the loop cannot safely continue without a human: needs a decision, clarification, review, or a choice between options. Pair this with an `AskUserQuestion` call in the session so the options are presented in plain language with tradeoffs. 2. **Done** — no meaningful remaining work under the initial or updated directives; the loop should stop scheduling further wakeups (CronDelete). Do **not** fire for routine progress. The `--body -` form reads details from stdin. ## Post-Execution Reflection After this skill completes, check before closing: 1. **Did the block/done briefing fire at the right moment with the right git and session context?** If it fired on routine progress or missed a real block, fix the trigger. 2. **Was the emergency vs high-priority routing correct?** Blocked = emergency+receipt, done = high-priority — fix if swapped. Only update if the issue is real and reproducible — not speculative.
Versions
The database has no other skills named loop-briefing.
Database snapshot: 13.11.2026 · package version 5e2500041d9e (SHA-256 digest of the entire package)
Downloads in the last 30 days: 0 · ranking
Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.
Similar skills
- 100render-incident-report-image
Render a verbose monospace "incident report" PNG tuned for reading on an iPhone 13 mini in a Pushover notification (72-column wrap, dark theme, green headings, no horizontal cut-off, unlimited scrollable height). Use when the user wants a detailed text briefing/report rendered… - 100emergency-priority2-receipt
Send a Pushover EMERGENCY (priority 2) alert that repeats until acknowledged, then poll the receipt until the user acks or it expires. Use when something is urgent and must not be missed - production breakage, a blocked autonomous loop needing immediate input, an… - 100loop-controller
Add a verifiable stop condition and a mandatory guardrail stack to any task so an autonomous loop converges instead of thrashing or burning the budget — the foundation harness every loop skill composes on, so it loads first and then routes to the right primitive (/goal vs /loop… - 90working-in-shifts
Explains how to work in a repo run by repeated headless Claude Code shifts, including what to read first, how to hand off through plan.md and progress.md, and when to write DONE or BLOCKED. Use when working from loop/prompt.md, when the user asks to set up or start the loop, or… - 100message-claude
Send a message from an external agent or script to a running Claude Code session on the same machine. Use when a manually started Codex session needs to tell any Claude session something, Codex needs to report back to the Claude session that launched it, a hook or long job… - 100iloop
In-session iterative loop — keeps Claude running in the current session until a task is done. Unlike /loop (which spawns background workers), /iloop stays in the current session and re-prompts each iteration via Stop hook. Use for: 'keep fixing until tests pass', 'iterate until…