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/risk-judgment-shapenpx skills add BlueWaterCorp/RiskModels_API --skill risk-judgment-shapegit 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/risk-judgment-shape)<a href="https://agentmods.dev/skills/bluewatercorp/riskmodels_api/risk-judgment-shape"><img src="https://agentmods.dev/badge/skills/bluewatercorp/riskmodels_api/risk-judgment-shape.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 | $0.00073 | $0.02084 |
| Opus 5 | $0.00036 | $0.01042 |
| Sonnet 5 | $0.00015 | $0.00417 |
| Haiku 4.5 | $0.00007 | $0.00208 |
Grade A, and why
risk-judgment-shape 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 — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Risk Judgment — public boundary
What this skill protects
The bwmacro/RiskModels stack centralizes risk interpretation (turning raw ERM3 outputs into qualified, PM-readable language) into a single engine that lives privately in BWMACRO. RiskModels_API is the public layer — data, math, chart primitives — and must not contain the editorial vocabulary that the engine produces.
If you are about to write a string like:
"Strong Residual Alpha","Solid Residual Quality","Muted", …"performance is beta-driven","returns are driven by idiosyncratic exposure", …"ranks near the top of the cohort","sits near the cohort median", …"High Systematic Exposure","Underperforming SMH", …
… STOP. That is editorial vocabulary. It belongs in BWMACRO, not here.
When this skill applies
- Any change to a snapshot renderer (
sdk/riskmodels/snapshots/*.py). - Any change to API route handlers under
app/api/that surface natural-language descriptions of risk. - Any change to MCP tools that return "interpreted" output.
- Any new feature that classifies a stock or portfolio into a state (driver = systematic / balanced / idiosyncratic, quality = strong / solid / muted, etc.).
The contract — public side (this repo)
The single public surface for interpretation in this repo is
sdk/riskmodels/interpretation.py.
It exports:
| Symbol | Purpose |
|---|---|
Judgment |
Frozen dataclass — the contract every consumer reads. Fields: version, as_of, ticker, features, text, states, flags. |
INTERPRETER_VERSION |
Schema version. Bumped when the public feature dictionary changes shape. |
compute_features(data) -> dict |
Pure numeric extraction from a DDData. No qualifiers, no thresholds. Both the bland stub and the BWMACRO engine consume this. |
derive_default_judgment(data) -> Judgment |
Bland public stub. text fields are raw numerics only ("AAPL — systematic 39%, residual +1.9%, peer rank 78") — no qualifiers, no editorial. |
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 · 171 lines · 73 tokens per session scan A 68311b805936
risk-judgment-shape is a skill published in the GitHub repository BlueWaterCorp/RiskModels_API (0 stars, last pushed 4d ago), licensed Apache-2.0. It adds 73 tokens to every session and 2,084 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 2026-08-31.
Other skills, from other repositories
convex-add
Add a capability to the CURRENT Convex app — consults the served Convex capability catalog for always-current procedures (billing, crons, auth, agent, search, …); falls back to built-in hosting or @convex-dev component search. TRIGGER when the user runs /add, or asks to add hosting/publishing or any backend capability…
twitter-reader
Read Twitter/X for financial research using opencli (read-only). Use this skill whenever the user wants to read their Twitter feed, search for financial tweets, view bookmarks, look up user profiles, or gather market sentiment from Twitter/X. Triggers include: "check my feed", "search Twitter for", "show my…
chenhao-limit-up
Use when evaluating A-share limit-up (涨停板) setups through Chen Hao's sentiment and momentum lens: market emotion cycles, board strength, follow-through, and short-term aggressive momentum trading.
trading-risk-gate
Unified pre-trade safety gate: Ruin check (Law #1), ergodicity audit, and win-rate dominance validation. Absorbs: ergodicity-check, law-of-ruin, win-rate-dominance.
cwv-optimizer
Diagnose and fix Core Web Vitals issues on AEM Edge Delivery Services pages. Goes deeper than generic CWV advice by understanding EDS-specific performance patterns including the 100KB LCP budget, E-L-D loading phases, block rendering behavior, and third-party script impact. Produces specific fixes for LCP, CLS, and…
multi-expert-analyzer
针对通用问题进行多领域专家联合分析, 综合稿产生前必经 fact-checker 与 red-team 两道独立校验。适用场景: 用户提出跨领域或不确定领域的复杂问题, 需要从多个专家角度分别搜证并相互校验后综合成文, 例如该不该买房、该不该跳槽、是否进入某个赛道等。触发关键词: 多角度分析、专家分析、综合分析、多视角、跨领域分析、从不同角度看、深度分析。问题只属于单一明确领域时, 优先使用该领域的专门 skill, 例如纯财务用 finance-core-analysis、纯技术用 software-architect。输出 (全部 markdown 保存到当前项目 markdown/ 目录): (1) 每位专家的中间分析稿…