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/laurigates/claude-plugins/comfy-corpus-validationnpx skills add laurigates/claude-plugins --skill comfy-corpus-validationgit clone --depth 1 https://github.com/laurigates/claude-pluginsWrote 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/laurigates/claude-plugins/comfy-corpus-validation)<a href="https://agentmods.dev/skills/laurigates/claude-plugins/comfy-corpus-validation"><img src="https://agentmods.dev/badge/skills/laurigates/claude-plugins/comfy-corpus-validation.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 | $0.00037 | $0.02398 |
| Opus 5 | $0.00018 | $0.01199 |
| Sonnet 5 | $0.00007 | $0.00480 |
| Haiku 4.5 | $0.00004 | $0.00240 |
Grade A, and why
comfy-corpus-validation 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 — 178 lines — stays where its author put it; the contents beside it link to each section on GitHub.
comfy-corpus-validation
comfyui-sampler-info ships a JSON corpus (web/data/samplers.json,
web/data/schedulers.json, web/data/models.json) of human-written facts
about ComfyUI's sampler and scheduler tokens — year, family, ODE order,
summary, good_for, pairs_with, and per-model default recipes. The pack's
entire value is that those facts are true. A wrong fact is worse than a
missing one: the UI presents it with the same confidence either way.
This skill is the method for making corpus claims verifiable instead of remembered. It exists because three factual misses shipped or nearly shipped in one day, each caught by luck: a blog-sourced sampler recommendation that the vendor's own template contradicted, a schedule-behaviour claim written from model memory that computing the sigmas falsified, and a model family absent from the corpus entirely because nothing ever asked what the live install offers that we describe. The first real run of the tooling below immediately found a fourth nobody knew about.
The core rule
A claim about ComfyUI is only as good as the highest rung you verified it on. Never write a Tier-3 claim that a Tier-1/2 source could settle but didn't.
When to Use This Skill
| Use this skill when... | Use instead when... |
|---|---|
Adding or editing an entry in web/data/*.json (sampler, scheduler, model recipe) |
Reading generation settings out of an output PNG/WebP/MP4 -> comfy-metadata |
| Auditing whether the corpus's existing facts are still true | Checking whether the pack itself works in a live install -> comfyui-pack-live-smoke |
| A source claims "model M wants sampler S" and you must decide whether to believe it | Debugging the pack's publish/release pipeline -> comfy-registry-lifecycle |
| Asking what the install offers that the corpus says nothing about | Writing the pack's frontend/backend code -> comfyui-node-authoring |
comfyui-pack-live-smoke verifies the pack functions. This skill verifies
its facts are true. A pack can be perfectly working and comprehensively
wrong.
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 First seen · 178 lines · 37 tokens per session scan A dced472ad584
comfy-corpus-validation is a skill published in the GitHub repository laurigates/claude-plugins (58 stars, last pushed today), licensed MIT. It adds 37 tokens to every session and 2,398 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 2026-09-03.
Other skills, from other repositories
build-expression-tree
For symbolic computation: ASTs, mathematical expressions, code that manipulates code structure, expression transformations.
find-convex-hull
For computational geometry: convex hull, point enclosure, polygon operations. Uses monotone chain algorithm with stack-based turn detection.
class-generation
Generate openEHR class documentation — class-definition tables, effective views, and UML class/package diagrams — from BMM schemas with the bmm-publisher tool, for specifications-XX repos and their docs/UML/ content. This skill should be used when the user asks to regenerate class tables, run bmm-publisher, generate…
auditing-subgroup-fairness
Audit an OpenMed NER or de-identification model for performance disparities across demographic subgroups (sex, age band, race/ethnicity when available) using openmed.eval.fairnessreport. Use when the user wants per-subgroup recall and leakage, wants to check whether de-identification under-protects a group, wants to…
tooluniverse-drug-research
Comprehensive drug profiling — mechanism, primary/secondary targets, drug interactions, clinical-trial status, adverse events (FAERS), pharmacogenomics, and approval history. Use for full drug investigation reports, 'tell me about drug X' queries, and assembling drug profiles for clinicians, researchers, or regulatory…
calc-sample-size
Interactive sample size calculator for medical research. Decision-tree guided test selection, reproducible R/Python code, effect size interpretation, and IRB-ready justification text. Supports diagnostic accuracy, agreement, proportions, continuous outcomes, survival, ANOVA, logistic regression, and…