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/Agent-Hellboy/mcp-runtimenpx agentmods add skills/agent-hellboy/mcp-runtime/release-readinessWrote 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/agent-hellboy/mcp-runtime/release-readiness)<a href="https://agentmods.dev/skills/agent-hellboy/mcp-runtime/release-readiness"><img src="https://agentmods.dev/badge/skills/agent-hellboy/mcp-runtime/release-readiness/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/agent-hellboy/mcp-runtime/release-readiness"><img src="https://agentmods.dev/badge/skills/agent-hellboy/mcp-runtime/release-readiness.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 | $0.00077 | $0.01257 |
| Opus 5.5 | $0.00031 | $0.00503 |
| Sonnet 5.5 | $0.00015 | $0.00251 |
| Haiku 4.5 | $0.00008 | $0.00126 |
Grade A, and why
release-readiness 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 2mo 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 — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Release Readiness
Overview
Use this skill when the user asks whether a branch can merge, ship, canary, or release. It is a coordinator, not a replacement for the focused skills. Load the matching skill for each surface you exercise and report one consolidated go/no-go result.
This workflow is intentionally repo-native. External agent workflows can inspire the order of review passes, but MCP Runtime release evidence must come from the repo's own commands, skills, CI, cluster state, docs, and security model.
Step 1 - Define Release Scope
Inspect the current state before choosing checks:
git status --short
git diff --stat origin/main...HEAD
git diff --name-only origin/main...HEAD
If the working tree has unrelated user changes, do not include them in a release commit or claim they were validated. If the user wants a tag or deploy, confirm the target version, branch, and environment before any destructive or external action.
Classify the request:
- merge-readiness: branch can be reviewed and merged.
- release-readiness: version/tag candidate can be cut.
- canary-readiness: candidate can be promoted to a limited environment.
- post-release-check: verify a just-shipped build and document evidence.
Step 2 - Route By Change Surface
Choose every applicable focused skill:
| Surface | Required skill |
|---|---|
| Operator, setup, registry, ingress, CLI, CRDs, service rollout | qa-e2e-operations |
| Auth, grants, sessions, gateway policy, audit, TLS, secrets | security-audit and often qa-e2e-security |
| Platform-wide release security signoff | security-audit-platform |
| Kubernetes RBAC, PSS, NetworkPolicy, manifests | k8s-hardening-audit |
| Images, SBOMs, GitHub Actions, dependency or base-image changes | supply-chain-audit |
| Sentinel dashboard, UI-visible API behavior, login/admin/tenant flows | qa-e2e-ui |
| MCP protocol behavior or upstream spec compatibility | mcp-spec-compliance |
| Gateway/API/operator hot paths or "feels slower" risk | qa-e2e-perf |
| Public k3s, TLS, ACME, production hostnames | k3s-public-ops or mcp-runtime-platform-public |
| Docs, CLI examples, contributor guidance, release notes | repo-guidance-sync |
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.
- 2mo ago First seen · 139 lines · 77 tokens per session scan A 38dd233140e3
release-readiness is a skill published in the GitHub repository Agent-Hellboy/mcp-runtime (6 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 77 tokens to every session and 1,257 once invoked, about $0.0003 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 2026-08-31.
release-readiness compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| release-readinessAgent-Hellboy/mcp-runtime | Skill | 6 | 1mo ago | Apache-2.0 | A | 77 | Codex |
| Verification & Quality Assuranceruvnet/ruflo | Skill | 81k | today | MIT | A | 36 | Claude Code |
| quality-scandiegosouzapw/OmniRoute | Skill | 83k | 5d ago | MIT | A | 45 | Claude Code, Codex |
| e2e-testingthedaviddias/Front-End-Checklist | Skill | 75k | 6d ago | MIT | A | 38 | Claude Code, Codex |
| cionsi/ginkgo | Skill | 9.1k | 4d ago | MIT | A | 151 | Claude Code |
| mirrord-prev-envmetalbear-co/mirrord | Skill | 5.4k | yesterday | MIT | A | 122 | Claude Code, Codex |
| test-setupDonchitos/Claude-Code-Game-Studios | Skill | 36k | 18d ago | MIT | A | 32 | Claude Code |