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 skyfox675/agents-skills --skill deploy-watchinggit clone --depth 1 https://github.com/skyfox675/agents-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/skyfox675/agents-skills/deploy-watching)<a href="https://agentmods.dev/skills/skyfox675/agents-skills/deploy-watching"><img src="https://agentmods.dev/badge/skills/skyfox675/agents-skills/deploy-watching/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/skyfox675/agents-skills/deploy-watching"><img src="https://agentmods.dev/badge/skills/skyfox675/agents-skills/deploy-watching.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 | $0.00219 | $0.02495 |
| Opus 5.5 | $0.00088 | $0.00998 |
| Sonnet 5.5 | $0.00044 | $0.00499 |
| Haiku 4.5 | $0.00022 | $0.00249 |
Grade A, and why
deploy-watching scanned grade A with 0 findings 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 10d 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deploy Watching
One job: keep the integration environment's deploys healthy by fixing forward. A failing deploy is diagnosed and repaired, not rolled back. The fix keeps whatever the offending commit shipped and makes the deploy healthy again. Nothing else.
This skill builds on driving-prs-to-merge (PR mechanics, the transient-vs-real ladder, force-push discipline) and pairs with ci-flake-hunting (the instability lane). Where a "make it green" instinct conflicts with the fix-forward rule, this skill wins.
Project bindings
Project-agnostic; the adopting project defines these in its own CLAUDE.md.
| Placeholder | Meaning |
|---|---|
<owner>/<repo> |
GitHub repository slug |
<integration-branch> |
Branch merges land on, and the branch the deploy follows |
<deploy-workflow> |
The workflow that deploys <integration-branch> to the shared environment |
<deploy-step> |
The job/step that actually applies infrastructure and code (IaC apply, release, migrate) |
<smoke-jobs> |
Post-deploy verification jobs that run against the live environment |
<local-gate> |
The full local verification command CI mirrors (lint + typecheck + tests) |
<transient-ledger> |
Where known transient deploy/smoke signatures are recorded; absent → degrade to "re-run once on the same SHA" |
The watcher model
A single-lane, interval-driven loop (/loop <interval> start), like the pr-checks lane but over deploy runs rather than PRs. Singleton: two deploy watchers re-run and fix the same red twice.
Slots = max concurrent fix sub-agents in flight — NOT a cap on runs watched. Look at every relevant deploy run each tick; queue extra fixes if more break at once than you have slots. Default 1 for this lane. A slots=N token in the start prompt overrides.
You orchestrate; you do not diagnose-by-editing. Delegate per MODEL-DEFAULTS.md:
- Read-only log trawl, locate, classify → the cheap tier (
caveman:cavecrew-investigatoror a cheap-tier sub-agent). Deploy and smoke logs are huge; keep them out of your context. - Code edit, ≤2 files, scope obvious →
caveman:cavecrew-builder. It has no Bash, so it cannot run tests or open a PR: investigator locates → builder edits → a Bash-capable step (you, or a workhorse sub-agent) verifies and opens the PR. - Anything bigger (3+ files, cross-cutting, needs tests run to diagnose) → a workhorse sub-agent, which may delegate further on the same rules. Never the cheap tier for code.
- Premium tier only on explicit operator instruction or an
agent-model:label — never self-escalated.
What ships with it
1 file 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.
- 10d ago First seen · 98 lines · 219 tokens per session scan A 7e1ff1d46f38
deploy-watching is a skill published in the GitHub repository skyfox675/agents-skills (11 stars, last pushed 11d ago), licensed MIT. It adds 219 tokens to every session and 2,495 once invoked, about $0.0009 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-09.
Other skills, from other repositories
chinese-git-workflow
A reference for configuring Git with Chinese code-hosting services such as Gitee, Coding.net, GitLab China, and CNB, including SSH, HTTPS, credentials, CI, and repository mirroring.
atmos-profiles
Atmos profiles: profile directories, --profile and ATMOSPROFILE activation, profile merge behavior, environment switching, and routing profile-specific auth/toolchain/config overrides.
webhook-management
Configure and validate CCAM webhook targets across supported chat, incident, automation, and generic providers. Use when listing provider requirements, creating or updating a target, scoping it to alert rules, sending a test notification, reviewing delivery history, or deleting a target.
monorepo-management
Master monorepo management with Turborepo, Nx, and pnpm workspaces to build efficient, scalable multi-package repositories with optimized builds and dependency management. Use when setting up monorepos, optimizing builds, or managing shared dependencies.
managing-github-actions-secrets
Creates and updates GitHub Actions secrets for PostHog workflows. Use when adding a new CI secret, rotating an existing secret, wiring a workflow to an API token, package registry credential, deploy key, or any value referenced via ${{ secrets. }} in .github/workflows/.
deployment-engineer
Expert deployment engineer specializing in modern CI/CD pipelines, GitOps workflows, and advanced deployment automation. Masters GitHub Actions, ArgoCD/Flux, progressive delivery, container security, and platform engineering. Handles zero-downtime deployments, security scanning, and developer experience optimization.…