Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/flurdy/agent-skillsnpx agentmods add skills/flurdy/agent-skills/release-maintenanceWrote 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/release-maintenance)<a href="https://agentmods.dev/skills/flurdy/agent-skills/release-maintenance"><img src="https://agentmods.dev/badge/skills/flurdy/agent-skills/release-maintenance/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/release-maintenance"><img src="https://agentmods.dev/badge/skills/flurdy/agent-skills/release-maintenance.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 | $0.00035 | $0.01541 |
| Opus 5 | $0.00017 | $0.00771 |
| Sonnet 5 | $0.00007 | $0.00308 |
| Haiku 4.5 | $0.00003 | $0.00154 |
Grade A, and why
release-maintenance 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 2d 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 — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Release Maintenance
Own production-affecting maintenance separately from shipping decisions.
This skill is never invoked by /release-manager or /watch-release; those workflows may suggest a fresh explicit
invocation but cannot dispatch it. A push answer is not maintenance authorization.
Usage
/release-maintenance reconcile-order
/release-maintenance config-sync <repository>
/release-maintenance restart <service>
/release-maintenance acknowledge-rollout <service>
Require an explicit operation and target. A missing/ambiguous argument is a clarification, not a license to scan for actions. Load the verified project's guidance and relevant runbook first. Do not invent repository names, cluster context, namespaces, startup-only config behavior, or consumer sets. Unsupported project capabilities require a handoff, not generic fallback commands.
Shared action boundary
- Identify the exact repository/worktree or Kubernetes context/namespace/resource and current evidence. Preserve unrelated edits and state. One writer per state file; pause the attended manager before any shared-state update. Malformed or concurrently changed state stops writes.
- Show the diff or operation, target, production consequence, and one visible command. Ask
immediately before each remote or destructive action; this skill also confirms local manifest
rewrites and state acknowledgements. Dismissal/no answer means do nothing. Every subsequent
command needs its own approval; no cached tick answer or bundled
&&chain. - Recheck target identity and relevant evidence after the answer. A changed target/evidence voids
approval. Never switch the active Kubernetes context; pass
--contextexplicitly every time. - Mutating Git/Kubernetes commands are deliberately not preapproved by this skill's tool list.
Obtain any required runtime permission as well as the current action answer; denial stops the
operation, never triggers a broader shell grant. For read-only Kubernetes evidence use
kubectl get --context <context> --namespace <namespace> ...with explicit safe fields. - Verify the actual outcome before recording it. Stop on failure or uncertainty; no automatic retry, rollback, push, tag, history rewrite, or deletion. Credentials remain in the keyring; never print Secret data or config values.
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.
- 2d ago First seen · 129 lines · 35 tokens per session scan A 75c19541d898
release-maintenance is a skill published in the GitHub repository flurdy/agent-skills (9 stars, last pushed 4d ago), licensed MIT. It adds 35 tokens to every session and 1,541 once invoked, about $0.0002 per session on Opus 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 2026-09-08.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…