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 agentmods add skills/hoatv2211/gamestudio-codexkit/safe-project-mutationnpx skills add hoatv2211/GameStudio-CodexKIT --skill safe-project-mutationgit 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/safe-project-mutation)<a href="https://agentmods.dev/skills/hoatv2211/gamestudio-codexkit/safe-project-mutation"><img src="https://agentmods.dev/badge/skills/hoatv2211/gamestudio-codexkit/safe-project-mutation.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 | $0.00035 | $0.00881 |
| Opus 5 | $0.00017 | $0.00441 |
| Sonnet 5 | $0.00007 | $0.00176 |
| Haiku 4.5 | $0.00003 | $0.00088 |
Grade A, and why
safe-project-mutation 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 6d 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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Safe Project Mutation
Overview
Separate inspection from mutation. Every applied file change must be scoped, reviewable, restorable, and verified.
When to use
Use for scripted edits, bulk normalization, generated files, project scaffolding, config rewrites, asset metadata operations, or any medium-risk file mutation.
When NOT to use
Do not use this skill as the primary owner for a scaffold or per-project adapter; use studio-project-scaffold and keep mutation safety as its dependency. Do not use it to authorize database writes, service control, publishing, credential changes, destructive cleanup, or edits outside the user-approved repository.
Required inputs and context discovery
Require repository root, exact operations, owned paths, excluded paths, expected before/after state, process/editor locks, reviewer, verification command, backup location, and restore objective.
Safety and risk level
Default to report-only. Reject path traversal, source deletion, out-of-scope writes, unknown generated ownership, active editor/build/server conflicts, missing reviewer, or missing restore information.
Workflow
- Normalize every target path and prove it remains inside the approved root. Completion criterion: the report lists no unresolved or out-of-scope target.
- Run report-only mode and calculate proposed changes without writing files. Completion criterion: hashes and diff intent exist while source state is unchanged.
- Create backups for existing targets and a manifest for creates, updates, and restore actions. Completion criterion: each operation has a backup or an explicit “created file; remove on restore” action.
- Apply only the reviewed manifest. Completion criterion: actual hashes match the manifest’s expected outputs.
- Run the declared verification command and capture exit code and artifacts. Completion criterion: success is supported by fresh output or labeled BLOCKED.
- Exercise restore in a fixture or provide a verified restore command for the real scope. Completion criterion: the original hashes can be reproduced.
What ships with it
2 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.
- 6d ago First seen · 85 lines · 35 tokens per session scan A 9705ae2dd069
safe-project-mutation is a skill published in the GitHub repository hoatv2211/GameStudio-CodexKIT (3 stars, last pushed 3d ago), licensed MIT. It adds 35 tokens to every session and 881 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.