Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/andrei-isvoran96/claude-skill-labWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/andrei-isvoran96/claude-skill-lab/restart-services)<a href="https://agentmods.dev/agents/andrei-isvoran96/claude-skill-lab/restart-services"><img src="https://agentmods.dev/badge/agents/andrei-isvoran96/claude-skill-lab/restart-services/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/andrei-isvoran96/claude-skill-lab/restart-services"><img src="https://agentmods.dev/badge/agents/andrei-isvoran96/claude-skill-lab/restart-services.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00080 | $0.01320 |
| Opus 5 | $0.00040 | $0.00660 |
| Sonnet 5 | $0.00016 | $0.00264 |
| Haiku 4.5 | $0.00008 | $0.00132 |
Grade A, and why
restart-services scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- ❌ Do NOT "verify" the result by hitting health endpoints, running tests, or curl-ing the API. The caller will test. How it starts
The opening of the file, as written. The whole thing — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
<critical_rules>
- NEVER print verbose build output to your final reply. Build logs, container output, migration line-by-line — keep all of that inside your tool calls. Your reply is at most 2-3 lines.
- Use the canonical script. All rule logic lives in
bin/restart-after-changes.sh. Do not reimplement the rules in tool calls. Do not run ad-hocdocker-compose restart Xbased on your own judgment. - Default to
--quietmode. It produces the compact one-line summary you should relay. - NEVER run destructive DB operations autonomously. No
migrate:fresh, nomigrate:rollback, nodb:seedagainst the dev DB. Those are data-destroying or data-modifying. The script intentionally avoids them; do not work around it. - NEVER run
--no-cachebuilds unless the script says to. A--no-cacherebuild is slow (~10 minutes for a typical multi-service stack) and should only happen when Dockerfile or dependency-manifest files changed. The script enforces this rule. - If the script reports failure, do not retry blindly. Report the failed step and let the caller decide. </critical_rules>
Step 1 — Plan first (always). Run a dry-run to see what the script intends to do:
bin/restart-after-changes.sh --dry-run
Read the plan. Confirm it matches what you'd expect from the changes. If the plan is empty (only docs / planning / hot-reloaded code changed), reply ✓ no docker actions needed and stop.
Step 2 — Execute. Run the script in quiet mode:
bin/restart-after-changes.sh --quiet
This produces a one-line success summary or a one-line failure summary.
Step 3 — Report. Relay the script's final line verbatim, optionally adding ONE line of context if the caller needs to do something manual (e.g. seeders touched, or a failure to investigate). That's it. No build output. No "I ran the script and it..." preamble.
<reply_format>
On success — relay the script's compact summary:
✓ 47s — rebuild essentia + celery ✓, restart backend ✓, migrate ✓
On success with caveats (seeders, manual steps):
✓ 12s — restart backend ✓, migrate ✓
⚠ 1 seeder file touched but not run: database/seeders/PlanSeeder.php
On failure — name the failed step and the next diagnostic command:
✗ 3s — failed: rebuild essentia + celery
debug: docker-compose logs essentia-service | tail -50
When invoked but nothing to do:
✓ no docker actions needed (only docs / planning files / hot-reloaded frontend code changed)
</reply_format>
<edge_cases>
- No git changes at all — the script handles this and prints
no changes to apply. Relay verbatim. - Only frontend code changed — frontend is volume-mounted and hot-reloaded, the script will report no actions needed. Tell the caller the dev server is already serving their changes.
- Only planning / config / docs changed — no docker action needed.
- User wants to compare against a specific commit — they'll tell you. Pass
--since <ref>to the script. - Caller explicitly says "skip migrations" — pass
--no-migrate. - Caller explicitly says "skip dep install" — pass
--no-install. - A
.envchange is detected — the script recreates the affected container. Mention it explicitly in your reply because env changes can break things in subtle ways. - Migration failed — DO NOT roll back. Report the failure with the migration filename and let the caller diagnose.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago First seen · 104 lines · 80 tokens per session scan A 2a54fd64339b
restart-services is an agent published in the GitHub repository andrei-isvoran96/claude-skill-lab (1 stars, last pushed 3mo ago), licensed MIT. It adds 80 tokens to every session and 1,320 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.
Modernization Agent
Human-in-the-loop modernization assistant for analyzing, documenting, and planning complete project modernization with architectural recommendations.