Borrowing it
Nothing to install: this file belongs to alecs5am/ralphy. 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/alecs5am/ralphy/main/.agents/skills/workspace-eval/SKILL.mdgit clone --depth 1 https://github.com/alecs5am/ralphyWrote 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/alecs5am/ralphy/workspace-eval)<a href="https://agentmods.dev/skills/alecs5am/ralphy/workspace-eval"><img src="https://agentmods.dev/badge/skills/alecs5am/ralphy/workspace-eval/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/alecs5am/ralphy/workspace-eval"><img src="https://agentmods.dev/badge/skills/alecs5am/ralphy/workspace-eval.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Agent Snooping · line 73 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 74 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 75 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00303 | $0.01490 |
| Opus 5.5 | $0.00121 | $0.00596 |
| Sonnet 5.5 | $0.00061 | $0.00298 |
| Haiku 4.5 | $0.00030 | $0.00149 |
Grade A, and why
workspace-eval 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 1mo 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
workspace-eval — run the universe rubric
A thin wrapper over the #469 runner. Your input is a project id + its workspace's custom rubric; your output is the per-criterion scorecard plus, on a non-clean verdict, a handoff to repair. The engine is ralphy workspace eval — this skill is only the agent-facing surface.
ALSO FIRE
- After a render, when the user wants a standalone score against the universe's bar without running the full four-stage
/universe-studioorchestrator. - When the user drops a
<project>and asks whether it clears the workspace's own criteria (distinct from the generic/evaluatorgates).
DO NOT FIRE
- For the generic structural / audio / caption / vision gates on an arbitrary mp4 — that is
/evaluator. This skill scores against the per-workspace CUSTOM rubric. - For applying fixes — that is
/fixer/ the repair loop (#409). This skill only produces the scorecard and routes failures onward. - For a workspace WITHOUT an
evaluators.jsonrubric — there are no custom criteria to score; the runner reports "no rubric configured". Route to/evaluatorfor the built-in gates instead. - As the per-stage gate inside the four-stage flow — that is
/universe-studio, which drives this same runner per stage.
HARD INVARIANTS
Inherited from AGENTS.md:
ralphyis the only entry-point. Run the eval throughralphy workspace eval— never call the model or probe the mp4 directly.- Append-only. The runner archives any existing
workspace-eval.json/workspace-eval-report.mdto.vNbefore writing the fresh one; never--force-overwritewithout the user asking. - Read
MODELS.mdbefore overriding the vision model (--model).
Run it
ralphy workspace eval <project>
Flags:
--no-vision— deterministic criteria only, NO model call (a free pass; use it to check the code-checked criteria without spending).--model <id>— override the deep-vision model (defaultgoogle/gemini-3.1-pro-preview; checkMODELS.mdfirst).--workspace <slug>— score against a different workspace's rubric (default: the project's registered workspace).--video <path>— override the scored video (default<project>/render/final.mp4).
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.
- 1mo ago First seen · 76 lines · 303 tokens per session scan A 6f6947a62e4c
workspace-eval is a skill published in the GitHub repository alecs5am/ralphy (140 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 303 tokens to every session and 1,490 once invoked, about $0.0012 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 2026-08-30.
Other skills, from other repositories
llm-as-judge-evaluation
Evaluate LLM outputs using frontier models as judges. Use for pairwise model comparison, quality scoring with custom rubrics, and automated evaluation pipelines. Covers position bias mitigation, statistical significance, and generating preference data for DPO/RLHF.
reproduce
Reproduces a paper's result, a claim, an artifact or a previous run with the target and success criterion frozen first, the canonical code path run before any substitute, exact inputs, environment, seeds and commands captured, and a verdict from a fixed set, reproduced, reproduced within tolerance, partially…
acceptance-checks
Turns the acceptance criteria a task states into executable checks and runs them against the finished outputs before delivering, rather than trusting that a correct-looking analysis satisfies them; rehearses the hidden condition when the grader scores unseen instances from a described family; treats a stated formula…
submitted-code
Writes code that survives being re-executed by someone else on inputs you never saw, targeting the grader's or collaborator's runtime rather than your own, with one self-contained entry point using only the libraries the specification names, no reliance on packages you installed or files you cached during development…
generated-media-qa
Provider-independent quality assurance for AI-generated and AI-assisted media. Use when reviewing, accepting, revising, or reporting on images, video, audio, avatars, ads, product content, social clips, explainers, localization, mixed-source edits, captions, accessibility, provenance, model metadata, safety/policy…
video-gen
Use when generate videos with AI models — Runway, Kling, Sora, Pika, Seedance 2.0, Grok Imagine, Veo. Text-to-video, image-to-video, video extension, multi-modal references. Use when generating video from text prompts, animating images, or creating AI video content.