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 skills add flurdy/agent-skills --skill watch-flux-rolloutgit clone --depth 1 https://github.com/flurdy/agent-skillsWrote 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/flurdy/agent-skills/watch-flux-rollout)<a href="https://agentmods.dev/skills/flurdy/agent-skills/watch-flux-rollout"><img src="https://agentmods.dev/badge/skills/flurdy/agent-skills/watch-flux-rollout/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/skills/flurdy/agent-skills/watch-flux-rollout"><img src="https://agentmods.dev/badge/skills/flurdy/agent-skills/watch-flux-rollout.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 10 Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
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 | $0.00065 | $0.02992 |
| Opus 5 | $0.00032 | $0.01496 |
| Sonnet 5 | $0.00013 | $0.00598 |
| Haiku 4.5 | $0.00006 | $0.00299 |
Grade A, and why
watch-flux-rollout 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.
allowed-tools: "Read,Grep,Glob,Write,AskUserQuestion,Skill,Bash(~/.agents/skills/watch-flux-rollout/scripts/rollout-status.sh:*),Bash(~/.agents/skills/watch-flux-rollout/scripts/default-head-sha.sh:*),Bash(~/.agents/skil How it starts
The opening of the file, as written. The whole thing — 224 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Watch Flux Rollout
Watch a CircleCI + FluxCD deploy of one commit until it's live, then smoke-test the change —
the kubectl/CircleCI sister of /watch-actions-rollout (which watches GitHub Actions CD). Built for
single-repo services deployed the Flux image-automation way: CircleCI builds and pushes an
image tagged <base>.<CIRCLE_BUILD_NUM>, a Flux ImagePolicy bumps the Deployment, the cluster
rolls it out.
The rollout-confirmation semantics are extracted from the multirepo /release-manager (step 4)
and deploy-status.sh flow: the exact post-push tag is unknowable at push time (the build
number is assigned when CircleCI runs), so "deployed" means the live tag has moved off the
pre-push baseline — never an exact-tag match.
Usage
/watch-flux-rollout # latest origin/main commit
/watch-flux-rollout <sha> # specific commit
/watch-flux-rollout --no-smoke # watch the rollout only, skip the smoke test
Procedure
Phase 0 — Load config (optional)
Read .claude/rollout.yaml at the repo root if present — same file /watch-actions-rollout uses,
different keys (they don't clash). Recognised keys (all optional):
namespace: apps # k8s namespace (default: apps)
deployment: badusernames-deployment # the Deployment Flux bumps
url: https://badusernames.flurdy.io # base URL the smoke targets
smoke: |
GET /health, expect 200 and status "ok".
Anything missing is inferred or asked for below. Never require the file. If deployment is
absent, infer it from the GitOps repo (grep the kubernetes repo for the service's image name)
or ask — don't guess across candidates.
Phase 1 — Resolve the commit and capture the baseline
Target commit: explicit sha arg, else the latest default-branch commit:
~/.agents/skills/watch-flux-rollout/scripts/default-head-sha.sh
Fallback if the script is unavailable — two steps, never &&: git fetch origin main -q,
then git rev-parse origin/main.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 Changed · -1 lines · -20 tokens per session ecd4539643ba
- 8d ago First seen · 225 lines · 85 tokens per session scan A e380b7bf6c6b
watch-flux-rollout is a skill published in the GitHub repository flurdy/agent-skills (9 stars, last pushed 5d ago), licensed MIT. It adds 65 tokens to every session and 2,992 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
nextjs-deployment
Provides comprehensive patterns for deploying Next.js applications to production. Use when configuring Docker containers, setting up GitHub Actions CI/CD pipelines, managing environment variables, implementing preview deployments, or setting up monitoring and logging for Next.js applications. Covers standalone output…
devops
DevOps - Docker, CI/CD, cloud infra, monitoring.
performing-container-security-scanning-with-trivy
Scan container images, filesystems, and Kubernetes manifests for vulnerabilities, misconfigurations, exposed secrets, and license compliance issues using Aqua Security Trivy with SBOM generation and CI/CD integration.
devops-deployment
Use when setting up CI/CD pipelines, containerizing applications, deploying to Kubernetes, or writing infrastructure as code. DevOps & Deployment covers GitHub Actions, Docker, Helm, and Terraform patterns.
devops-infrastructure
Guides Docker, CI/CD pipelines, deployment strategies, infrastructure as code, and observability setup. Use when writing Dockerfiles, configuring GitHub Actions, planning deployments, setting up monitoring, or when asked about containers, pipelines, Terraform, or production infrastructure.
devops-automator
Expert DevOps engineer for CI/CD, IaC, Kubernetes, and deployment automation. Activate on: CI/CD, GitHub Actions, Terraform, Docker, Kubernetes, Helm, ArgoCD, GitOps, deployment pipeline, infrastructure as code, container orchestration. NOT for: application code (use language skills), database schema (use…