fundamentals-pit

fundamentals-pit is a skill for Claude Code from BlueWaterCorp/RiskModels_API. It costs 107 tokens per session (816 once invoked), scanned A, original, Apache-2.0.

A tool for retrieving quarterly financial measures for a US company as they were actually available by a chosen date. This point-in-time approach prevents later filings or restatements from leaking into historical analysis.

In plain words
What is it for?
Use it to retrieve profitability, cash-flow, leverage, capital-return, risk, and cost-of-capital data for a ticker and historical date.
Why use it?
It helps backtests and past analyses avoid using information investors could not yet have seen.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter.

Part of the riskmodels plugin — 5 skills, 5 commands, 1 agent shipped together

Good fit Use it to retrieve profitability, cash-flow, leverage, capital-return, risk, and cost-of-capital data for a ticker and historical date.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/bluewatercorp/riskmodels_api/fundamentals-pit
Install

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.

Any agent
npx skills add BlueWaterCorp/RiskModels_API --skill fundamentals-pit
Clone the repo
git clone --depth 1 https://github.com/BlueWaterCorp/RiskModels_API

Made for: Claude Code.

Or install riskmodels, the plugin that ships this one along with the rest of its 5 skills, 5 commands, 1 agent.

Wrote 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.

agentmods badge for fundamentals-pit

README.md
[![agentmods](https://agentmods.dev/badge/skills/bluewatercorp/riskmodels_api/fundamentals-pit.svg)](https://agentmods.dev/skills/bluewatercorp/riskmodels_api/fundamentals-pit)
Your own site
<a href="https://agentmods.dev/skills/bluewatercorp/riskmodels_api/fundamentals-pit"><img src="https://agentmods.dev/badge/skills/bluewatercorp/riskmodels_api/fundamentals-pit.svg" alt="Measured on agentmods" height="20"></a>
Per session 107 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 816 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00107 $0.00816
Opus 5 $0.00053 $0.00408
Sonnet 5 $0.00021 $0.00163
Haiku 4.5 $0.00011 $0.00082

Measured 3d ago against content hash 12fc7ed7f4e6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

fundamentals-pit 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.

claude-plugin/plugins/riskmodels/skills/fundamentals-pit/SKILL.md · 63 lines

How it starts

The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Point-in-time quarterly fundamentals

PIT-normalized fundamentals derived from SEC filings and licensed sources. The differentiator is the as_of discipline: rows are returned only where filed_date <= as_of, so a query dated in the past reflects exactly what had been filed by then — no silent restatement, no look-ahead. This skill wraps the hosted RiskModels MCP; it reports tool outputs and computes nothing itself.

What to call

Resolve a company name to a ticker first (riskmodels_search_tickers), then:

  • riskmodels_get_fundamentals — the one tool. Params: ticker, as_of (PIT date, default today), periods (quarterly rows, most recent last). Set grid=true for the cost-of-capital sensitivity table (see the cost-of-capital skill).

Reading the response

Each row carries:

  • Ratios — TTM roe_ttm, roa_ttm, fcf_margin, leverage_ratio, and the capital-return set (payout_ratio, retention_ratio, buyback_ratio, total_payout_ratio, sustainable_growth). Ratios are null unless four finite trailing quarters exist — report null as "not enough history," never as zero.
  • sec_facts — raw line items only for the cells whose serving value is SEC XBRL, each as {value, source} with source ∈ {us_gaap, ifrs}. A concept is absent for a period when that cell is not SEC-sourced. Do not describe the panel as "raw fundamentals" — raw values are present per-cell where SEC-sourced and not elsewhere. Values are as-originally-reported (earliest filing).
  • equity_bridge_residual + equity_bridge_inputs — a disclosed decomposition of the quarter-over-quarter change in equity. The residual is a plug that makes the roll-forward an identity by construction; it is frequently large. Report it as a decomposition, not truth. For modelling, anchor on retained_earnings.
  • Cascade betasbeta_market / beta_sector / beta_subsector with beta_source. beta_market is a short-half-life conditional beta, not a textbook long-run CAPM beta, so for defensive names it can be low or negative.

Read the full file on GitHub · 63 lines

Changes

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.

  1. 3d ago First seen · 63 lines · 107 tokens per session scan A 12fc7ed7f4e6

Subscribe to this mod's changes

fundamentals-pit is a skill published in the GitHub repository BlueWaterCorp/RiskModels_API (0 stars, last pushed 3d ago), licensed Apache-2.0. It adds 107 tokens to every session and 816 once invoked, about $0.0005 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 2026-09-04.

Related

Other skills, from other repositories