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/bluewatercorp/riskmodels_api/riskmodels-smart-subheadernpx skills add BlueWaterCorp/RiskModels_API --skill riskmodels-smart-subheadergit clone --depth 1 https://github.com/BlueWaterCorp/RiskModels_APIWrote 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/bluewatercorp/riskmodels_api/riskmodels-smart-subheader)<a href="https://agentmods.dev/skills/bluewatercorp/riskmodels_api/riskmodels-smart-subheader"><img src="https://agentmods.dev/badge/skills/bluewatercorp/riskmodels_api/riskmodels-smart-subheader.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 | $0.00048 | $0.00781 |
| Opus 5 | $0.00024 | $0.00391 |
| Sonnet 5 | $0.00010 | $0.00156 |
| Haiku 4.5 | $0.00005 | $0.00078 |
Grade A, and why
riskmodels-smart-subheader 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 3d 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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
RiskModels Smart Subheader Generator
When building or refining any chart in sdk/riskmodels/snapshots/ or sdk/riskmodels/visuals/
(R1 profile, waterfall, hedge cascade, etc.), generate the subheader (the italic explanatory
sentence(s) under each section title) using the smart_subheader module.
Module Location
sdk/riskmodels/visuals/smart_subheader.py
Usage
from riskmodels.visuals.smart_subheader import generate_subheader
text = generate_subheader(
chart_type="er_attribution", # or "hr_cascade", "peer_table", etc.
title="L3 Explained-Return Attribution",
data=metrics_dict, # the raw metrics powering the chart
data_as_of="2026-04-04", # from RiskLineage.data_as_of
time_range="past 252 trading days",
ticker="NVDA",
benchmark="SOXX",
use_llm=False, # True to enable LLM enhancement
)
Supported Chart Types
| chart_type | Used by | Description |
|---|---|---|
er_attribution |
R1 Panel I | L3 ER decomposition horizontal bar |
hr_cascade |
R1 Panel II | Hedge-ratio cascade grouped bar |
peer_table |
R1 Panel III | Peer comparison table |
waterfall |
S2, future R3 | Return attribution waterfall |
histogram |
Future R2/P2 | Cross-sectional distribution |
multi_line |
Future R2/P2 | Time series overlay |
stacked_area |
Future R4 | Factor contribution stacked area |
Strict Rules
- Always mention the exact time range (e.g. "over the past 252 trading days ending 2026-04-04")
- Always include data_as_of from lineage
- Use only real numbers from the data dict — never round, estimate, or hallucinate
- Never say "outperformance by X%" without the exact period
- Max 2 short sentences, institutional tone (think Bloomberg PORT commentary)
- Rule-based mode is the default — no LLM dependency for rendering
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.
- 3d ago First seen · 91 lines · 48 tokens per session scan A a7560bfcebbc
riskmodels-smart-subheader is a skill published in the GitHub repository BlueWaterCorp/RiskModels_API (0 stars, last pushed 4d ago), licensed Apache-2.0. It adds 48 tokens to every session and 781 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…