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 skill-authoring-and-auditgit 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/skill-authoring-and-audit)<a href="https://agentmods.dev/skills/hoatv2211/gamestudio-codexkit/skill-authoring-and-audit"><img src="https://agentmods.dev/badge/skills/hoatv2211/gamestudio-codexkit/skill-authoring-and-audit/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/hoatv2211/gamestudio-codexkit/skill-authoring-and-audit"><img src="https://agentmods.dev/badge/skills/hoatv2211/gamestudio-codexkit/skill-authoring-and-audit.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 | $0.00041 | $0.01221 |
| Opus 5 | $0.00020 | $0.00611 |
| Sonnet 5 | $0.00008 | $0.00244 |
| Haiku 4.5 | $0.00004 | $0.00122 |
Grade A, and why
skill-authoring-and-audit 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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill Authoring and Audit
Overview
One governance skill supports two modes: author creates or updates a needed workflow; audit detects gaps, collisions, stale maturity, and unsupported claims. Update-first is mandatory.
When to use
Use when a recurring workflow needs codification, a skill trigger is ambiguous, session history reveals repeated failures, or catalog lifecycle and provenance need review.
When NOT to use
Do not use this skill merely to execute or report an existing evaluation, and do not author a skill for a one-off task, duplicate an existing capability, copy noncommercial content, or promote maturity without eval and dogfood evidence.
Required inputs and context discovery
Collect requested mode, catalog and registries, existing descriptions, project-local skills and agent roles, routing cases, session or issue evidence, provenance source/license/SHA, owner, reviewer, risk, and target pack.
Safety and risk level
Writes are limited to owned skill, eval, registry, and documentation paths. Never mutate .research sources, external projects, generated adapters, or copied NC content.
Workflow
- Scan the catalog and bundled helpers for exact, neighboring, deprecated, reusable, or updateable capabilities. Completion criterion: the decision is reuse, update, new skill or tool, backlog, or no action, with existing workflows and tools preferred.
- In
authormode, create failing routing, behavior, or pressure cases from observed needs before editing the skill. Completion criterion: the gap is reproducible and not a hypothetical preference. - Write the smallest complete skill with closed schema, provenance, safety, evidence, workflow criteria, and concise triggers. Completion criterion: structural validation passes for the skill.
- Run deterministic routing, behavior, pressure, originality, and safety checks.
For a governed Tier-B, behavior, or pressure run, capture
python -B scripts/catalog_audit.py . --input-digestimmediately before invoking the model and store that value asinput_digestin the runner status. Run the catalog audit afterward so it compares the recorded digest with the then-current inputs. Completion criterion: failures are repaired without weakening cases, and accepted runner evidence has one uniquely newest timezone-aware timestamp, is no older than 90 days, and matches current catalog, shipped-skill, evaluator, and eval inputs. - In
auditmode, scan catalog, project overlays, agent-role IDs, and session history for stale skills, repeated manual workflows, trigger or role collisions, missing owners, and observed-versus-target KPI gaps. Completion criterion: findings have evidence, owner, severity, and update-first recommendation. - Apply lifecycle promotion or demotion only when prerequisites are observed. Completion criterion: registry maturity matches evidence rather than aspiration.
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.
- 2d ago Changed · +3 lines 0f179653d4ea
- 3d ago Changed · +3 lines 945a9914a5e0
- 9d ago First seen · 85 lines · 41 tokens per session scan A 8829da1344ef
skill-authoring-and-audit is a skill published in the GitHub repository hoatv2211/GameStudio-CodexKIT (3 stars, last pushed 2d ago), licensed MIT. It adds 41 tokens to every session and 1,221 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
deep-discovery
Use when the user asks for deep discovery, 100-question brainstorming, idea interrogation, architecture stress testing, strategy vetting, weakness finding, hole-poking, exhaustive exploration, planning or auditing Codex plugins or skills, or pre-commitment review of a design, plan, strategy, architecture, product…
prewalk
Use when the user wants a coding task executed with a strong planner model first and a faster/cheaper executor model after the first successful implementation edit.
registry-broker-orchestrator
Use Registry Broker to discover and summon specialist agents for focused subtasks from inside Codex.
codex-sdd:customize
Guide for injecting custom MCP tools, skills, and hook points into the OpenSpec workflow for team-specific processes.
codex-sdd:archive
Preserve change artifacts (proposal, design, tasks) into structured archive and update knowledge base. Final phase of OpenSpec workflow.
codex-sdd:plan
Create design.md with technical architecture and tasks.md with executable breakdown from an approved proposal. Second phase of OpenSpec workflow.