Borrowing it
Nothing to install: this file belongs to volantlabs/vellis. 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/volantlabs/vellis/main/.agents/skills/model-hygiene-review/SKILL.mdgit clone --depth 1 https://github.com/volantlabs/vellisWrote 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/volantlabs/vellis/model-hygiene-review)<a href="https://agentmods.dev/skills/volantlabs/vellis/model-hygiene-review"><img src="https://agentmods.dev/badge/skills/volantlabs/vellis/model-hygiene-review/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/volantlabs/vellis/model-hygiene-review"><img src="https://agentmods.dev/badge/skills/volantlabs/vellis/model-hygiene-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00072 | $0.00573 |
| Opus 5.5 | $0.00029 | $0.00229 |
| Sonnet 5.5 | $0.00014 | $0.00115 |
| Haiku 4.5 | $0.00007 | $0.00057 |
Grade A, and why
model-hygiene-review 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 2mo 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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Model Hygiene Review
Review divergence without assuming that either the accepted model or current implementation is automatically correct. Produce an advisory authority assessment before changing either side.
Workflow
-
Run the deterministic evidence collector for the requested stable ID. Omit the target only when the user requests every accepted component:
just model-audit component.rtg.queryRead the JSON bundle under
build/model-audits/. Treat comparisons as leads, not findings. -
Read
references/authority-triage.mdcompletely. Identify the model lifecycle, owner, requirements, satisfiers, realization binding, codecs, verification cases, and exact evidence nodes. -
Inspect the public implementation protocol, behavior, black-box tests, adapters, and consumers. Do not infer a contract from private helpers.
-
Inspect
git log --follow, the introducing commits on both sides, and any predecessor accepted specification. Determine whether code predates the model, implements a later decision, or merely drifted. -
Invoke
sysml-referenceonly when syntax or language semantics affect the conclusion. Report the specification, section, printed or physical page, and whether the source is normative or informative. Do not use training recall as specification evidence. -
Classify every material difference using the authority-triage reference. Separate an explicit realization codec or intentional implementation freedom from public semantic drift.
-
Report compatibility impact, confidence, evidence on each side, proposed authority, and the smallest verification needed before remediation.
Safety Rule
This skill is review-only. Do not edit the model, implementation, tests, generated views, or
evidence while performing the audit. If accepted behavior is unresolved, classify it as
human_decision_required and pause for the human owner. Successful parsing, tests, or evidence
reference resolution are evidence, not proof of semantic agreement or verification closure.
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.
- 2mo ago First seen · 57 lines · 72 tokens per session scan A 9f8f0543431b
model-hygiene-review is a skill published in the GitHub repository volantlabs/vellis (9 stars, last pushed 4d ago), licensed Apache-2.0. It adds 72 tokens to every session and 573 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 2026-08-31.
Other skills, from other repositories
pre-pr
Prepare a Honcho change for a pull request to plastic-labs/honcho. Invoke before opening a PR, when drafting a PR body, when asked if a branch is PR-ready, or when filling the pull request template. Checks required tests and docs, then writes Description / Proofs / Fixes.
source-command-github-pr-enhance
Migrated source command github-pr-enhance.
Pair Programming
AI-assisted pair programming with multiple modes (driver/navigator/switch), real-time verification, quality monitoring, and comprehensive testing. Supports TDD, debugging, refactoring, and learning sessions. Features automatic role switching, continuous code review, security scanning, and performance optimization with…
pr-comment-evaluator
Use to judge whether a PR review comment sounds polite.
diff-risk-explainer
Use to briefly explain small code diffs.
code-review
Review a diff against its acceptance criteria in four segments (convention adherence, bug scan, historical-context regressions, test-coverage gaps) as a NON-implementing agent. Findings are sorted by severity, each with file:line + a failure scenario. A planted defect must be caught; a clean diff must not be…