Wait Efficiently
Wait without token-heavy polling. Use when the user asks to wait, pause, check back later, babysit a command, monitor a long-running process, wait for CI or GitHub Actions, or avoid repeated status polling while external work completes.
Install
$ agentstack add skill-jesse-merhi-skills-wait-efficiently ✓ 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.
Links to your public security report.[](https://agentstack.voostack.com/security/report/skill-jesse-merhi-skills-wait-efficiently) 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
Wait Efficiently
Keep one tool call pending for the whole wait. Do not return unchanged state to the model between polls.
Direct waits
For requests such as "wait five minutes", resolve `` to this skill and run:
/scripts/quiet-wait.py 5mIn Codex code mode, hold the outer functions.exec call longer than the requested delay. Start the script with a 30-second command yield, then poll its session internally with 60-second write_stdin waits until it exits. Keep that loop inside the same functions.exec call. Do not emit commentary, call notify, or yield control while the wait is unchanged.
Each individual internal wait must be at most 60 seconds. The outer tool call may span the complete requested delay.
Long-running commands
Use the same held-call pattern for builds, tests, reviews, deployments, and other quiet processes:
- Start with a 30-second command yield.
- If it is still running, poll internally for 60 seconds at a time.
- Return to the model only when the process exits, produces a state that
requires action, or the user-requested deadline arrives.
- Do not narrate unchanged heartbeats.
If the available tool cannot keep one outer call pending, use the longest safe blocking wait it supports. Never replace a wait with a tight polling loop.
GitHub Actions
Read [github-actions.md](references/github-actions.md), then estimate the next useful observation from completed runs of the same workflow:
/scripts/estimate-gh-wait.py --run-id Wait for the returned suggested_wait_seconds inside the same held tool call, then inspect the run once. Recalculate only after a meaningful state change. Fall back to 120 seconds when fewer than three comparable runs exist.
Completion
Report the result after the wait. For a plain delay, say that the requested time elapsed. For monitoring, report only meaningful state changes or the final state.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: jesse-merhi
- Source: jesse-merhi/skills
- License: MIT
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.