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.
npx agentmods add skills/komluk/scaffolding/watch-patternsnpx skills add komluk/scaffolding --skill watch-patternsgit clone --depth 1 https://github.com/komluk/scaffoldingWrote 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/skills/komluk/scaffolding/watch-patterns)<a href="https://agentmods.dev/skills/komluk/scaffolding/watch-patterns"><img src="https://agentmods.dev/badge/skills/komluk/scaffolding/watch-patterns.svg" alt="Measured on agentmods" 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 | $0.00076 | $0.02374 |
| Opus 5 | $0.00038 | $0.01187 |
| Sonnet 5 | $0.00015 | $0.00475 |
| Haiku 4.5 | $0.00008 | $0.00237 |
Grade A, and why
watch-patterns scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
| Transient errors | A remote probe MAY fail transiently: `OUT=$(curl -fsS "$URL" 2>&1) || OUT="PROBE_FAILED: $OUT"` — capture and classify; a blind `\|\| true` on every command converts persistent outage into silence. C How it starts
The opening of the file, as written. The whole thing — 186 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Watch Patterns Skill
Purpose
How to observe long-running operations correctly. Anyone can run a loop — the value is a watcher that never lies: it terminates, it detects failure as reliably as success, and its silence is never mistaken for progress.
Key architectural fact: a subagent cannot hold a long-lived observation.
Notifications from an armed Monitor land in the conversation that armed it;
a subagent finishes and dies. Observation is therefore always armed by the
main loop — this skill is loadable anywhere for exactly that reason.
Auto-Invoke Triggers
- Watching a CI run, deployment, file transfer, GC/prune job, or log stream
- Writing any poll/
untilloop over a remote or local state - Using the
Monitortool orBash(run_in_background)for observation
Decision Tree — Choose the Mechanism FIRST
The single most common failure is picking the wrong mechanism. Decide BEFORE writing any script:
| Situation | Mechanism |
|---|---|
| "Is it done now?" — answerable immediately | One-shot check. Single command, no loop, no monitor. |
| ONE notification when a condition becomes true (deploy finished, download complete, GC done) | Bash(run_in_background) + until loop with a terminal condition and a bounded iteration count. NOT Monitor. |
| REPEATING events, each occurrence matters (every error line, every restart) | Monitor tool with a filter covering ALL terminal states. |
| CI run status (Gitea Actions) | MCP polling: mcp__gitea__actions_run_read polled until status is terminal. Structured status beats scraping logs. |
| Metric/log condition (error rate, service down) | MCP: mcp__grafana__query_prometheus / query_loki_logs. One query returns aggregated truth; a bash loop re-derives it badly. |
| You only need the outcome eventually, no urgency | Do nothing now. Check once when the result is actually needed. |
Anti-pattern (observed failure)
Unbounded tail -f / while true piped into Monitor when only ONE
notification was needed → the tool stays armed until timeout, and every
intermediate line risks a spurious notification. Single notification =
Bash(run_in_background) + until; Monitor is for recurring events only.
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.
- 4d ago First seen · 186 lines · 76 tokens per session scan A a4fcb4e82b28
watch-patterns is a skill published in the GitHub repository komluk/scaffolding (15 stars, last pushed 29d ago), licensed MIT. It adds 76 tokens to every session and 2,374 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 2026-08-30.
Other skills, from other repositories
platform-operations
Unified platform operations guidance for CI/CD pipeline design, deployment strategies, observability, SLI/SLOs, and incident-ready rollouts. Use when building release workflows, production monitoring, or reliability controls.
vibe-ship
Generates a complete, production-ready deployment setup for any app in one pass -- Dockerfile, docker-compose.yml, .dockerignore, CI/CD (GitHub Actions), scalability config (health checks, resource limits, K8s on request), and security hardening (non-root user, secrets, dependency scanning). Auto-detects the stack…
web-ci-spec
Produce a sprint CI.md covering pipeline stages, secrets handling, deployment strategy, and rollback for GitHub Actions / Cloud Build / GitLab CI / etc. Coordinator-only — produces drafts, never modifies live workflows. Pauses for user confirmation.
deploy-planner
Deployment and DevOps agent that generates Dockerfiles, CI/CD configs, and step-by-step deployment guides for free hosting platforms. Triggers on: deploy, launch, hosting, Docker, CI/CD, production, go live, ship it.
dockerized-service-release-deployment-workflow
Create a Dockerized-service release contract with clean GitHub Actions builds, main-anchored tags, immutable digest manifests, published-release deployments, production approval, health checks, and exact-digest rollback.
ci-workflow
Design and maintain .NET CI workflows for F#, C#, and mixed solutions with SDK setup, restore, build, test, format checks, package checks, caching, and matrix decisions.