Borrowing it
Nothing to install: this file belongs to WingedGuardian/skyrimvr-claude-toolkit. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/WingedGuardian/skyrimvr-claude-toolkit/master/.agents/skills/devbench/SKILL.mdgit clone --depth 1 https://github.com/WingedGuardian/skyrimvr-claude-toolkitWrote 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/wingedguardian/skyrimvr-claude-toolkit/devbench)<a href="https://agentmods.dev/skills/wingedguardian/skyrimvr-claude-toolkit/devbench"><img src="https://agentmods.dev/badge/skills/wingedguardian/skyrimvr-claude-toolkit/devbench/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/wingedguardian/skyrimvr-claude-toolkit/devbench"><img src="https://agentmods.dev/badge/skills/wingedguardian/skyrimvr-claude-toolkit/devbench.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 | $0.00073 | $0.03157 |
| Opus 5.5 | $0.00029 | $0.01263 |
| Sonnet 5.5 | $0.00015 | $0.00631 |
| Haiku 4.5 | $0.00007 | $0.00316 |
Grade A, and why
devbench 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 — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DevBench — the live in-game test channel
The single biggest time sink in modding is the in-game test loop: change something, ask the user to launch the game, have them trigger it, wait, hear "it didn't work", guess again. DevBench breaks that loop. It is a dev-only SKSE plugin (alandtse, Nexus SE 181326 — same author as Engine Fixes VR) that runs a localhost REST + MCP server inside the running game, so the agent can inspect live state, run console commands and read their output, call Papyrus functions and get the return value, dismiss modals, and drive scripted scenarios — directly, while the user just keeps playing.
NOT bundled (GPL-3.0-or-later; the toolkit ships only the wrapper). It changes no gameplay and writes no save data.
It is a mod, not one of the tools/ dev utilities — so do NOT install it for the user. Every
other optional tool lives in tools/ and never touches the game; DevBench is an SKSE plugin that ends
up in Data/SKSE/Plugins/. Hand-copying a DLL there bypasses Vortex/MO2, leaves the file untracked,
and on a managed install a later deploy or purge can clobber it. If the user wants DevBench, they
install it through their own mod manager like any other SKSE plugin; the wrapper below works the
moment it's present.
bash tools/devbench-cli.sh alive # is the GAME running, paused, hung, or not loaded?
bash tools/devbench-cli.sh health # raw off-thread liveness + instance identity
bash tools/devbench-cli.sh ping # server self-test only -- NOT proof of liveness
bash tools/devbench-cli.sh state # {plugin,version,vr,playerLoaded,frame,pid,port,exe}
bash tools/devbench-cli.sh inspect vm # Papyrus VM health — freeze diagnosis
bash tools/devbench-cli.sh exec "player.getav health" # console exec + capture + read output
bash tools/devbench-cli.sh call Actor IsInCombat '[]' '{"form":"0x14"}'
bash tools/devbench-cli.sh notify "Test 3 of 5: swing now" # HUD narration
bash tools/devbench-cli.sh tool menu '{"action":"accept"}' # raw: any tool, any JSON
Hard requirement: the game must be running. The server only exists while the game is genuinely running with a save loaded. In VR that normally means the headset is on (Skyrim VR errors at VR-init without one) -- or headless mode, below. When the game is closed the port is dead — fall back to the offline tools (xelib, Spriggit, ReSaver, PyNifly).
Headless Skyrim VR (no headset): bash tools/vr-headless.sh on. It points the game at SteamVR's
null driver (replacing an OpenComposite openvr_api.dll with SteamVR's own), so the game boots and
DevBench is drivable with nobody in the headset. Close SteamVR first; then start SteamVR, let it
settle (if room setup opens, wait for it to close: launching while it runs gets the game evicted),
and launch the game. bash tools/vr-headless.sh off restores both files byte-exact and verifies
them; it is safe to repeat and after a crash, so run it before the user plays again. Valid only for
pose-independent tests -- scripts, records, console, frame rate. Anything that depends on where the
head and hands are (HIGGS, VRIK, PLANCK, hand collision) needs the real headset. emu on|off swaps in
a pose-emulating driver (its hands track) once the user has built it (tools/vr-emu-driver/README.md:
fetched from a pinned upstream commit, never shipped). Skyrim VR only.
Port is deterministic per runtime: SE/AE 8920, VR 8921 (DevBench iterates if the port is busy
and writes the bound port to Data/SKSE/Plugins/devbench/runtime.json, which the wrapper reads).
Override with DEVBENCH_PORT. MCP clients can point at http://127.0.0.1:<port>/mcp; the REST path
the wrapper uses works any time the server is up, with no reconnect.
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 · +18 lines 92c8e149c587
- 23d ago Changed · +37 lines a7aabbb34d87
- 26d ago First seen · 96 lines · 73 tokens per session scan A b051c48bc483
devbench is a skill published in the GitHub repository WingedGuardian/skyrimvr-claude-toolkit (21 stars, last pushed yesterday), licensed MIT. It adds 73 tokens to every session and 3,157 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 2026-10-12.
devbench compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| devbenchWingedGuardian/skyrimvr-claude-toolkit | Skill | 21 | yesterday | MIT | A | 73 | Claude Code, Codex |
| minecraft-debug-mcpmoeru-ai/airi | Skill | 51k | yesterday | MIT | A | 68 | Codex |
| cli-anything-nsight-graphicsHKUDS/CLI-Anything | Skill | 58k | 1mo ago | Apache-2.0 | A | 29 | Claude Code, Codex |
| performance-optimizationgamedev-skills/awesome-gamedev-agent-skills | Skill | 6.9k | 9d ago | Apache-2.0 | A | 121 | Claude Code |
| unity-consoleBesty0728/Unity-Skills | Skill | 1.9k | yesterday | MIT | A | 10 | Claude Code, Codex |
| diagnosing-bgs-problemshashgraph-online/awesome-codex-plugins | Skill | 1.5k | yesterday | Apache-2.0 | A | 72 | Claude Code, Codex |
| axiom-audit-spritekitCharlesWiltgen/Axiom | Skill | 1.3k | yesterday | MIT | A | 39 | Codex |