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 codexkit-repository-maintenancegit 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/codexkit-repository-maintenance)<a href="https://agentmods.dev/skills/hoatv2211/gamestudio-codexkit/codexkit-repository-maintenance"><img src="https://agentmods.dev/badge/skills/hoatv2211/gamestudio-codexkit/codexkit-repository-maintenance.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 | $0.00045 | $0.01292 |
| Opus 5 | $0.00023 | $0.00646 |
| Sonnet 5 | $0.00009 | $0.00258 |
| Haiku 4.5 | $0.00005 | $0.00129 |
Grade A, and why
codexkit-repository-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 yesterday.
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.
CodexKIT Repository Maintenance
Overview
Maintain and improve this repository without confusing kit-source work with game-project work. Keep the main thread responsible for repository integration, route specialist analysis to existing distributed skills, edit canonical sources, and bind every verdict to evidence.
Repository identity gate
Before any write, resolve the repository root and verify all of these facts:
.codex-plugin/plugin.jsonexists and declaresgame-studio-codex-kit.registry/capabilities.yamlexists.scripts/validate.pyexists.skills/exists.
If any check fails, stop with BLOCKED: repository identity mismatch. Do not reinterpret another repository as CodexKIT and do not apply this workflow to a game project that merely installed the plugin.
Scope
Use this skill for repository architecture, skill or agent authoring, registries, packs, personas, generators, adapters, project initialization, GitHub Actions, tests, packaging, documentation, versioning decisions, release readiness, and evidence-backed technical-debt cleanup.
Keep gameplay, content, services, assets, and operational changes in consuming game projects outside this workflow. Treat private studio projects, .research/, and external repositories as read-only unless a separate explicit request authorizes their use.
Intake
- Record repository path, branch, requested outcome, owned write scope, do-not-touch scope, and current tracked or untracked changes.
- Read
AGENTS.mdand the relevant canonical files before selecting an edit. - Classify the request using the routing table.
- Preserve unrelated work and assign one writer per file, shared registry, or generated output.
Routing
| Maintenance class | Route or evidence source |
|---|---|
| Failure, regression, CI, or unexpected behavior | evidence-first-debugging and the exact failing command or Actions log |
| Skill creation, revision, trigger collision, provenance, or maturity | skill-authoring-and-audit |
| Build, test, package, runtime, or cross-platform verification | build-and-runtime-verification |
| Broad diff or independent review | review-swarm with read-only review lanes |
| Candidate readiness or semantic-version decision | release-candidate-preflight |
| Multi-agent ownership | studio-agent-orchestration after repository scope is fixed |
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.
- yesterday Changed a7c3487401b6
- 8d ago First seen · 98 lines · 45 tokens per session scan A 87e6d23a6df0
codexkit-repository-maintenance is a skill published in the GitHub repository hoatv2211/GameStudio-CodexKIT (3 stars, last pushed yesterday), licensed MIT. It adds 45 tokens to every session and 1,292 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
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.
finishing-a-development-branch
Use when implementation is complete, all tests pass, and you need to decide how to integrate the work.
document
Run /document pr | changelog | release-note | postmortem (or let it ask) to write the human facing prose about a change. Drafts from the real commits and diff, writing to the right place. Does not write code, tests, or specs.
version-bump
Version the Team plugin at land time (DEV-internal, not distributed): decide the SemVer level, compute the next free version against current main, update all six version strings, cut the [Unreleased] changelog body into a dated [X.Y.Z] section, run the land-time consistency assertion, and commit chore(version): X.Y.Z.…
team-pr
Opens a pull request after verification. Trigger on "open the PR", "open a draft PR", or "/team-pr" only; never infer the phase from passed verification.
changelog
Defines Keep a Changelog updates. Load when the ship phase updates CHANGELOG.md with user-facing changes.