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 hoatv2211/GameStudio-CodexKIT --skill release-candidate-preflightgit clone --depth 1 https://github.com/hoatv2211/GameStudio-CodexKITWrote 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/hoatv2211/gamestudio-codexkit/release-candidate-preflight)<a href="https://agentmods.dev/skills/hoatv2211/gamestudio-codexkit/release-candidate-preflight"><img src="https://agentmods.dev/badge/skills/hoatv2211/gamestudio-codexkit/release-candidate-preflight.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 5.1 | $0.00039 | $0.00853 |
| Opus 5 | $0.00019 | $0.00426 |
| Sonnet 5 | $0.00008 | $0.00171 |
| Haiku 4.5 | $0.00004 | $0.00085 |
Grade A, and why
release-candidate-preflight 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 7d 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Release Candidate Preflight
Overview
Gate a release candidate on complete, build-bound evidence while keeping store upload, deployment, and publication outside the read-only decision.
When to use
Use for milestone candidates, hotfix candidates, platform packages, server releases, content updates, and go/no-go review preparation.
When NOT to use
Do not use to publish, deploy, submit to a store, sign binaries, or waive missing evidence without the named human authority.
Required inputs and context discovery
Collect candidate version and hashes, source snapshot, build commands, artifact paths, test suites, defects, performance results, security checks, data migrations, compatibility matrix, release notes, monitoring, rollback plan, owners, and approvals.
Safety and risk level
Read-only gate. Missing required evidence, mismatched build identity, unresolved release blockers, or unavailable rollback produces FAIL or BLOCKED, never assumed PASS.
Workflow
- Bind all evidence to the exact candidate build and source snapshot. Completion criterion: hashes, versions, and artifact paths agree across records.
- Validate required build, test, security, performance, migration, and compatibility evidence. Completion criterion: every required gate has a command, exit code, artifact, and freshness status.
- Review open defects, waivers, ownership, and player-impact risks. Completion criterion: each accepted risk names an approver, scope, expiry, and mitigation.
- Verify monitoring, rollback, support, and incident readiness. Completion criterion: rollback target, trigger, owner, and validation steps are concrete.
- Produce a go, no-go, or
BLOCKEDrecommendation. Completion criterion: the recommendation lists all failed, blocked, and waived gates without performing release actions.
Evidence and output contract
Produce release-preflight.json with candidate identity, gate results, defects, waivers, owners, monitoring, rollback, recommendation, limitations, and missing evidence.
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.
- 7d ago First seen · 79 lines · 39 tokens per session scan A d9dbb3e56413
release-candidate-preflight is a skill published in the GitHub repository hoatv2211/GameStudio-CodexKIT (3 stars, last pushed yesterday), licensed MIT. It adds 39 tokens to every session and 853 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 2026-08-31.
Other skills, from other repositories
agent-release-manager
Agent skill for release-manager - invoke with $agent-release-manager.
agent-release-swarm
Agent skill for release-swarm - invoke with $agent-release-swarm.
agent-github-modes
Agent skill for github-modes - invoke with $agent-github-modes.
github-automation
GitHub workflow automation, PR management, issue tracking, and code review coordination. Integrates with GitHub Actions and repository management. Use when: PR creation, code review, issue management, release automation, workflow setup. Skip when: local-only changes, non-GitHub repositories.
git-integration
Git commit patterns, formats, and conventions for GSD methodology. Provides atomic commits per task, structured commit messages, planning file commits, branch management, and milestone tag operations.
strict-tdd
Strict RED->GREEN->REFACTOR test-driven development with enforcement. Never write production code before a failing test. Atomic commits per TDD cycle.