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 skills add VincentChuWaiChow/vanguard-frontier-agentic --skill model-registry-refreshgit clone --depth 1 https://github.com/VincentChuWaiChow/vanguard-frontier-agenticWrote 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/vincentchuwaichow/vanguard-frontier-agentic/model-registry-refresh)<a href="https://agentmods.dev/skills/vincentchuwaichow/vanguard-frontier-agentic/model-registry-refresh"><img src="https://agentmods.dev/badge/skills/vincentchuwaichow/vanguard-frontier-agentic/model-registry-refresh/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/vincentchuwaichow/vanguard-frontier-agentic/model-registry-refresh"><img src="https://agentmods.dev/badge/skills/vincentchuwaichow/vanguard-frontier-agentic/model-registry-refresh.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, 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 103 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 | $0.00079 | $0.01878 |
| Opus 5 | $0.00039 | $0.00939 |
| Sonnet 5 | $0.00016 | $0.00376 |
| Haiku 4.5 | $0.00008 | $0.00188 |
Grade A, and why
model-registry-refresh 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 — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Model Registry Refresh
Doctrine
catalog/model-registry.json is the single source of truth scripts/model-policy.mjs fails closed
against. Every model name and reasoning-effort value it accepts must trace to official documentation
with a citation — never to memory, never to a plausible-sounding guess at a slug. This skill is the
repeatable workflow for keeping that registry accurate without letting research cost dominate the
orchestrator's context.
When to run
npm run model-policy:checkfails with an error naming a model "not in the verified model registry" — the registry is missing a model the policy (or an operator) wants to use.- A provider (OpenAI, Anthropic, Cursor) ships new models or retires old ones and the catalog needs to reflect current reality.
- Quarterly staleness check —
last_refreshedincatalog/model-registry.jsonis more than ~3 months old.
Step 1 — delegate research to Haiku Explore agents
Fan out one Haiku Explore agent per harness (or per namespace, for codex) using the Context7 MCP
tools (mcp__Context7__resolve-library-id then mcp__Context7__query-docs) plus official docs
URLs already cited in the registry. Each research task must:
- Ask for exact slugs/IDs, not families —
gpt-5.5not "the gpt-5 line". - Ask for reasoning-effort support per model, not per harness — some models in a family
predate newer effort levels (see
o1/o3/o4-minilackingnone/minimal/xhighin the current registry). - Ask for failure-mode evidence — what error shape a bad model name or unsupported effort
actually produces (HTTP status, error code/type), so
docs/model-policy-matrix.md's failure table stays accurate. - Require a source citation per claim — a Context7 library ID + section, or an official docs URL. A finding without one is not actionable.
- Require an explicit
UNVERIFIEDflag on anything the agent could not confirm from a primary source (e.g. inferred from a changelog mention, or contradicted between two docs). Do not let an agent silently round an uncertain claim into a confident one.
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 · +23 lines 833af3adb991
- 11d ago First seen · 106 lines · 79 tokens per session scan A 92de5f22ab2c
model-registry-refresh is a skill published in the GitHub repository VincentChuWaiChow/vanguard-frontier-agentic (22 stars, last pushed 2d ago), licensed Apache-2.0. It adds 79 tokens to every session and 1,878 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
r-ml
R machine learning packages. Use for classification, regression, clustering, deep learning, gradient boosting (xgboost, lightgbm), random forests, neural networks, and time series forecasting.
r-parallel
R parallel computing and high performance packages. Use for multi-core processing, distributed computing, Spark integration, and C++ acceleration with Rcpp.
broom
R broom package for tidying model outputs. Use for converting statistical model results to tidy data frames.
r-ml-boosting
R gradient boosting packages. Use for xgboost, lightgbm, gbm, and catboost.
lightgbm
R lightgbm package for gradient boosting. Use for fast, distributed, high-performance gradient boosting.
xgboost
R xgboost package for gradient boosting. Use for high-performance classification, regression, and ranking.